Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/aget-framework/template-advisor-agetnpx agentmods add skills/aget-framework/template-advisor-aget/aget-wind-downWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/aget-framework/template-advisor-aget/aget-wind-down)<a href="https://agentmods.dev/skills/aget-framework/template-advisor-aget/aget-wind-down"><img src="https://agentmods.dev/badge/skills/aget-framework/template-advisor-aget/aget-wind-down/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/aget-framework/template-advisor-aget/aget-wind-down"><img src="https://agentmods.dev/badge/skills/aget-framework/template-advisor-aget/aget-wind-down.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00015 | $0.00657 |
| Opus 5 | $0.00008 | $0.00329 |
| Sonnet 5 | $0.00003 | $0.00131 |
| Haiku 4.5 | $0.00002 | $0.00066 |
Grade A, and why
aget-wind-down scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
This is a copy
100% identical to aget-wind-down — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 86 lines — stays where its author put it; the contents beside it link to each section on GitHub.
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:
python3 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:
python3 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
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 9d ago First seen · 86 lines · 15 tokens per session scan A e337900f5357
aget-wind-down is a skill published in the GitHub repository aget-framework/template-advisor-aget (2 stars, last pushed 9d ago), licensed Apache-2.0. It adds 15 tokens to every session and 657 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to aget-wind-down, differing in 0 lines, and is treated as a copy.
Other skills, from other repositories
gws-calendar
Google Calendar: Manage calendars and events.
gws-gmail-send
Skill "gws-gmail-send" from googleworkspace/cli, covering gmail +send, usage, flags, examples and tips.
gws-gmail-watch
Gmail: Watch for new emails and stream them as NDJSON.
gws-gmail
Gmail: Send, read, and manage email.
gws-workflow-meeting-prep
Google Workflow: Prepare for your next meeting: agenda, attendees, and linked docs.
gws-keep
Manage Google Keep notes.