compound-agent 1.2.2 → 1.2.4

package/CHANGELOG.md

@@ -9,6 +9,20 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 
 ## [Unreleased]
 
+## [1.2.4] - 2026-02-15
+
+### Changed
+
+- **lfg.md delegates phases to slash commands**: Instead of inlining all 5 phase workflows (~80 lines), lfg.md now invokes `/compound:{brainstorm,plan,work,review,compound}`. This prevents phase instructions from being compacted away by late phases.
+- **lfg.md slimmed to thin orchestrator**: Reduced from ~2200 to ~1324 characters. Removed inlined Purpose, Stop Conditions, and Memory Integration sections.
+- **Phase gates relocated to individual commands**: PHASE GATE 3 moved to work.md, PHASE GATE 4 to review.md, FINAL GATE to compound.md — gates now survive compaction.
+- **YAML frontmatter on all 13 command templates**: Each template now has name, description, and argument-hint metadata. lfg.md additionally uses `disable-model-invocation: true`.
+- **Anti-MEMORY.md guardrails**: compound.md and review.md now explicitly warn against using MEMORY.md for lesson storage, directing Claude to use `memory_capture` MCP tool instead.
+
+### Fixed
+
+- **Phase 5 context drift**: Claude no longer falls back to MEMORY.md during compound phase because each phase loads fresh instructions from its dedicated slash command.
+
 ## [1.2.1] - 2026-02-15
 
 ### Added
@@ -456,7 +470,8 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
   - Vitest test suite
   - tsup build configuration
 
-[Unreleased]: https://github.com/Nathandela/learning_agent/compare/v1.2.1...HEAD
+[Unreleased]: https://github.com/Nathandela/learning_agent/compare/v1.2.4...HEAD
+[1.2.4]: https://github.com/Nathandela/learning_agent/compare/v1.2.1...v1.2.4
 [1.2.1]: https://github.com/Nathandela/learning_agent/compare/v1.2.0...v1.2.1
 [1.2.0]: https://github.com/Nathandela/learning_agent/compare/v1.1.0...v1.2.0
 [1.1.0]: https://github.com/Nathandela/learning_agent/compare/v1.0.0...v1.1.0

package/dist/cli.js

@@ -2881,7 +2881,12 @@ var AGENT_TEMPLATES = {
 
 // src/setup/templates/commands.ts
 var WORKFLOW_COMMANDS = {
-  "brainstorm.md": `$ARGUMENTS
+  "brainstorm.md": `---
+name: compound:brainstorm
+description: Explore requirements through collaborative dialogue before committing to a plan
+argument-hint: "<goal or topic to brainstorm>"
+---
+$ARGUMENTS
 
 # Brainstorm
 
@@ -2889,7 +2894,7 @@ var WORKFLOW_COMMANDS = {
 Explore requirements through collaborative dialogue before committing to a plan.
 
 ## Workflow
-1. Parse the topic from \`$ARGUMENTS\`. If empty, ask the user what to brainstorm.
+1. Parse the topic from the arguments above. If empty, ask the user what to brainstorm.
 2. Call \`memory_search\` with the topic to surface relevant past lessons. Display retrieved items and incorporate them into exploration.
 3. Create a research team and spawn explorers in parallel:
    \`\`\`
@@ -2906,12 +2911,10 @@ Explore requirements through collaborative dialogue before committing to a plan.
 7. Run \`bd ready\` to check if related tasks already exist.
 8. Output a clear problem definition, chosen approach, and open questions.
 9. Create a beads epic from conclusions:
-   \`\`\`bash
-   bd create --title="<epic title>" --type=feature --description="<problem definition + approach + scope>"
-   \`\`\`
+   bd create --title="(epic title)" --type=feature --description="(problem definition + approach + scope)"
 10. For each significant decision, auto-create an ADR in \`docs/decisions/\`:
     - Scan \`docs/decisions/\` for the highest existing number, increment by 1
-    - Write \`docs/decisions/NNN-<kebab-title>.md\` using this template:
+    - Write docs/decisions/NNN-(kebab-title).md using this template:
       \`\`\`markdown
       # NNN. <Title>
       Status: accepted
@@ -2941,7 +2944,12 @@ Explore requirements through collaborative dialogue before committing to a plan.
 - Create a beads epic from brainstorm conclusions with \`bd create --type=feature\`.
 - If the brainstorm identifies sub-tasks, suggest creating them with \`bd create\`.
 `,
-  "plan.md": `$ARGUMENTS
+  "plan.md": `---
+name: compound:plan
+description: Create a structured implementation plan with concrete tasks and dependencies
+argument-hint: "<goal or epic to plan>"
+---
+$ARGUMENTS
 
 # Plan
 
@@ -2949,7 +2957,7 @@ Explore requirements through collaborative dialogue before committing to a plan.
 Create a structured implementation plan enriched by semantic memory and existing documentation, with concrete tasks and dependencies.
 
