Borrowing it
Nothing to install: this file belongs to alonf/specrew. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/alonf/specrew/main/.squad/skills/iteration-closeout-evidence/SKILL.mdgit clone --depth 1 https://github.com/alonf/specrewWrote 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/alonf/specrew/iteration-closeout-evidence)<a href="https://agentmods.dev/skills/alonf/specrew/iteration-closeout-evidence"><img src="https://agentmods.dev/badge/skills/alonf/specrew/iteration-closeout-evidence/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/alonf/specrew/iteration-closeout-evidence"><img src="https://agentmods.dev/badge/skills/alonf/specrew/iteration-closeout-evidence.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 34 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00024 | $0.00645 |
| Opus 5 | $0.00012 | $0.00322 |
| Sonnet 5 | $0.00005 | $0.00129 |
| Haiku 4.5 | $0.00002 | $0.00064 |
Grade A, and why
iteration-closeout-evidence 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 5d 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.
How it starts
The opening of the file, as written. The whole thing — 37 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Context
Use this when a closeout or acceptance note says work is complete because plan/state/spike artifacts now exist. Presence alone is not enough for reviewer acceptance if the evidence files are not versioned with the implementation they certify.
Patterns
- Read the contract and the live artifact content first; reject empty or malformed proof even if the file is tracked.
- After content review, confirm the proving artifacts are actually tracked in git. Closure evidence must be durable.
- Treat scripts and their proving artifacts as one acceptance set: if the script is tracked but the state or spike proof is untracked, the closeout is still incomplete.
- Separate substantive correctness from persistence. It is possible for an artifact to be well-written and still fail acceptance because it is untracked.
- Generate historical dashboard snapshots only after plan/state truth surfaces have moved to the closeout boundary. Otherwise the artifact can freeze a stale live phase (for example
reviewing) into what claims to be closeout evidence. - On rejection, name the exact files that must be versioned and lock out the original closeout author for the next revision cycle.
- For narrow re-reviews, judge only the cited defect. If the exact evidence files named in the rejection are now tracked, close that defect directly instead of reopening already-cleared content questions.
Examples
scripts\specrew-init.ps1and the two deployment scripts were tracked, butspecs\001-specrew-product\iterations\001\state.mdandspecs\001-specrew-product\iterations\001\spikes.mdremained untracked. Verdict: NEEDS-WORK because the accepted-work evidence was not durable.- A plan row may truthfully mark a task
done, but if the spike deliverable cited by that row is still outside version control, the closeout record is incomplete. - Re-reviewing the same closeout later,
git ls-filesreturned bothstate.mdandspikes.md, andgit status --shortshowed them as tracked additions. Verdict: PASS on the prior rejection reason, because the durability defect was the only remaining acceptance gap in scope.
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.
- 5d ago First seen · 37 lines · 24 tokens per session scan A 05dae33c1541
iteration-closeout-evidence is a skill published in the GitHub repository alonf/specrew (54 stars, last pushed today), licensed MIT. It adds 24 tokens to every session and 645 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other skills, from other repositories
gsd-quick
Execute a quick task with GSD guarantees (atomic commits, state tracking) but skip optional agents.
gsd-quick-batch
Batch several /gsd:quick-shaped tasks together — planned, dispatched, and merged as one run.
gh-issues
Fetch GitHub issues, spawn sub-agents to implement fixes and open PRs, then monitor and address PR review comments. Usage: /gh-issues [owner/repo] [--label bug] [--limit 5] [--milestone v1.0] [--assignee @me] [--fork user/repo] [--watch] [--interval 5] [--reviews-only] [--cron] [--dry-run] [--model glm-5]…
gsd-pause-work
Create context handoff when pausing work mid-phase.
gsd-ship
Create PR, run review, and prepare for merge after verification passes.
mcore-split-pr
Split a PR into multiple PRs to reduce the number of required CODEOWNERS reviewer groups.