MCP Server Reference

The MCP server exposes 114 tools from the live registry.

Registry Summary

The current registry contains 114 tools (107 in the core allTools registry plus 7 runtime task tools).

| Category | Count | Description | | -------------------------- | ----: | -------------------------------------------------------------- | | Core WU Operations | 7 | Context and primary WU lifecycle operations. | | Extended WU Lifecycle | 20 | WU maintenance, recovery, prep, and cleanup flows. | | Initiatives | 8 | Initiative planning, assignment, and status operations. | | Memory | 13 | Session memory, checkpoints, recovery, and coordination flows. | | Agent | 5 | Agent session lifecycle and issue capture operations. | | Orchestration & Delegation | 4 | Initiative orchestration, monitoring, and delegation helpers. | | Flow & Metrics | 3 | Flow analysis and metrics tooling. | | Validation | 5 | Validation and health-check operations. | | Setup & Bootstrap | 15 | Initialization, onboarding, and environment setup flows. | | Parity & Utilities | 27 | File, git, plan, state, config, and parity helpers. | | Runtime Task Tools | 7 | Kernel runtime task lifecycle tools. |

Tool Reference

Core WU Operations

Context and primary WU lifecycle operations.

context_get

Get current LumenFlow context including location, git state, and active WU

Input: None

gates_run

Run LumenFlow quality gates (lint, typecheck, tests)

Input:

| Parameter | Type | Required | Description | | --------------- | ------- | -------- | ------------------------------------------------------------ | | docs_only | boolean | No | Run docs-only gates (skip lint/typecheck/tests) | | full_lint | boolean | No | Run full lint instead of incremental | | full_tests | boolean | No | Run full test suite instead of incremental | | full_coverage | boolean | No | Force full test suite and coverage gate (implies full_tests) | | coverage_mode | string | No | Coverage gate mode: “warn” or “block” | | verbose | boolean | No | Stream output in agent mode instead of logging to file |

wu_claim

Claim a Work Unit and create worktree for implementation

Input:

| Parameter | Type | Required | Description | | ----------------- | -------- | -------- | ------------------------------------------------------------------------------ | | id | string | Yes | WU ID to claim (e.g., WU-1234) | | lane | string | Yes | Lane for the WU | | cloud | boolean | No | Use cloud/branch-pr mode (no worktree, PR-based completion for cloud agents) | | branch_only | boolean | No | Use branch-only mode (no worktree, direct branch work) | | pr_mode | boolean | No | Use PR mode (create PR instead of auto-merge) | | sandbox | boolean | No | Launch post-claim session through wu:sandbox (requires sandbox_command in MCP) | | sandbox_command | string[] | No | Command argv to run with —sandbox (e.g., [“node”, “-v”]) |

wu_create

Create a new Work Unit specification

Input:

| Parameter | Type | Required | Description | | ------------------- | -------------------------------------------------- | -------- | -------------------------------------------------------- | | id | string | No | WU ID (e.g., WU-1234). Auto-generated if omitted. | | lane | string | Yes | Lane name (e.g., “Framework: Core”) | | title | string | Yes | Work Unit title | | description | string | No | WU description (Context: … Problem: … Solution: …) | | acceptance | string[] | No | Acceptance criteria (array of strings) | | code_paths | string[] | No | Code paths affected by this WU | | test_paths_unit | string[] | No | Unit test file paths | | test_paths_e2e | string[] | No | E2E test file paths | | test_paths_manual | string[] | No | Manual test descriptions | | exposure | “ui” | “api” | “backend-only” | “documentation” | No | Exposure level (ui, api, backend-only, documentation) | | spec_refs | string[] | No | Spec/plan references (lumenflow:// URIs) | | initiative | string | No | Parent initiative (INIT-XXX or slug) | | initiative_phase | integer | No | Canonical initiative_phase field | | priority | string | No | Priority level (P0, P1, P2, P3) | | type | string | No | WU type (feature, bug, refactor, documentation) |

wu_done

Complete a Work Unit (merge, stamp, cleanup). MUST be run from main checkout. Use skip_gate (array of gate names) for explicit per-gate skip. skip_gates is a removed tombstone and is always rejected.

Input:

| Parameter | Type | Required | Description | | ------------ | -------- | -------- | --------------------------------------------------------------------------------------------------------- | | id | string | Yes | WU ID to complete | | skip_gate | string[] | No | Per-gate skip list. Skip only the named gates (must be skippable). Requires reason and fix_wu. | | skip_gates | boolean | No | REMOVED: legacy binary skip-all tombstone. Requests are rejected; use skip_gate with explicit gate names. | | reason | string | No | Reason for skipping gates | | fix_wu | string | No | WU ID that will fix the skipped issue |

wu_list

List all Work Units (WUs) with optional status filter

Input:

| Parameter | Type | Required | Description | | --------- | ------------------------------------------------------------ | -------- | ----------- | | status | “ready” | “in_progress” | “blocked” | “waiting” | “done” | No | | | lane | string | No | |

wu_status

Get detailed status of a specific Work Unit

Input:

| Parameter | Type | Required | Description | | --------- | ------- | -------- | --------------------- | | id | string | Yes | WU ID (e.g., WU-1234) | | json | boolean | No | Output as JSON |