 ## Workflow
-1. Parse the goal from \`$ARGUMENTS\`. If empty, ask the user what to plan.
+1. Parse the goal from the arguments above. If empty, ask the user what to plan.
 2. Check for brainstorm output: run \`bd list\` to find a related brainstorm epic. If one exists, read its description for decisions and open questions.
 3. Call \`memory_search\` with the goal to retrieve relevant past lessons. Display retrieved memory items and incorporate them into planning context.
 4. Create a research team and spawn analysts in parallel:
@@ -2967,26 +2975,20 @@ Create a structured implementation plan enriched by semantic memory and existing
 6. Use \`AskUserQuestion\` to resolve ambiguities: unclear requirements, conflicting ADRs, or priority trade-offs that need user input before decomposing.
 7. Break the goal into concrete, ordered tasks with clear acceptance criteria.
 8. **Create review and compound blocking tasks** so they survive compaction:
-   \`\`\`bash
-   bd create --title="Review: /compound:review" --type=task --priority=1
-   bd create --title="Compound: /compound:compound" --type=task --priority=1
-   bd dep add <review-id> <last-work-task>   # review depends on work
-   bd dep add <compound-id> <review-id>       # compound depends on review
-   \`\`\`
+   - bd create --title="Review: /compound:review" --type=task --priority=1
+   - bd create --title="Compound: /compound:compound" --type=task --priority=1
+   - bd dep add (review-id) (last-work-task)   -- review depends on work
+   - bd dep add (compound-id) (review-id)       -- compound depends on review
    These tasks surface via \`bd ready\` after work completes, ensuring review and compound phases are never skipped \u2014 even after context compaction.
 9. Create beads issues and map dependencies:
-   \`\`\`bash
-   bd create --title="<task>" --type=task --priority=<1-4>
-   bd dep add <dependent-task> <blocking-task>
-   \`\`\`
+   - bd create --title="(task)" --type=task --priority=(1-4)
+   - bd dep add (dependent-task) (blocking-task)
 10. Output the plan as a structured list with task IDs and dependency graph.
 
 ## POST-PLAN VERIFICATION -- MANDATORY
 After creating all tasks, verify review and compound tasks exist:
-\`\`\`bash
-bd list --status=open | grep 'Review:'    # Must show a result
-bd list --status=open | grep 'Compound:'  # Must show a result
-\`\`\`
+- Run bd list --status=open and check for a "Review:" task
+- Run bd list --status=open and check for a "Compound:" task
 If either is missing, CREATE THEM NOW. The plan is NOT complete without these gates.
 
 ## Memory Integration
@@ -3002,10 +3004,15 @@ If either is missing, CREATE THEM NOW. The plan is NOT complete without these ga
 ## Beads Integration
 - Create one \`bd\` issue per task with \`bd create\`.
 - Set priority (1=critical, 4=low) based on dependency order.
-- Map dependencies with \`bd dep add <dependent> <blocker>\`.
+- Map dependencies with bd dep add (dependent) (blocker).
 - Each task should include acceptance criteria in its description.
 `,
-  "work.md": `$ARGUMENTS
+  "work.md": `---
+name: compound:work
+description: Execute implementation by delegating to an agent team
+argument-hint: "<task ID or description>"
+---
+$ARGUMENTS
 
 # Work
 
@@ -3013,8 +3020,8 @@ If either is missing, CREATE THEM NOW. The plan is NOT complete without these ga
 Execute implementation by delegating to an agent team. The lead coordinates and does not code directly.
 
 ## Workflow
-1. Parse task from \`$ARGUMENTS\`. If empty, run \`bd ready\` to find available tasks.
-2. Mark task in progress: \`bd update <id> --status=in_progress\`.
+1. Parse task from the arguments above. If empty, run \`bd ready\` to find available tasks.
+2. Mark task in progress: bd update (id) --status=in_progress.
 3. Call \`memory_search\` with the task description to retrieve relevant lessons. Run \`memory_search\` per agent/subtask so each gets targeted context. Display retrieved lessons in your response. Do not silently discard memory results.
 4. Assess complexity to determine team strategy.
 5. If **trivial** (config changes, typos, one-line fixes): handle directly with a single subagent. No AgentTeam needed. Proceed to step 10.
@@ -3040,11 +3047,11 @@ Execute implementation by delegating to an agent team. The lead coordinates and
 12. Shut down the team when done: send \`shutdown_request\` to all teammates.
 13. Commit incrementally as tests pass \u2014 do not batch all commits to the end.
 14. Run the full test suite to check for regressions.
-15. Close the task: \`bd close <id>\`.
+15. Close the task: bd close (id).
 
