close-out

A finishing step for a completed software change identified by a short name, or slug. It updates the main specification to match what shipped, archives the related planning files, and records the release in the changelog.

In plain words
What is it for?
Use it after a change meets its completion criteria to reconcile its specification, preview and archive its plan and blueprint, and add one release entry.
Why use it?
Plans and specifications can become outdated after implementation, while old planning files clutter the project. This step brings the record up to date and preserves the history of the work.

Command

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add commands/ackeskin/contexture/close-out
Clone the repo
git clone --depth 1 https://github.com/AcKeskin/contexture
Per session 48 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 279 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00048 $0.00279
Opus 5 $0.00024 $0.00139
Sonnet 5 $0.00010 $0.00056
Haiku 4.5 $0.00005 $0.00028

Measured 2d ago against content hash fefa2104317b, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

close-out 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 2d 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.

commands/close-out.md · 15 lines

What it actually says

Run the close-out skill for the given slug.

The text after /close-out is the slug to close out. Examples:

  • /close-out auth-rework — reconcile the shipped auth-rework change into its spec (a new as-shipped version, intent preserved), retire its plan + blueprint to .claude/archive/<date>-auth-rework/, and log one ship line to CHANGELOG.md.
  • /close-out (no slug) — the skill asks which slug (it requires one).

The skill confirms the change actually shipped (done-criteria met), then runs reconcile → retire → record: it diffs spec-vs-shipped and proposes the reconciled spec version behind accept/edit/reject, previews the artefact moves before performing them, and invokes update-changelog for the single ship line. It never auto-writes — every spec edit and file move passes a propose-confirm gate. Mode A, never auto-fires.

See ~/.claude/skills/close-out/SKILL.md for the full procedure.

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. 2d ago First seen · 15 lines · 48 tokens per session scan A fefa2104317b

Subscribe to this mod's changes

close-out is a command published in the GitHub repository AcKeskin/contexture (2 stars, last pushed 1mo ago), licensed MIT. It adds 48 tokens to every session and 279 once invoked, about $0.0002 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 2026-08-31.