Extended WU Lifecycle

WU maintenance, recovery, prep, and cleanup flows.

wu_block

Block a Work Unit and move it from in_progress to blocked status

Input:

| Parameter | Type | Required | Description | | ----------------- | ------- | -------- | ----------------------------- | | id | string | Yes | WU ID to block | | reason | string | Yes | Reason for blocking | | remove_worktree | boolean | No | Remove worktree when blocking |

wu_brief

Generate handoff prompt for sub-agent WU execution

Input:

| Parameter | Type | Required | Description | | --------------- | ------- | -------- | ----------------------------------------------------------------- | | id | string | Yes | WU ID to spawn | | client | string | No | Target client (e.g. claude-code, codex-cli, gemini-cli) | | thinking | boolean | No | Enable extended thinking | | budget | number | No | Token budget for extended thinking | | parent_wu | string | No | Parent WU ID for orchestrator context | | no_context | boolean | No | Skip memory context injection | | evidence_only | boolean | No | Record wu:brief evidence without generating handoff prompt output |

wu_cleanup

Clean up worktree and branch after PR merge (PR-based completion workflow)

Input:

| Parameter | Type | Required | Description | | ----------- | ------- | -------- | ---------------------- | | id | string | Yes | WU ID to cleanup | | artifacts | boolean | No | Remove build artifacts |

wu_delegate

Generate delegation prompt and record explicit lineage intent

Input:

wu_delete

Safely delete WU YAML files with micro-worktree isolation

Input:

| Parameter | Type | Required | Description | | --------- | ------- | -------- | ------------------------------------------------- | | id | string | Yes | WU ID to delete | | dry_run | boolean | No | Show what would be deleted without making changes | | batch | string | No | Delete multiple WUs (comma-separated) |

wu_deps

Visualize WU dependency graph

Input:

| Parameter | Type | Required | Description | | ----------- | ----------------------------------------- | -------- | ----------------------- | | id | string | Yes | WU ID to analyze | | format | “table” | “json” | “ascii” | “mermaid” | No | Output format | | depth | number | No | Maximum traversal depth | | direction | “up” | “down” | “both” | No | Graph direction |

wu_edit

Edit Work Unit spec fields with micro-worktree isolation

Input:

| Parameter | Type | Required | Description | | ------------------------- | ----------------------------------------------------------------------------------- | -------- | ---------------------------------------------------------------- | | id | string | Yes | WU ID to edit | | description | string | No | New description text | | acceptance | string[] | No | Acceptance criteria to add | | notes | string | No | Notes text to add | | code_paths | string[] | No | Code paths to add | | lane | string | No | New lane assignment | | priority | “P0” | “P1” | “P2” | “P3” | No | New priority | | initiative | string | No | Initiative ID | | initiative_phase | integer | No | Canonical phase number within parent initiative | | estimated_files | integer | No | Sizing estimate: expected number of files modified | | estimated_tool_calls | integer | No | Sizing estimate: expected number of tool calls | | sizing_strategy | “single-session” | “checkpoint-resume” | “orchestrator-worker” | “decomposition” | No | Execution strategy from the sizing guide | | sizing_exception_type | “docs-only” | “shallow-multi-file” | “review-audit” | No | Exception type when sizing thresholds are intentionally exceeded | | sizing_exception_reason | string | No | Justification text (required when sizing_exception_type is set) | | no_strict | boolean | No | Bypass strict validation |

wu_infer_lane

Suggest lane for a WU based on code paths and description

Input:

| Parameter | Type | Required | Description | | --------- | -------- | -------- | ----------------------------- | | id | string | No | WU ID to analyze (reads YAML) | | paths | string[] | No | Code paths to analyze | | desc | string | No | WU description/title text |

wu_preflight

Fast validation of code_paths and test paths before gates run (under 5 seconds vs 2+ minutes)

Input:

| Parameter | Type | Required | Description | | ---------- | ------ | -------- | ---------------------- | | id | string | Yes | WU ID to preflight | | worktree | string | No | Override worktree path |

wu_prep

Prepare WU for completion by running gates in worktree. Use skip_gate (array of gate names) for per-gate skip (requires reason and fix_wu).