 ## MANDATORY VERIFICATION -- DO NOT CLOSE TASK WITHOUT THIS
 STOP. Before running \`bd close\`, you MUST:
-1. Run \`pnpm test && pnpm lint\` (quality gates)
+1. Run pnpm test, then pnpm lint (quality gates)
 2. Run /implementation-reviewer on the changed code
 3. Wait for APPROVED status
 If /implementation-reviewer returns REJECTED: fix ALL issues, re-run tests, resubmit.
@@ -3060,10 +3067,21 @@ for complex changes. For all changes, /implementation-reviewer is the minimum re
 
 ## Beads Integration
 - Start with \`bd ready\` to pick work.
-- Update status with \`bd update <id> --status=in_progress\`.
-- Close with \`bd close <id>\` when all tests pass.
+- Update status with bd update (id) --status=in_progress.
+- Close with bd close (id) when all tests pass.
+
+## PHASE GATE 3 -- MANDATORY
+Before starting Review, verify ALL work tasks are closed:
+- Run bd list with status in_progress -- must return empty
+- Run bd list with status open -- only Review and Compound tasks should remain
+If any work tasks remain open, DO NOT proceed. Complete them first.
 `,
-  "review.md": `$ARGUMENTS
+  "review.md": `---
+name: compound:review
+description: Multi-agent code review with severity classification and mandatory gate
+argument-hint: "<scope or git diff range>"
+---
+$ARGUMENTS
 
 # Review
 
@@ -3071,8 +3089,8 @@ for complex changes. For all changes, /implementation-reviewer is the minimum re
 Multi-agent code review with severity classification and a mandatory \`/implementation-reviewer\` gate.
 
 ## Workflow
-1. Run quality gates first: \`pnpm test && pnpm lint\`.
-2. Identify scope from \`$ARGUMENTS\` or \`git diff\`. Count changed lines.
+1. Run quality gates first: pnpm test, then pnpm lint.
+2. Identify scope from the arguments above or \`git diff\`. Count changed lines.
 3. Call \`memory_search\` with changed areas to surface past lessons.
 4. **Select reviewer tier based on diff size:**
    - **Small** (<100 lines): 4 core reviewers \u2014 security, test-coverage, simplicity, cct-reviewer.
@@ -3096,7 +3114,7 @@ Multi-agent code review with severity classification and a mandatory \`/implemen
 6. Reviewers communicate cross-cutting findings via SendMessage.
 7. Classify findings: **P1** (security, data loss, correctness \u2014 blocks completion), **P2** (architecture, performance), **P3** (style, minor).
 8. Deduplicate and prioritize. Use \`AskUserQuestion\` for ambiguous severity.
-9. For P1/P2 findings: \`bd create --title="P1: <finding>" --type=bug --priority=1\`
+9. For P1/P2 findings: bd create --title="P1: (finding)" --type=bug --priority=1
 10. Submit to **\`/implementation-reviewer\`** \u2014 mandatory gate, final authority. All P1s must be resolved.
 11. **External reviewers (optional)**: Check \`.claude/compound-agent.json\` for \`"externalReviewers"\`. Spawn configured reviewers. Advisory only, never blocks.
 12. Output review summary with severity breakdown and external findings (if any).
@@ -3106,6 +3124,7 @@ Multi-agent code review with severity classification and a mandatory \`/implemen
 - **pattern-matcher** auto-reinforces recurring findings via \`memory_capture\`.
 - **cct-reviewer** reads \`.claude/lessons/cct-patterns.jsonl\` for known Claude mistakes.
 - After review, call \`memory_capture\` with \`type=solution\` to store the review report.
+- **CRITICAL**: Use \`memory_capture\` MCP tool for ALL lesson storage -- NOT MEMORY.md.
 
