agents-remember: Skill for Claude Code

.agents/skills/c-12-closeout/SKILL.md

c-12-closeout is a skill for Claude Code, Codex from Foxfire1st/agents-remember. It costs 45 tokens per session (6,323 once invoked), scanned A, original, MIT.

A final review process for committing approved changes made in both a code repository and its separate memory repository. It coordinates code quality checks, onboarding updates, and ledger alignment before committing.

In plain words
What is it for?
Use it to finish worktree-based coding tasks, verify code and memory changes, commit them in the required order, and leave pushing changes as a separate decision.
Why use it?
It reduces the risk of committing code while leaving its documentation or external project memory incomplete or inconsistent.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: installed under .agents/ (shared by several agents).

This is Foxfire1st/agents-remember's own configuration. It tells Claude Code and Codex how to work on agents-remember 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 agents-remember configures →

Reuse

Borrowing it

Nothing to install: this file belongs to Foxfire1st/agents-remember. 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/Foxfire1st/agents-remember/main/.agents/skills/c-12-closeout/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/Foxfire1st/agents-remember

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 c-12-closeout

README.md
[![agentmods](https://agentmods.dev/badge/skills/foxfire1st/agents-remember/c-12-closeout.svg)](https://agentmods.dev/skills/foxfire1st/agents-remember/c-12-closeout)
Your own site
<a href="https://agentmods.dev/skills/foxfire1st/agents-remember/c-12-closeout"><img src="https://agentmods.dev/badge/skills/foxfire1st/agents-remember/c-12-closeout.svg" alt="Measured on agentmods" height="20"></a>
Per session 45 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 6,323 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 pass 7 Sept 2026
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 $0.00045 $0.06323
Opus 5 $0.00023 $0.03161
Sonnet 5 $0.00009 $0.01265
Haiku 4.5 $0.00005 $0.00632

Measured 7d ago against content hash a1ff46ce8007, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

c-12-closeout 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 7d 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.

.agents/skills/c-12-closeout/SKILL.md · 429 lines

How it starts

The opening of the file, as written. The whole thing — 429 lines — stays where its author put it; the contents beside it link to each section on GitHub.

c-12-closeout Closeout

Use this skill when approved Agents Remember edits in an external- or internal-memory worktree need to be committed.

The c-12-closeout skill owns closeout sequencing for worktree-backed tasks. Closeout is worktree-only: every change affecting the code repo runs through a c-09-git-worktree-manager dual worktree (code + memory) — there is no direct-checkout closeout path. Use the c-09-git-worktree-manager skill for worktree start, attach, status, integration, lifecycle finalization, and cleanup; use this skill for the closeout gate and code-memory-ledger commit order.

Seat note (manager -> builder -> reviewer -> curator chain): in that chain, the builder produces code and a turn report only — it does not author onboarding. The dedicated curator seat (l-01-agent-lifecycles roles/curator.md) runs the c-05-create-or-update-onboarding-files skill as its own fresh pass, fed the leaf's landed change set, task doc, and notes/, BEFORE the owning seat (the manager) runs this skill's closeout preview. Everywhere below that says "create" or "refresh" onboarding, that authoring already happened in the curator's pass; the seat running closeout verifies the curator's output against the checks in this skill, it does not author onboarding inline to make a failing check pass. A check that still fails after the curator pass is a closeout failure — respawn/rerun the curator, do not patch onboarding from the closeout seat. This distinction does not apply outside that chain (e.g. a solo flat session with no separate curator seat still runs c-05-create-or-update-onboarding-files itself before closing out).

Candidate-bound route-review gate: every code-changing leaf reaches this skill only after an independent reviewer has written the verdict and per-major-route reports and the owner has called task_doc(operation="record_route_review", review={verdict, verdictRef, routes:[...]}). The plane stamps the exact current Git candidate tree and verifies the task-relative artifacts. Curator dispatch and both closeout preview/apply recompute that tree and refuse when the record is absent, blocking, stale, or points at missing evidence. Direct/solo and builder-verified tiers still require another agent's review; loop knobs change depth, not this gate. Never supply or remember the tree hash yourself, and never treat chat prose as a substitute for the task-bound record.

Read the full file on GitHub · 429 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. 7d ago First seen · 429 lines · 45 tokens per session scan A a1ff46ce8007

Subscribe to this mod's changes

c-12-closeout is a skill published in the GitHub repository Foxfire1st/agents-remember (27 stars, last pushed yesterday), licensed MIT. It adds 45 tokens to every session and 6,323 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 2026-08-30.

Related

Other skills, from other repositories

agent-framework-py-release

Use when cutting a Python release for the microsoft/agent-framework monorepo. Triggers on "bump py versions", "cut a python release", "prepare release PR for python", "release py packages", "bump python to X.Y.Z", or similar requests to bump Python package versions and prepare a release PR. Handles all four lifecycle…

microsoft/agent-framework · 103 tokens

github-ops

GitHub CLI for issues, PRs, code search, CI logs, releases, and API queries. Requires gh CLI and auth.

fuyuxiang/echo-agent · 31 tokens

release-finalizer

Merges a release PR, associates it with resolved issues, replies to issue reporters, and closes issues. Use after PR review is complete and ready for merge. Closes the release cycle.

Fu-Jie/openwebui-extensions · 42 tokens

release-prep

Orchestrates the full release preparation flow for a plugin — version sync across 7+ files, bilingual release notes creation, and commit message drafting. Use before submitting a PR. Does NOT push or create a PR; that is handled by pr-submitter.

Fu-Jie/openwebui-extensions · 56 tokens

publish-no-version-bump

Commit and push code to GitHub, then publish to OpenWebUI official marketplace without updating version. Use when fixing bugs or optimizing performance that doesn't warrant a version bump.

Fu-Jie/openwebui-extensions · 40 tokens

version-bumper

Automates version upgrades and changelog synchronization across 7+ files (Code, READMEs, Docs). Use when a plugin is ready for release to ensure version consistency.

Fu-Jie/openwebui-extensions · 39 tokens