Input:

| Parameter | Type | Required | Description | | ------------ | -------- | -------- | ---------------------------------------------------------------------------------------------- | | id | string | Yes | WU ID to prepare | | docs_only | boolean | No | Run docs-only gates | | full_tests | boolean | No | Run test_full once instead of tests.unit or incremental execution | | skip_gate | string[] | No | Per-gate skip list. Skip only the named gates (must be skippable). Requires reason and fix_wu. | | reason | string | No | Reason for skipping gates | | fix_wu | string | No | WU ID that will fix the skipped gate |

wu_proto

Create and claim a prototype WU with relaxed validation

Input:

| Parameter | Type | Required | Description | | ------------- | -------- | -------- | ----------- | | lane | string | No | | | title | string | No | | | description | string | No | | | code_paths | string[] | No | | | labels | string[] | No | | | assigned_to | string | No | |

wu_prune

Lease-aware stale worktree cleanup with quarantine audit evidence (dry-run by default)

Input:

| Parameter | Type | Required | Description | | --------- | ------- | -------- | -------------------------------------------------------------------- | | execute | boolean | No | Execute cleanup (default is dry-run) | | remote | boolean | No | Prune already-merged remote lane branches instead of local worktrees |

wu_rebase

Rebase the claimed Work Unit lane branch onto the integration target (governed); auto-resolves only governed metadata and force-with-lease pushes branch-pr lane branches

Input:

| Parameter | Type | Required | Description | | --------- | ------- | -------- | ----------------------------------------------------- | | id | string | No | WU ID (default: inferred from the lane branch) | | dry_run | boolean | No | Report how far behind the branch is, without rebasing |

wu_recover

Recover WU state, including restoring missing active worktrees

Input:

| Parameter | Type | Required | Description | | --------- | ------------------------------------------------------- | -------- | ------------------------------------------ | | id | string | Yes | WU ID to recover | | action | “resume” | “restore” | “reset” | “nuke” | “cleanup” | No | Recovery action to take | | force | boolean | No | Required for destructive actions like nuke | | json | boolean | No | Output as JSON |

wu_release

Release an orphaned WU from in_progress back to ready state for reclaiming

Input:

| Parameter | Type | Required | Description | | --------- | ------ | -------- | -------------------- | | id | string | Yes | WU ID to release | | reason | string | No | Reason for releasing |

wu_repair

Unified WU repair tool - detect and fix WU state issues

Input:

| Parameter | Type | Required | Description | | -------------- | ------- | -------- | ---------------------- | | id | string | No | WU ID to check/repair | | check | boolean | No | Audit only, no changes | | all | boolean | No | Check/repair all WUs | | claim | boolean | No | Claim repair mode | | admin | boolean | No | Admin repair mode | | repair_state | boolean | No | State repair mode |

wu_sandbox

Run a command through the hardened WU sandbox backend

Input:

| Parameter | Type | Required | Description | | ---------- | -------- | -------- | ----------------------------------------------------------------- | | id | string | Yes | WU ID (e.g., WU-1234) | | worktree | string | No | Optional worktree path override | | command | string[] | Yes | Command argv to execute (e.g., [“node”, “-e”, “process.exit(0)”]) |

wu_unblock

Unblock a Work Unit and move it from blocked to in_progress status

Input:

| Parameter | Type | Required | Description | | ----------------- | ------- | -------- | ------------------------------- | | id | string | Yes | WU ID to unblock | | reason | string | No | Reason for unblocking | | create_worktree | boolean | No | Create worktree when unblocking |

wu_unlock_lane

Safely unlock a lane lock with audit logging

Input:

| Parameter | Type | Required | Description | | --------- | ------- | -------- | --------------------------------- | | lane | string | No | Lane name to unlock | | reason | string | No | Reason for unlocking | | force | boolean | No | Force operation | | list | boolean | No | List all current lane locks | | status | boolean | No | Show detailed status for the lane |

wu_validate

Validate WU YAML files against schema (strict mode by default)

Input:

| Parameter | Type | Required | Description | | ----------- | ------- | -------- | ------------------------ | | id | string | Yes | WU ID to validate | | no_strict | boolean | No | Bypass strict validation |

Initiatives

Initiative planning, assignment, and status operations.

initiative_add_wu

Add a Work Unit to an initiative, optionally assigning to a phase

Input:

| Parameter | Type | Required | Description | | ------------ | ------ | -------- | --------------------------------- | | initiative | string | Yes | Initiative ID to link WU to | | wu | string | Yes | WU ID to add (or array for batch) | | phase | number | No | Phase number to assign (1-based) |

initiative_bulk_assign

Bulk assign WUs to an initiative based on lane prefix rules

Input:

| Parameter | Type | Required | Description | | ---------------------- | ------- | -------- | ---------------------------------------- | | config | string | No | Path to lane bucket configuration file | | apply | boolean | No | Apply changes (default is dry-run) | | sync_from_initiative | string | No | Reconcile WUs from a specific initiative |

initiative_create

Create a new initiative for multi-phase project orchestration

Input:

| Parameter | Type | Required | Description | | ------------- | ------ | -------- | ------------------------------------------------- | | id | string | Yes | Initiative ID (e.g., INIT-001) | | slug | string | Yes | Initiative slug (kebab-case, e.g., my-initiative) | | title | string | Yes | Initiative title | | priority | string | No | Priority level (P0, P1, P2, P3) | | owner | string | No | Owner email or name | | target_date | string | No | Target completion date (YYYY-MM-DD) |

initiative_edit

Edit initiative fields

Input:

| Parameter | Type | Required | Description | | ----------------------- | ---------------------------------------------------------- | -------- | ------------------------------------------------- | | id | string | Yes | Initiative ID to edit | | status | “draft” | “open” | “in_progress” | “done” | “archived” | No | New initiative status | | blocked_by | string | No | Initiative ID that blocks this initiative | | blocked_reason | string | No | Reason for blocking | | unblock | boolean | No | Remove blocked_by and blocked_reason fields | | add_lane | string[] | No | Lanes to add (repeatable) | | remove_lane | string[] | No | Lanes to remove (repeatable) | | notes | string | No | Note to append to notes array | | description | string | No | Replace the initiative description field | | add_phase | string[] | No | Phase titles to add (repeatable) | | add_success_metric | string[] | No | Success metrics to add (repeatable, deduplicated) | | phase_id | string | No | Phase ID to update (use with phase_status) | | phase_status | “pending” | “in_progress” | “done” | “blocked” | No | New phase status | | phase_title | string | No | New phase title | | created | string | No | Set created date (YYYY-MM-DD format) | | phase_execution_order | “sequential” | “parallel” | No | Phase execution order (sequential or parallel) | | dependency_model | string | No | Dependency model for the initiative |

initiative_list

List all initiatives with optional status filter

Input:

| Parameter | Type | Required | Description | | --------- | ----------------- | -------- | --------------------------- | | status | string | No | Filter by initiative status | | format | “table” | “json” | No | Output format (table, json) | | color | boolean | No | Enable colored output |

initiative_plan

Link an existing plan or create a new plan template for an initiative

Input:

| Parameter | Type | Required | Description | | ------------ | ------- | -------- | --------------------------------------------- | | initiative | string | Yes | Initiative ID to link plan to | | plan | string | No | Path to existing plan file (markdown) | | create | boolean | No | Create a new plan template instead of linking |

initiative_remove_wu

Remove a Work Unit from an initiative

Input:

| Parameter | Type | Required | Description | | ------------ | ------ | -------- | ------------------------------- | | initiative | string | Yes | Initiative ID to unlink WU from | | wu | string | Yes | WU ID to remove |

initiative_status

Get detailed status of a specific initiative including WUs and progress

Input:

| Parameter | Type | Required | Description | | --------- | ----------------- | -------- | --------------------------- | | id | string | Yes | Initiative ID or slug | | format | “table” | “json” | No | Output format (table, json) | | color | boolean | No | Enable colored output |

Memory

Session memory, checkpoints, recovery, and coordination flows.

mem_checkpoint

Save a progress checkpoint for a Work Unit

Input:

| Parameter | Type | Required | Description | | ------------ | ------ | -------- | ------------------------------------------- | | wu | string | Yes | WU ID to checkpoint | | message | string | No | Checkpoint message | | session | string | No | Session ID to link checkpoint to (UUID) | | progress | string | No | Progress summary | | next_steps | string | No | Next steps description | | trigger | string | No | Handoff trigger type (e.g., clear, handoff) |

mem_cleanup

Clean up stale memory data

Input:

| Parameter | Type | Required | Description | | ------------ | ------- | -------- | ----------------------------------------------------- | | dry_run | boolean | No | Preview cleanup without making changes | | ttl | string | No | Remove nodes older than duration (e.g., 30d, 7d, 24h) | | session_id | string | No | Session ID to consider closed |

mem_converged

Evaluate whether every recipient on an A2A signal thread has posted AGREE

Input:

| Parameter | Type | Required | Description | | --------- | ------- | -------- | ----------------------------------------- | | thread | string | Yes | A2A thread ID to evaluate | | quiet | boolean | No | Suppress detail output; rely on exit code |

mem_create

Create a memory node (e.g., for bug discovery)

Input:

| Parameter | Type | Required | Description | | ----------------- | -------- | -------- | ------------------------------------------------------ | | message | string | Yes | Memory node message | | wu | string | No | WU ID to associate with | | type | string | No | Node type (e.g., discovery, session, checkpoint, note) | | tags | string[] | No | Tags for the node | | discovered_from | string | No | Parent node ID for provenance tracking | | session | string | No | Session ID to link node to (UUID) | | priority | string | No | Priority level (P0, P1, P2, P3) |

mem_delete

Delete or archive a memory node

Input:

| Parameter | Type | Required | Description | | ------------ | ------- | -------- | -------------------------------------------- | | id | string | Yes | Memory node ID to delete | | tag | string | No | Delete all nodes matching this tag | | older_than | string | No | Delete nodes older than duration (e.g., 30d) | | dry_run | boolean | No | Preview deletion without making changes |

mem_export

Export memory for a Work Unit as markdown or JSON

Input:

| Parameter | Type | Required | Description | | ----------- | -------------------- | -------- | ----------------------------------------------------- | | wu | string | Yes | WU ID to export | | format | “markdown” | “json” | No | Export format | | type | string | No | Filter by node type | | lifecycle | string | No | Filter by lifecycle (ephemeral, session, wu, project) |