 ## Docs Integration
 - **docs-reviewer** checks code changes align with \`docs/\` and existing ADRs.
@@ -3114,16 +3133,29 @@ Multi-agent code review with severity classification and a mandatory \`/implemen
 ## Beads Integration
 - Create \`bd\` issues for P1 and P2 findings with \`bd create\`.
 - Close related issues with \`bd close\` when findings are resolved.
+
+## PHASE GATE 4 -- MANDATORY
+Before starting Compound, verify review is complete:
+- /implementation-reviewer must have returned APPROVED
+- All P1 findings must be resolved
 `,
-  "compound.md": `$ARGUMENTS
+  "compound.md": `---
+name: compound:compound
+description: Capture high-quality lessons from completed work into the memory system
+argument-hint: "<topic or epic context>"
+---
+$ARGUMENTS
 
 # Compound
 
 ## Purpose
 Multi-agent analysis to capture high-quality lessons from completed work into the memory system and update project documentation.
 
+**CRITICAL**: Store all lessons via \`memory_capture\` MCP tool -- NOT via MEMORY.md, NOT via markdown files.
+Lessons go to \`.claude/lessons/index.jsonl\` through the MCP tool. MEMORY.md is a different system and MUST NOT be used for compounding.
+
 ## Workflow
-1. Parse what was done from \`$ARGUMENTS\` or recent git history (\`git diff\`, \`git log\`).
+1. Parse what was done from the arguments above or recent git history (\`git diff\`, \`git log\`).
 2. Call \`memory_search\` with the topic to check what is already known (avoid duplicates).
 3. Create a compound team and spawn the 6 analysis agents in parallel:
    \`\`\`
@@ -3170,118 +3202,53 @@ Multi-agent analysis to capture high-quality lessons from completed work into th
 ## Beads Integration
 - Check \`bd ready\` for related open issues.
 - Close resolved issues with \`bd close\`.
-`,
-  "lfg.md": `$ARGUMENTS
-
-# LFG (Full Cycle)
-
-## Purpose
-Chain all phases: brainstorm, plan, work, review, compound. End-to-end delivery.
-
-## Workflow
-1. **Brainstorm phase**: Explore the goal from \`$ARGUMENTS\`.
-   - MEMORY CHECK: Call \`memory_search\` with the current goal/task. Display results to user. If relevant items found, state which ones apply and why. If none found, state "No relevant lessons found."
-   - Call \`memory_search\` with the goal.
-   - \`TeamCreate\` team "brainstorm-<slug>", spawn docs-explorer + code-explorer as parallel teammates.
-   - Ask clarifying questions via \`AskUserQuestion\`, explore alternatives.
-   - Auto-create ADRs for significant decisions in \`docs/decisions/\`.
-   - Create a beads epic from conclusions with \`bd create --type=feature\`.
-   - Shut down brainstorm team before next phase.
-   - Update epic phase state: \`bd update <epic-id> --notes="Phase: brainstorm COMPLETE | Next: plan"\`
-
-2. **Plan phase**: Structure the work.
-   - MEMORY CHECK: Call \`memory_search\` with the current goal/task. Display results to user. If relevant items found, state which ones apply and why. If none found, state "No relevant lessons found."
-   - Check for brainstorm epic via \`bd list\`.
-   - \`TeamCreate\` team "plan-<slug>", spawn docs-analyst + repo-analyst + memory-analyst as parallel teammates.
-   - Break into tasks with dependencies and acceptance criteria.
-   - Create beads issues with \`bd create\` and map dependencies with \`bd dep add\`.
-   - Create review and compound blocking tasks (\`bd create\` + \`bd dep add\`) so they survive compaction and surface via \`bd ready\` after work completes.
-   - Shut down plan team before next phase.
-   - Update epic phase state: \`bd update <epic-id> --notes="Phase: plan COMPLETE | Next: work"\`
-
-3. **Work phase**: Implement with adaptive TDD.
-   - MEMORY CHECK: Call \`memory_search\` with the current goal/task. Display results to user. If relevant items found, state which ones apply and why. If none found, state "No relevant lessons found."
-   - Assess complexity (trivial/simple/complex) to choose strategy.
-   - Trivial: single subagent, no team. Simple/complex: \`TeamCreate\` team "work-<task-id>".
-   - Spawn test-analyst first, then test-writer + implementer as teammates.
-   - Call \`memory_search\` per subtask; \`memory_capture\` after corrections.
-   - Commit incrementally. Close tasks as they complete.
-   - Run verification gate before marking complete. Shut down work team.
-   - Update epic phase state: \`bd update <epic-id> --notes="Phase: work COMPLETE | Next: review"\`
-
-## PHASE GATE 3->4 -- MANDATORY
-Before starting Review, verify ALL work tasks are closed:
-- Run \`bd list --status=in_progress\` \u2014 must return empty
-- Run \`bd list --status=open\` \u2014 only Review and Compound tasks should remain
-If any work tasks remain open, DO NOT proceed. Complete them first.
-Update epic phase: \`bd update <epic-id> --notes="Phase: work COMPLETE | Next: review"\`
-
-4. **Review phase**: 11-agent review with severity classification.
-   - MEMORY CHECK: Call \`memory_search\` with the current goal/task. Display results to user. If relevant items found, state which ones apply and why. If none found, state "No relevant lessons found."
-   - Run quality gates first: \`pnpm test && pnpm lint\`.
-   - \`TeamCreate\` team "review-<slug>", spawn all 11 reviewers as parallel teammates.
-   - Classify findings as P1 (critical/blocking), P2 (important), P3 (minor).
-   - P1 findings must be fixed before proceeding \u2014 they block completion.
-   - Submit to \`/implementation-reviewer\` as the mandatory gate. Shut down review team.
-   - Update epic phase state: \`bd update <epic-id> --notes="Phase: review COMPLETE | Next: compound"\`
-
-## PHASE GATE 4->5 -- MANDATORY
-Before starting Compound, verify review is complete:
-- /implementation-reviewer must have returned APPROVED
-- All P1 findings must be resolved
-Update epic phase: \`bd update <epic-id> --notes="Phase: review COMPLETE | Next: compound"\`
-
-5. **Compound phase**: Capture learnings.
-   - MEMORY CHECK: Call \`memory_search\` with the current goal/task. Display results to user. If relevant items found, state which ones apply and why. If none found, state "No relevant lessons found."
-   - \`TeamCreate\` team "compound-<slug>", spawn 6 analysis agents as parallel teammates.
-   - Search first with \`memory_search\` to avoid duplicates. Apply quality filters (novelty + specificity).
-   - Store novel insights via \`memory_capture\` with supersedes/related links.
-   - Update outdated docs and deprecate superseded ADRs.
-   - Use \`AskUserQuestion\` to confirm high-severity items. Shut down compound team.
-   - Update epic phase state: \`bd update <epic-id> --notes="Phase: compound COMPLETE | Next: close"\`
 
