Agent skill
aget-wind-down
End AGET session with state capture and sanity checks
Install this agent skill to your Project
npx add-skill https://github.com/majiayu000/claude-skill-registry/tree/main/skills/other/other/aget-wind-down-aget-framework-template-analyst-age
SKILL.md
aget-wind-down
End an AGET agent session properly. This skill runs the wind-down protocol to capture session state, run sanity checks, and prepare handoff notes.
Instructions
When this skill is invoked:
-
Run the wind-down script:
bashpython3 scripts/wind_down.py -
The script will:
- Run sanity checks (housekeeping protocol)
- Capture session duration and activity
- Scan for pending work in
planning/ - Generate session summary
- Suggest commit message if changes exist
-
If user provides notes, pass them to the script:
bashpython3 scripts/wind_down.py --notes "User provided notes here" -
Create session record file at
sessions/SESSION_YYYY-MM-DD_descriptive_title.md:- Use YAML frontmatter with Session Metadata Standard v1.0 fields (date, duration_minutes, objectives, outcomes)
- Include optional fields: learnings, commits, files_changed, pain_points, next_steps
- Add session body sections: Objectives, Deliverables, Outcomes, Lessons, Blockers, Files Changed
- Capture wind-down state in the file: sanity result, pending work, git diff stats
- Reference schema:
.aget/schemas/session_metadata_v1.0.yaml - Reference exemplar:
sessions/SESSION_2025-12-03_kb_enhancement.md
-
If re-entrancy guard blocks (exit code 4), inform user:
- Wind-down was run recently (5-minute cooldown)
- Use
--forceto bypass if needed
Required Outputs
Every wind-down must produce:
- Terminal summary (stdout) — sanity, changes, pending, suggested commit
- Session record file —
sessions/SESSION_YYYY-MM-DD_*.md(L004: process governance)
Output Format
Present the wind-down summary:
Wind Down Complete
- Session: [duration]
- Sanity: [healthy/warnings/errors]
- Pending: [N] items in planning/
- Changes: [staged/unstaged counts]
- Suggested commit: "[message]"
Error Handling
- Exit code 0: Clean close, sanity healthy
- Exit code 1: Close with warnings (report them)
- Exit code 2: Close with errors (require acknowledgment)
- Exit code 3: Configuration error
- Exit code 4: Re-entrancy guard active
Options
--skip-sanity: Skip sanity check (not recommended)--force: Bypass re-entrancy guard (L468)--json: Machine-readable output
Related
- L004: Process Governance Gap (session file as required output)
- L468: Re-entrancy Protection
- L532: Skills vs Learnings Distinction
- CAP-SESSION-003: Wind Down Protocol
Recommended Agent Skills
Expand your agent's capabilities with these related and highly-rated skills.
agent-ops-spec
Manage specification documents in .agent/specs/. Use when user provides requirements, acceptance criteria, or feature descriptions that need to be tracked and validated against implementation.
agent-ops-state
Maintain .agent state files. Use at session start, after meaningful steps, and before concluding: read/update constitution/memory/focus/issues/baseline consistently.
agent-ops-spec
Manage specification documents in .agent/specs/. Use when user provides requirements, acceptance criteria, or feature descriptions that need to be tracked and validated against implementation.
agent-ops-testing
Test strategy, execution, and coverage analysis. Use when designing tests, running test suites, or analyzing test results beyond baseline checks.
agent-ops-testing
Test strategy, execution, and coverage analysis. Use when designing tests, running test suites, or analyzing test results beyond baseline checks.
agent-ops-state
Maintain .agent state files. Use at session start, after meaningful steps, and before concluding: read/update constitution/memory/focus/issues/baseline consistently.
Didn't find tool you were looking for?