mem_inbox

Check coordination signals from other agents

Input:

| Parameter | Type | Required | Description | | --------- | ------ | -------- | ---------------------------------------------------- | | since | string | No | Time filter (e.g., “30m”, “1h”) | | wu | string | No | Filter by WU ID | | lane | string | No | Filter by lane | | for | string | No | Reader identity/session to evaluate unread state for | | thread | string | No | Filter by A2A thread ID | | intent | string | No | Comma-separated A2A intents to include |

mem_init

Initialize memory layer for a Work Unit

Input:

| Parameter | Type | Required | Description | | --------- | ------ | -------- | ------------------------------ | | wu | string | No | WU ID to initialize memory for |

mem_ready

Check pending memory nodes for a Work Unit

Input:

| Parameter | Type | Required | Description | | --------- | ----------------- | -------- | -------------------------------- | | wu | string | Yes | WU ID to check pending nodes for | | type | string | No | Filter by node type | | format | “json” | “human” | No | Output format |

mem_recover

Generate recovery context after compaction for a Work Unit

Input:

| Parameter | Type | Required | Description | | ---------- | ----------------- | -------- | ----------- | | wu | string | No | | | max_size | number | No | | | format | “json” | “human” | No | | | quiet | boolean | No | | | base_dir | string | No | |

mem_start

Start a memory session for a Work Unit

Input:

| Parameter | Type | Required | Description | | -------------- | ------ | -------- | ---------------------------------------------------------- | | wu | string | Yes | WU ID to start session for | | lane | string | No | Lane name | | agent_type | string | No | Agent type (e.g., general-purpose, explore, test-engineer) | | context_tier | string | No | Context tier (core, full, minimal) |

mem_summarize

Summarize memory context for a Work Unit

Input:

| Parameter | Type | Required | Description | | --------- | ------- | -------- | -------------------------------------- | | wu | string | Yes | WU ID to summarize | | dry_run | boolean | No | Preview summary without making changes |

mem_triage

Triage discovered bugs for a Work Unit, optionally promoting to WU

Input:

| Parameter | Type | Required | Description | | --------- | ------ | -------- | ----------------------------------- | | wu | string | No | WU ID to triage discoveries for | | promote | string | No | Memory node ID to promote to Bug WU | | lane | string | No | Lane for promoted Bug WU | | archive | string | No | Memory node ID to archive | | reason | string | No | Reason for archiving |

Agent

Agent session lifecycle and issue capture operations.

agent_issues_query

Query and display logged agent incidents/issues summary

Input:

| Parameter | Type | Required | Description | | ---------- | -------------------------------------------- | -------- | ---------------------------- | | since | number | No | Days to include (default: 7) | | category | string | No | Filter by category | | severity | “blocker” | “major” | “minor” | “trivial” | No | Filter by severity |

agent_log_issue

Log a workflow issue or incident during agent execution

Input:

| Parameter | Type | Required | Description | | ------------- | ---------------------------------------------------------------- | -------- | -------------------------------------------- | | category | “workflow” | “tooling” | “confusion” | “violation” | “error” | Yes | Issue category | | severity | “blocker” | “major” | “minor” | “info” | Yes | Severity level | | title | string | Yes | Short description (5-100 chars) | | description | string | Yes | Detailed context (10-2000 chars) | | resolution | string | No | How the issue was resolved | | tags | string[] | No | Tags for categorization | | step | string | No | Current workflow step (e.g., wu:done, gates) | | files | string[] | No | Related file paths |

agent_resolve

Show effective vendor model routing (model_profile → model) per agent

Input:

| Parameter | Type | Required | Description | | -------------- | ------- | -------- | ----------- | | client | string | No | | | json | boolean | No | | | no_telemetry | boolean | No | |

agent_session

Start an agent session for tracking WU execution

Input:

| Parameter | Type | Required | Description | | ------------ | ------ | -------- | --------------------------------- | | wu | string | Yes | WU ID to work on (e.g., WU-1234) | | tier | number | Yes | Context tier (1, 2, or 3) | | agent_type | string | No | Agent type (default: claude-code) |

agent_session_end

End the current agent session and return summary

Input: None

Orchestration & Delegation

Initiative orchestration, monitoring, and delegation helpers.

delegation_list

Display delegation and launch records for WUs or initiatives

Input:

| Parameter | Type | Required | Description | | ------------ | ------- | -------- | ---------------------------------------------------------------------- | | wu | string | No | WU ID to show delegation / launch records for (e.g., WU-1234) | | initiative | string | No | Initiative ID to show delegation / launch records for (e.g., INIT-001) | | json | boolean | No | Output as JSON |

orchestrate_init_status

Show compact initiative status including evidence-based orchestration state

Input:

| Parameter | Type | Required | Description | | ------------ | ------ | -------- | -------------------------------------- | | initiative | string | Yes | Initiative ID or slug (e.g., INIT-001) |

orchestrate_initiative

Plan, launch, and reconcile initiative execution with structured orchestration artifacts