 ## FINAL GATE -- EPIC CLOSURE
 Before closing the epic:
-- Run \`ca verify-gates <epic-id>\` \u2014 must return PASS for both gates
-- Run \`pnpm test\` \u2014 must pass
-- Run \`pnpm lint\` \u2014 must pass
+- Run ca verify-gates (epic-id) -- must return PASS for both gates
+- Run pnpm test -- must pass
+- Run pnpm lint -- must pass
 If verify-gates fails, the missing phase was SKIPPED. Go back and complete it.
 CRITICAL: 3/5 phases is NOT success. All 5 phases are required.
+`,
+  "lfg.md": `---
+name: compound:lfg
+description: Full workflow cycle chaining brainstorm, plan, work, review, and compound phases
+argument-hint: "<goal>"
+disable-model-invocation: true
+---
+$ARGUMENTS
 
-## Agent Team Pattern
-Each phase creates its own AgentTeam via \`TeamCreate\`, spawns teammates via \`Task\` tool with \`team_name\`, coordinates via \`SendMessage\`, and shuts down with \`shutdown_request\` before the next phase starts. Use subagents (Task without team_name) only for quick lookups like \`memory_search\` or \`bd\` commands.
-
-## Phase Control
-- **Skip phases**: Parse \`$ARGUMENTS\` for "from <phase>" (e.g., "from plan"). Skip all phases before the named one.
-- **Progress**: Announce the current phase before starting it (e.g., "[Phase 2/5] Plan").
-- **Retry**: If a phase fails, report the failure and ask the user whether to retry, skip, or abort.
-- **Resume**: After interruption, run \`bd show <epic-id>\` and read the notes field for current phase state. Resume from that phase. If no phase state, check \`bd list --status=in_progress\` to infer.
+# LFG (Full Cycle)
 
