specrew: Skill for Claude Code

.squad/skills/iteration-closeout-evidence/SKILL.md

iteration-closeout-evidence is a skill for Claude Code, Codex from alonf/specrew. It costs 24 tokens per session (645 once invoked), scanned A, original, MIT.

A closeout-review procedure for checking whether completion evidence is valid and stored in version control. It verifies both the contents of planning records and whether the files are tracked with the implementation.

In plain words
What is it for?
Use it to review plan, state, spike, script, and dashboard evidence before closing an iteration. It identifies exact files that must be corrected or versioned.
Why use it?
It prevents a project from being marked complete because files merely exist or because untracked evidence happens to look correct. It also avoids preserving an outdated lifecycle state in historical snapshots.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

This is alonf/specrew's own configuration. It tells Claude Code and Codex how to work on specrew itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything specrew configures →

Reuse

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.

Copy the file
curl -O https://raw.githubusercontent.com/alonf/specrew/main/.squad/skills/iteration-closeout-evidence/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/alonf/specrew

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for iteration-closeout-evidence

README.md
[![agentmods](https://agentmods.dev/badge/skills/alonf/specrew/iteration-closeout-evidence/github.svg)](https://agentmods.dev/skills/alonf/specrew/iteration-closeout-evidence)
Your own site
<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.

agentmods 80×15 button for iteration-closeout-evidence

Your own site · 80×15
<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>
Per session 24 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 645 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
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.
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce 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

Measured 5d ago against content hash 05dae33c1541, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

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.

.squad/skills/iteration-closeout-evidence/SKILL.md · 37 lines

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.ps1 and the two deployment scripts were tracked, but specs\001-specrew-product\iterations\001\state.md and specs\001-specrew-product\iterations\001\spikes.md remained 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-files returned both state.md and spikes.md, and git status --short showed them as tracked additions. Verdict: PASS on the prior rejection reason, because the durability defect was the only remaining acceptance gap in scope.

Read the full file on GitHub · 37 lines

Changes

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.

  1. 5d ago First seen · 37 lines · 24 tokens per session scan A 05dae33c1541

Subscribe to this mod's changes

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.