Input:

| Parameter | Type | Required | Description | | --------------------- | ------- | -------- | -------------------------------------------------------------------- | | initiative | string | Yes | Initiative ID to orchestrate (e.g., INIT-001) | | dry_run | boolean | No | Show the logical wave plan without launching or refreshing workers | | progress | boolean | No | Show current reconciled progress only | | checkpoint_per_wave | boolean | No | Process one logical wave / launch attempt, then exit without polling |

orchestrate_monitor

Monitor orchestration progress, stalls, returned workers, and recovery signals

Input:

| Parameter | Type | Required | Description | | -------------- | ------- | -------- | -------------------------------------------------------------- | | threshold | number | No | Stuck detection threshold in minutes (default: 30) | | recover | boolean | No | Run recovery actions for stuck spawns | | dry_run | boolean | No | Show what would be done without taking action | | since | string | No | Show recent signals/checkpoints since (e.g., 30m, 1h) | | wu | string | No | Filter by WU ID | | signals_only | boolean | No | Only show signal traffic (skip broader orchestration evidence) |

Flow & Metrics

Flow analysis and metrics tooling.

flow_bottlenecks

Identify flow bottlenecks in the workflow (WIP violations, stuck WUs, etc.)

Input:

| Parameter | Type | Required | Description | | --------- | ------------------------------ | -------- | -------------------------------------------------------------- | | limit | number | No | Number of bottlenecks to show (default: 10) | | format | “json” | “table” | “mermaid” | No | Output format for bottleneck diagnostics: json, table, mermaid | | json | boolean | No | Output as JSON (shorthand for —format json) |

lumenflow_metrics

View workflow metrics (lumenflow:metrics alias)

Input:

| Parameter | Type | Required | Description | | ------------ | ------------------------------------ | -------- | ------------------------------------------- | | subcommand | “lanes” | “dora” | “flow” | “all” | No | Metrics subcommand (lanes, dora, flow, all) | | format | “json” | “table” | No | Output format | | days | number | No | Days window for metrics calculation | | output | string | No | Custom output file path | | dry_run | boolean | No | Preview without writing |

metrics

View workflow metrics (lanes, dora, flow, all)

Input:

Validation

Validation and health-check operations.

validate

Validate WU YAML files and status consistency

Input:

| Parameter | Type | Required | Description | | ----------- | ------- | -------- | -------------------------- | | id | string | No | Specific WU ID to validate | | strict | boolean | No | Fail on warnings too | | done_only | boolean | No | Only validate done WUs |

validate_agent_skills

Validate canonical LumenFlow skill definitions and projected vendor skills

Input:

| Parameter | Type | Required | Description | | --------- | ------ | -------- | ------------------------------------------------- | | skill | string | No | Specific skill to validate (e.g., “wu-lifecycle”) |

validate_agent_sync

Validate agent synchronization state

Input: None

validate_backlog_sync

Validate backlog synchronization between WU YAMLs and backlog.md

Input: None

validate_skills_spec

Validate skills specification files

Input: None

Setup & Bootstrap

Initialization, onboarding, and environment setup flows.

cloud_connect

Connect workspace.yaml to cloud control plane

Input:

| Parameter | Type | Required | Description | | --------------- | --------------------------------------------------- | -------- | ----------- | | endpoint | string | No | | | org_id | string | No | | | project_id | string | No | | | token_env | string | No | | | policy_mode | “authoritative” | “tighten-only” | “dev-override” | No | | | sync_interval | integer | No | | | output | string | No | | | force | boolean | No | |

lumenflow

Initialize LumenFlow in a project

Input:

| Parameter | Type | Required | Description | | ----------- | ------- | -------- | -------------------------------------------------------- | | client | string | No | Client type (claude, cursor, windsurf, codex, all, none) | | merge | boolean | No | Merge into existing files using bounded markers | | full | boolean | No | Add docs + agent onboarding + task scaffolding | | minimal | boolean | No | Skip agent onboarding docs (only core files) | | framework | string | No | Add framework hint + overlay docs |

lumenflow_commands

List all available LumenFlow CLI commands

Input: None

lumenflow_docs_sync

Sync agent documentation after upgrading LumenFlow packages

Input: None

lumenflow_doctor

Diagnose LumenFlow configuration and safety components

Input: None

lumenflow_gates

Run quality gates (lumenflow-gates alias)

Input:

lumenflow_init

Initialize LumenFlow workflow framework in a project

Input:

lumenflow_integrate

Generate enforcement hooks for a specific client (e.g., claude-code)

Input:

| Parameter | Type | Required | Description | | --------- | ------ | -------- | --------------------------------------------------------------- | | client | string | Yes | Target client (e.g. claude-code, codex-cli, cursor, gemini-cli) |

lumenflow_onboard

Interactive setup wizard for LumenFlow workspace (alias)