-## Stop Conditions
-- Stop if brainstorm reveals the goal is unclear (ask user).
-- Stop if any test phase produces failures that cannot be resolved.
-- Stop if review finds critical security issues.
+## Workflow
+1. **Brainstorm**: /compound:brainstorm with the goal. Update: bd update (epic-id) --notes="Phase: brainstorm COMPLETE, Next: plan"
+2. **Plan**: /compound:plan with conclusions. Update: bd update (epic-id) --notes="Phase: plan COMPLETE, Next: work"
+3. **Work**: /compound:work (finds tasks via bd ready). Update: bd update (epic-id) --notes="Phase: work COMPLETE, Next: review"
+4. **Review**: /compound:review on changed code. Update: bd update (epic-id) --notes="Phase: review COMPLETE, Next: compound"
+5. **Compound**: /compound:compound to capture learnings (via memory_capture, NOT MEMORY.md). Update: bd update (epic-id) --notes="Phase: compound COMPLETE, Next: close"
 
-## Memory Integration
-- \`memory_search\` is called in brainstorm, work, and compound phases.
-- \`memory_capture\` is called in work and compound phases.
+## Phase Control
+- Skip: "from <phase>" in arguments skips earlier phases.
+- Resume: bd show (epic-id), read notes field for phase state.
+- Progress: announce "[Phase N/5] Name" before each phase.
 
 ## SESSION CLOSE -- INVIOLABLE
-Before saying "done" or "complete", ALL of these must pass:
-1. \`ca verify-gates <epic-id>\` -- All workflow gates satisfied
-2. \`pnpm test && pnpm lint\` -- Quality gates green
-3. \`git status\` -- Review changes
-4. \`git add <specific-files>\` -- Stage (never git add .)
-5. \`bd sync\` -- Sync beads
-6. \`git commit -m "..."\` -- Commit
-7. \`bd sync\` -- Post-commit sync
-8. \`git push\` -- Push to remote
-If ANY step fails, fix it. Work is NOT done until git push succeeds.
+1. ca verify-gates (epic-id)
+2. pnpm test -- all green
+3. pnpm lint -- zero violations
+4. git status, git add (specific files), bd sync, git commit, git push
+Work is NOT done until git push succeeds.
 `,
   // =========================================================================
   // Utility commands (CLI wrappers)
   // =========================================================================
-  "learn.md": `Capture a lesson from this session.
+  "learn.md": `---
+name: compound:learn
+description: Capture a lesson from this session into the memory system
+argument-hint: "<insight to remember>"
+---
+Capture a lesson from this session.
 
 Usage: /compound learn <insight>
 
@@ -3293,7 +3260,12 @@ Examples:
 npx ca learn "$ARGUMENTS"
 \`\`\`
 `,
-  "search.md": `Search lessons for relevant context.
+  "search.md": `---
+name: compound:search
+description: Search stored lessons for relevant context
+argument-hint: "<search query>"
+---
+Search lessons for relevant context.
 
 Usage: /compound search <query>
 
@@ -3307,19 +3279,32 @@ npx ca search "$ARGUMENTS"
 
 Note: You can also use the \`memory_search\` MCP tool directly.
 `,
-  "list.md": `Show all stored lessons.
+  "list.md": `---
+name: compound:list
+description: Show all stored lessons
+---
+Show all stored lessons.
 
 \`\`\`bash
 npx ca list
 \`\`\`
 `,
-  "prime.md": `Load compound-agent workflow context after compaction or context loss.
+  "prime.md": `---
+name: compound:prime
+description: Load compound-agent workflow context after compaction or context loss
+---
+Load compound-agent workflow context after compaction or context loss.
 
 \`\`\`bash
 npx ca prime
 \`\`\`
 `,
-  "show.md": `Show details of a specific lesson.
+  "show.md": `---
+name: compound:show
+description: Show details of a specific lesson
+argument-hint: "<lesson-id>"
+---
+Show details of a specific lesson.
 
 Usage: /compound show <lesson-id>
 
@@ -3327,7 +3312,12 @@ Usage: /compound show <lesson-id>
 npx ca show "$ARGUMENTS"
 \`\`\`
 `,
-  "wrong.md": `Mark a lesson as incorrect or invalid.
+  "wrong.md": `---
+name: compound:wrong
+description: Mark a lesson as incorrect or invalid
+argument-hint: "<lesson-id>"
+---
+Mark a lesson as incorrect or invalid.
 
 Usage: /compound wrong <lesson-id>
 
@@ -3335,7 +3325,11 @@ Usage: /compound wrong <lesson-id>
 npx ca wrong "$ARGUMENTS"
 \`\`\`
 `,
-  "stats.md": `Show compound-agent database statistics and health.
+  "stats.md": `---
+name: compound:stats
+description: Show compound-agent database statistics and health
+---
+Show compound-agent database statistics and health.
 
 \`\`\`bash
 npx ca stats