Borrowing it
Nothing to install: this file belongs to thingineeer/claude-cat. 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/thingineeer/claude-cat/main/.claude/skills/resume-claude-cat/SKILL.mdgit clone --depth 1 https://github.com/thingineeer/claude-catWrote 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/thingineeer/claude-cat/resume-claude-cat)<a href="https://agentmods.dev/skills/thingineeer/claude-cat/resume-claude-cat"><img src="https://agentmods.dev/badge/skills/thingineeer/claude-cat/resume-claude-cat/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/thingineeer/claude-cat/resume-claude-cat"><img src="https://agentmods.dev/badge/skills/thingineeer/claude-cat/resume-claude-cat.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00024 | $0.00744 |
| Opus 5 | $0.00012 | $0.00372 |
| Sonnet 5 | $0.00005 | $0.00149 |
| Haiku 4.5 | $0.00002 | $0.00074 |
Grade B, and why
resume-claude-cat scanned grade B 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 12d 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.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
- `~/.claude/settings.json` 의 `statusLine` 이 `npx -y claude-cat@latest` 계열이 아니면 그 사실만 알려준다 — 묻지 않고 고치지 않는다. What it actually says
Resume — claude-cat
1. Sync with remote — 무조건 가장 먼저
다른 어떤 파일을 읽기 전에 반드시 git pull부터 한다. 건너뛰면 pull 이전의 옛 파일로 작업하게 된다.
git fetch origin --prunegit status -sb | head -1로 'behind' 여부 확인- behind면
git pull --ff-only origin dev. diverged면 멈추고 사용자에게 경고 — force pull 금지
@참조는 스킬 로드 시점(= git pull 이전)에 파일을 읽어버리므로 여기서는 쓰지 않는다. pull이 끝난 뒤 2단계에서 직접 Read 해 최신 상태를 확보한다.
2. Read the refreshed files (pull 이후에)
git pull로 파일이 새로고침됐으니, 이제 Read 도구로 읽는다:
CLAUDE.md— branch model, worktree-only policy, release flow, layout/mood invariantsdocs/checkpoints/SESSION-STATE.md— 작업 상태 + 대화 요약- 위 SESSION-STATE.md의 "Key Files"에
@참조로 적힌 파일들을 모두 읽는다 — 각 설명대로 어떤 파일이 어떤 작업과 관련되는지 파악한다.
경로 규칙: 이 스킬과 SESSION-STATE.md 안의 모든 파일 참조는 프로젝트 루트 기준 상대 경로여야 한다.
~/Desktop/...같은 머신 종속 절대 경로 금지 — 그래야 모든 컴퓨터에서 동일하게 동작한다.
3. Git status
git status 와 git branch --show-current 를 실행하고, 최근 커밋을 (오늘 커밋 전체 git log --oneline --since="midnight") 또는 (최근 10개 git log --oneline -10) 중 많은 쪽으로 보여준다. git worktree list 도 실행해 남은 side worktree가 있는지 확인한다.
4. Build environment
테스트 fixture가 깨끗하게 렌더되는지 확인:
npm run test:sample
npm run test:full
./.env가 없으면(새 머신)docs/SESSION-RESUME.md§3 의 bootstrap 절차를 안내만 한다 — 자동 실행 금지.~/.claude/settings.json의statusLine이npx -y claude-cat@latest계열이 아니면 그 사실만 알려준다 — 묻지 않고 고치지 않는다.
5. Briefing
Print:
Project: claude-cat (Claude Code statusLine renderer, maintained by thingineeer)
Branch: {current branch — should be dev}
Tip: {short SHA + subject}
npm: claude-cat@{npm view claude-cat version} (latest published)
Done: {SESSION-STATE의 Completed 요약}
Current: {In Progress}
Next: {Remaining backlog 상위 3개}
지난 대화 핵심: {SESSION-STATE의 "## 대화 요약"에서 결정·다음할일 1~2줄}
Ask: "Ready to continue?"
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.
- 12d ago First seen · 54 lines · 24 tokens per session scan B 4e036263dab9
resume-claude-cat is a skill published in the GitHub repository thingineeer/claude-cat (10 stars, last pushed 21d ago), licensed MIT. It adds 24 tokens to every session and 744 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
conventional-commit
Workflow for generating conventional commit messages following the Conventional Commits specification. MUST be invoked every time a commit is created. Guides construction of standardized commit messages with correct type, scope, description, body, and footer.
python-release
Handle Python SDK release, build, bump, packaging metadata, PyPI client pin, uv.lock, nox/build workflow, and publish verification changes. Use for Python release process work or dependency pin bumps; do not use for ordinary Python feature implementation.
release-notes
Generate and publish concise, evidence-based notes in the body of the latest existing GitHub Release. Use only when the user explicitly invokes $release-notes or explicitly asks to update the latest existing GitHub Release body. Do not invoke for general release planning, changelog, tag, or version tasks.
contributor
End-to-end open source contribution workflow: from scanning issues to submitting PRs. Use this skill whenever the user wants to contribute to an open source project, find issues to fix, submit a pull request, fork a repo to contribute, fix a GitHub issue, or mentions 'open source contribution'. Also trigger when they…
git-commit-smart
Generates meaningful, conventional commit messages automatically. Use when committing code changes. Analyzes diff to create descriptive commits following best practices.
review-gate
Use before an agent-produced diff is committed, pushed, opened as a PR, merged, landed, or applied to user files when explicit implementation approval is missing. Trigger for review gate, review pack, approve before landing, diff first then land, human approval, merge gate, commit gate, push gate, or PR readiness.…