Input:

| Parameter | Type | Required | Description | | ------------------- | ------------------------------------------ | -------- | ----------- | | yes | boolean | No | | | domain | “software-delivery” | “infra” | “custom” | No | | | project_name | string | No | | | output | string | No | | | force | boolean | No | | | skip_pack_install | boolean | No | | | skip_dashboard | boolean | No | |

lumenflow_release

Run LumenFlow release workflow (versioning, npm publish)

Input:

| Parameter | Type | Required | Description | | --------- | ------- | -------- | ---------------------------------- | | dry_run | boolean | No | Preview release without publishing |

lumenflow_sync_templates

Sync LumenFlow templates to the project

Input: None

lumenflow_upgrade

Upgrade LumenFlow packages to latest versions

Input: None

lumenflow_validate

Run validation checks (lumenflow-validate alias)

Input:

onboard

Interactive setup wizard for LumenFlow workspace

Input:

workspace_init

Initialize workspace.yaml from interactive prompts

Input:

| Parameter | Type | Required | Description | | --------- | ------- | -------- | ----------- | | yes | boolean | No | | | output | string | No | | | force | boolean | No | |

Parity & Utilities

File, git, plan, state, config, and parity helpers.

backlog_prune

Clean stale backlog entries and archive old completed WUs

Input:

| Parameter | Type | Required | Description | | ------------------------ | ------- | -------- | ----------- | | execute | boolean | No | | | dry_run | boolean | No | | | stale_days_in_progress | number | No | | | stale_days_ready | number | No | | | archive_days | number | No | |

cert_verify

Verify an agent promotion-ladder transition against certification evidence

Input:

| Parameter | Type | Required | Description | | --------------- | ------- | -------- | ----------- | | agent_id | string | No | | | agent_version | string | No | | | current_state | string | No | | | target_state | string | No | | | evidence_dir | string | No | | | json | boolean | No | |

config_get

Read and display a value from workspace.yaml

Input:

| Parameter | Type | Required | Description | | --------- | ------ | -------- | ----------- | | key | string | No | |

config_set

Safely update workspace.yaml via micro-worktree

Input:

| Parameter | Type | Required | Description | | --------- | ------ | -------- | ----------- | | key | string | No | | | value | string | No | |

config_unset

Safely delete a key from workspace.yaml via micro-worktree

Input:

| Parameter | Type | Required | Description | | --------- | ------ | -------- | ----------- | | key | string | No | |

docs_sync

Sync agent onboarding docs and skills to existing projects

Input:

| Parameter | Type | Required | Description | | --------- | ------- | -------- | ----------- | | force | boolean | No | |

eval_run

Run a certification scenario suite against an agent evaluation report

Input:

| Parameter | Type | Required | Description | | --------------- | ------- | -------- | ----------- | | agent_id | string | No | | | agent_version | string | No | | | report | string | No | | | suite | string | No | | | evidence_dir | string | No | | | json | boolean | No | |

eval_suite

Define, list, and validate agent certification scenario suites

Input:

| Parameter | Type | Required | Description | | ---------- | ------- | -------- | ----------- | | suite | string | No | | | show | string | No | | | validate | string | No | | | json | boolean | No | |

file_delete

Delete files or directories with safety flags

Input:

| Parameter | Type | Required | Description | | ----------- | ------- | -------- | ----------- | | path | string | No | | | recursive | boolean | No | | | force | boolean | No | |

file_edit

Edit a file via exact string replacement

Input:

| Parameter | Type | Required | Description | | ------------- | ------- | -------- | ----------- | | path | string | No | | | old_string | string | No | | | new_string | string | No | | | encoding | string | No | | | replace_all | boolean | No | |

file_read

Read a file with optional line ranges and encoding

Input:

| Parameter | Type | Required | Description | | ------------ | ------ | -------- | ----------- | | path | string | No | | | encoding | string | No | | | start_line | number | No | | | end_line | number | No | | | max_size | number | No | |

file_write

Write content to a file with audit trail

Input:

| Parameter | Type | Required | Description | | ---------------- | ------- | -------- | ----------- | | path | string | No | | | content | string | No | | | encoding | string | No | | | no_create_dirs | boolean | No | |

gates

Run LumenFlow quality gates

Input:

gates_docs

Run docs-only quality gates

Input:

git_branch

Show git branch listing and current branch

Input:

| Parameter | Type | Required | Description | | -------------- | ------- | -------- | ----------- | | list | boolean | No | | | all | boolean | No | | | remotes | boolean | No | | | show_current | boolean | No | | | contains | string | No | |

git_diff

Show git diff with staged/name-only/stat modes

Input:

| Parameter | Type | Required | Description | | ----------- | ------- | -------- | ----------- | | ref | string | No | | | staged | boolean | No | | | name_only | boolean | No | | | stat | boolean | No | | | path | string | No | |

git_log

Show git commit log with filters

Input:

| Parameter | Type | Required | Description | | ----------- | ------- | -------- | ----------- | | ref | string | No | | | oneline | boolean | No | | | max_count | number | No | | | format | string | No | | | since | string | No | | | author | string | No | |

git_status

Show git status with optional porcelain/short modes

Input:

| Parameter | Type | Required | Description | | ----------- | ------- | -------- | ----------- | | path | string | No | | | porcelain | boolean | No | | | short | boolean | No | |

git_sync_main

Fast-forward a clean primary main checkout to origin/main

Input:

| Parameter | Type | Required | Description | | ---------- | ------ | -------- | ----------- | | base_dir | string | No | |

init_plan

Link or create a plan for an initiative

Input:

lane_health

Check lane configuration health (overlaps and coverage gaps)

