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.
npx agentmods add skills/kewton/commandmate/catalog-reconcilenpx skills add Kewton/CommandMate --skill catalog-reconcilegit clone --depth 1 https://github.com/Kewton/CommandMateWrote 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/kewton/commandmate/catalog-reconcile)<a href="https://agentmods.dev/skills/kewton/commandmate/catalog-reconcile"><img src="https://agentmods.dev/badge/skills/kewton/commandmate/catalog-reconcile.svg" alt="Measured on agentmods" 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 | $0.00062 | $0.12083 |
| Opus 5 | $0.00031 | $0.06041 |
| Sonnet 5 | $0.00012 | $0.02417 |
| Haiku 4.5 | $0.00006 | $0.01208 |
Grade A, and why
catalog-reconcile scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 5d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -sS "https://raw.githubusercontent.com/openai/codex/${TAG}/codex-rs/tui/src/slash_command.rs" \ How it starts
The opening of the file, as written. The whole thing — 687 lines — stays where its author put it; the contents beside it link to each section on GitHub.
スラッシュコマンドカタログ リコンサイル スキル
src/config/slash-commands-catalog.json と locales/{en,ja}/worktree.json を、
各 CLI の権威ソース(claude docs / codex OSS enum @release タグ)へ合わせ、
その読み取りを src/config/slash-commands-attestations.json に記録し直すスキルです。
このスキルは「機械が出した差分を人が確定させる」手順である。
npm run catalog:refresh -- --writeは追加候補を流し込むだけで、 ja 訳・説明衝突・過去の除外判断の 3 点は決められない(Phase 4)。 そこを埋めずに commit すると、[要レビュー]混じりの ja 辞書と 「/btw — btw」のような説明が出荷される。
attestation は機械が書かない(Issue #2026)。 「版 V で source S は tool T についてこの集合を列挙した」という記録は
--writeの対象外で、人がソースを読んで書くときだけ動く。 カタログ側の pin が守る不変条件はcatalog(tool) ≡ attested(tool) \ excluded(tool)なので、--writeだけを適用すると[<tool>] /<name> is in the catalog but not attestedで赤くなる。 それが審査ゲートである。 カタログからコピーして緑にするとゲートが恒真になり、 「ソースがこう言っていた」が「カタログがこうなっている」の言い換えに退化する。
使用方法
/catalog-reconcile # 通常。codex は latest release タグを取る
/catalog-reconcile --codex-ref rust-v0.146.0 # codex のソースを特定タグに固定
前提条件
npm run buildを primary checkout で実行しない。 このスキルはリリース手順の一部として develop(=稼働サーバの cwd)で走ることがある。build は.nextを作り替えてBUILD_IDを 変えるため、配信中の成果物を壊す(開いているタブの chunk が 404 になり遷移で client-side exception。過去 3 回発生)。build の検証は PR の CI に委ねる。- 作業ツリーが(このスキルが触る 3 ファイル以外)クリーンであること。stash しない (他エージェント稼働中だと破損の恐れ)。
- ネットワークが通ること。通らなくても壊れはしないが、「差分 0 件」と 「調べられなかった」が同じ見た目になる(Phase 1-3)。
このスキルが触るファイル
| ファイル | 誰が書くか |
|---|---|
src/config/slash-commands-catalog.json |
--write(追加は自動。除外は人間) |
locales/en/worktree.json |
--write が heuristic 抽出した英文 → 人手で文体を正す |
locales/ja/worktree.json |
--write が [要レビュー] プレースホルダを置く → 人手で全件翻訳 |
src/config/slash-commands-exclusions.json |
人間(除外の意図=「ソースに在るが載せない」。engine はここを読んで再提案をやめる) |
src/config/slash-commands-attestations.json |
人間だけ(Issue #2026。「ソースが列挙した集合そのもの」+版+採取日。--write は触らない) |
tests/unit/lib/standard-commands.test.ts |
原則触らない(Issue #2026 で件数 pin は撤去され、期待値は attestation から導出される)。禁止系ガードは絶対に触らない |
tests/unit/lib/slash-command-catalog.test.ts |
人間(attestation の version を上げたときだけ。verifiedAgainst リテラルを持つ箇所) |
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 · 687 lines · 62 tokens per session scan A d63f8ae5d193
catalog-reconcile is a skill published in the GitHub repository Kewton/CommandMate (39 stars, last pushed today), licensed MIT. It adds 62 tokens to every session and 12,083 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
aoe
Use when launching, monitoring, or controlling AI coding agents (Claude Code, Codex, OpenCode, etc.) in tmux via Agent of Empires (aoe). Covers creating sessions, capturing agent output, running parallel worktree agents, and organizing work into groups and profiles. Prefer aoe over raw tmux for agent management.
aoe
Manage AI coding agent sessions via Agent of Empires (aoe).
verify
Drive CrowTelemetry's OTLP ingest end-to-end — boot the real receiver, POST OTLP JSON with curl, inspect the SQLite db.
crow-show-image
Surface an image you've generated (a diagram, chart, screenshot, or rendered figure) in Crow's Images panel so the user can see it inline. Use whenever you produce a visual artifact worth showing.
remobi-setup
Full interactive onboarding for remobi — the mobile terminal overlay for tmux. Checks prerequisites, inspects tmux config, interviews the user about their workflow, generates a validated remobi.config.ts, suggests tmux mobile optimisations, and walks through deployment. Use this skill whenever someone asks to set up…
build-and-verify
Build, test, and end-to-end verify the Multiplex visionOS/iPadOS SSH-tmux terminal app. Use this whenever you need to compile the app, run its unit tests, regenerate the Xcode project after editing project.yml or adding/ removing source files, or confirm a change works in the real app on the visionOS or iPad…