Input:

| Parameter | Type | Required | Description | | ------------- | ------- | -------- | ----------- | | json | boolean | No | | | verbose | boolean | No | | | no_coverage | boolean | No | |

lane_suggest

Generate lane suggestions from codebase context

Input:

| Parameter | Type | Required | Description | | ------------- | ------- | -------- | ----------- | | dry_run | boolean | No | | | interactive | boolean | No | | | output | string | No | | | json | boolean | No | | | no_llm | boolean | No | | | include_git | boolean | No | |

signal_cleanup

Cleanup stale signals using TTL policy

Input:

| Parameter | Type | Required | Description | | ------------- | ------- | -------- | ----------- | | dry_run | boolean | No | | | ttl | string | No | | | unread_ttl | string | No | | | max_entries | number | No | | | json | boolean | No | | | quiet | boolean | No | | | base_dir | string | No | |

state_bootstrap

Bootstrap state store from existing WU YAML files

Input:

| Parameter | Type | Required | Description | | ----------- | ------- | -------- | ----------- | | execute | boolean | No | | | dry_run | boolean | No | | | force | boolean | No | | | wu_dir | string | No | | | state_dir | string | No | |

state_cleanup

Clean stale state, memory, and signal data

Input:

| Parameter | Type | Required | Description | | -------------- | ------- | -------- | ----------- | | dry_run | boolean | No | | | signals_only | boolean | No | | | memory_only | boolean | No | | | events_only | boolean | No | | | json | boolean | No | | | quiet | boolean | No | | | base_dir | string | No | |

state_doctor

Diagnose state store integrity issues

Input:

| Parameter | Type | Required | Description | | ---------- | ------- | -------- | ----------- | | fix | boolean | No | | | dry_run | boolean | No | | | json | boolean | No | | | quiet | boolean | No | | | base_dir | string | No | |

sync_templates

Sync internal docs to CLI templates

Input:

| Parameter | Type | Required | Description | | ------------- | ------- | -------- | ----------- | | dry_run | boolean | No | | | verbose | boolean | No | | | check_drift | boolean | No | |

Runtime Task Tools

Kernel runtime task lifecycle tools.

task_block

Block a task directly through KernelRuntime (no CLI shell-out).

Input:

| Parameter | Type | Required | Description | | ----------- | ------ | -------- | ----------- | | task_id | string | Yes | | | reason | string | Yes | | | timestamp | string | No | |

task_claim

Claim a task directly through KernelRuntime (no CLI shell-out).

Input:

| Parameter | Type | Required | Description | | ------------- | ------ | -------- | ----------- | | task_id | string | Yes | | | domain_data | object | No | |

task_complete

Complete a task directly through KernelRuntime (no CLI shell-out).

Input:

| Parameter | Type | Required | Description | | --------------- | -------- | -------- | ----------- | | task_id | string | Yes | | | run_id | string | No | | | evidence_refs | string[] | No | |

task_create

Create a task directly through KernelRuntime (no CLI shell-out).

Input:

| Parameter | Type | Required | Description | | -------------------------- | ----------------------------------------- | -------- | ----------- | | lane_id | string | Yes | | | domain | string | Yes | | | title | string | Yes | | | description | string | Yes | | | acceptance | array | object | Yes | | | expected_artifacts | string[] | No | | | risk | “low” | “medium” | “high” | “critical” | Yes | | | blocks | string[] | No | | | blocked_by | string[] | No | | | execution_policy_profile | string | No | | | extensions | object | No | | | type | string | Yes | | | priority | “P0” | “P1” | “P2” | “P3” | Yes | | | labels | string[] | No | |

task_inspect

Inspect a task directly through KernelRuntime (no CLI shell-out).

Input:

| Parameter | Type | Required | Description | | --------- | ------ | -------- | ----------- | | task_id | string | Yes | |

task_unblock

Unblock a task directly through KernelRuntime (no CLI shell-out).

Input:

| Parameter | Type | Required | Description | | ----------- | ------ | -------- | ----------- | | task_id | string | Yes | | | timestamp | string | No | |

tool_execute

Execute a tool directly through KernelRuntime (no CLI shell-out).

Input:

| Parameter | Type | Required | Description | | -------------------- | ------- | -------- | ----------- | | tool_name | string | Yes | | | tool_input | unknown | No | | | execution_selector | object | Yes | |

Next Steps

CLI Commands – Public command reference
Kernel Runtime – Tool execution pipeline
Tool Execution – Dispatch and sandboxing