project-commands

project-commands is a skill for Claude Code from tigu77/tiguclaw. It costs 84 tokens per session (1,041 once invoked), scanned A, original, Apache-2.0.

A project-specific command builder for creating shortcuts that either run shell commands or ask an agent to perform a repeated task. Shell commands are text instructions executed by the operating system.

In plain words
What is it for?
Use it to create project shortcuts for builds, tests, deployments, cleanup, release-note drafts, or code reviews.
Why use it?
It avoids repeating common build, test, deployment, or review instructions and requires confirmation before saving the command or running risky actions.

Skill for Claude Code

Written for Claude Code: $ARGUMENTS substitution.

Good fit Use it to create project shortcuts for builds, tests, deployments, cleanup, release-note drafts, or code reviews.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/tigu77/tiguclaw/project-commands
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.

Any agent
npx skills add tigu77/tiguclaw --skill project-commands
Clone the repo
git clone --depth 1 https://github.com/tigu77/tiguclaw

Made for: Claude Code.

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 project-commands

README.md
[![agentmods](https://agentmods.dev/badge/skills/tigu77/tiguclaw/project-commands/github.svg)](https://agentmods.dev/skills/tigu77/tiguclaw/project-commands)
Your own site
<a href="https://agentmods.dev/skills/tigu77/tiguclaw/project-commands"><img src="https://agentmods.dev/badge/skills/tigu77/tiguclaw/project-commands/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 project-commands

Your own site · 80×15
<a href="https://agentmods.dev/skills/tigu77/tiguclaw/project-commands"><img src="https://agentmods.dev/badge/skills/tigu77/tiguclaw/project-commands.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 84 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,041 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.
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 $0.00084 $0.01041
Opus 5.5 $0.00034 $0.00416
Sonnet 5.5 $0.00017 $0.00208
Haiku 4.5 $0.00008 $0.00104

Measured 6d ago against content hash f25e22d84613, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

project-commands 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 6d 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.

skills/project-commands/SKILL.md · 49 lines

What it actually says

프로젝트 커맨드 만들기

프로젝트를 대화에 연결하면 그 프로젝트의 커맨드가 그 대화의 📁 메뉴(대시보드)·/ 목록·텔레그램 /project 에 뜬다. 파일 자리는 <프로젝트>/.tiguclaw/commands/<이름>.md, 만드는 도구는 register_command(project 를 준다). 커맨드가 많으면 하위 폴더로 묶을 수 있다(commands/배포/staging.md → 메뉴에 배포 › /staging). 부르는 이름은 파일 이름 그대로라 폴더가 달라도 이름은 겹치면 안 된다. 묶음은 register_command 의 group(예 배포/스테이징)으로 — 만들 때 주면 그 묶음에, 이미 있는 명령에 group 만 주면 내용은 그대로 두고 옮긴다('' 은 맨 위로). 정리 전에 list_commands(project) 로 지금 묶음을 본다.

1. 종류를 고른다

언제 도구 인자
실행형 매번 같은 셸 명령(배포·빌드·테스트·정리) — 판단이 필요 없다 run (+ 필요하면 confirm)
프롬프트형 매번 같은 부탁(릴리스 노트 초안·코드 리뷰) — 판단이 필요하다 prompt

실행형은 비서 턴 없이 그 프로젝트 폴더에서 돌고, 끝나면 결과(종료 코드·출력 꼬리)가 대화에 온다. 돌고 있는 것은 /stop 이나 대시보드 셸 카드에서 멈춘다.

2. 실행형 요령

  • run 은 한 줄이다. 여러 단계면 묶어서 그 한 줄이 부르게 한다:
    • 프로젝트에 package.json 이 있으면 npm 스크립트가 첫 선택이다 — 윈도우·맥·리눅스에서 똑같이 돈다(run: npm run deploy).
    • 없으면 프로젝트 안 스크립트 파일(scripts/deploy.sh 등)을 만들고 run 이 그걸 부른다. 윈도우 사용자라면 셸 차이를 생각한다.
  • 되돌리기 어려운 일(배포·삭제·외부로 보내기)은 confirm: true — 돌리기 전에 사용자에게 한 번 묻는다.
  • 오래 걸려도 된다(백그라운드 셸). 다만 입력을 기다리는 명령(대화형 프롬프트)은 영원히 멈춰 있으니 피한다(--yes 류 플래그).
  • $ARGUMENTS 를 쓰면 /deploy staging 의 staging 이 들어간다.

3. 순서 (★저장 전에 확인)

  1. 프로젝트 폴더를 보고(package.json 스크립트·기존 스크립트) 무엇을 돌릴지 정한다.
  2. 사용자에게 보여 준다 — 이름 · 종류 · 돌릴 줄(또는 부탁 글) · confirm 여부 · 새로 만들 스크립트 파일이 있으면 그 내용. 셸 명령을 저장하는 일이라 확인 없이 만들지 않는다.
  3. 승인받으면 register_command({ name, project, run, confirm, description }).
  4. 연결이 안 돼 있으면 «이 대화에 연결할까요?» — 연결해야 메뉴에 뜬다(link_project).
  5. 위험하지 않은 것이면 한 번 돌려 보자고 권한다(/project run <프로젝트> <이름>). 배포처럼 위험한 건 사용자가 직접 누르게 둔다.

4. 고치기·지우기

  • 고치기: 같은 이름으로 register_command({ ..., overwrite: true }).
  • 지우기: delete_command({ name, project }).
  • 같은 이름의 전역 커맨드가 있으면 /이름 은 전역이 돈다 — 프로젝트 것은 📁 메뉴나 /project run <프로젝트> <이름> 으로 부른다. 헷갈리면 다른 이름을 권한다.
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. 6d ago Changed · +3 lines f25e22d84613
  2. 8d ago First seen · 46 lines · 84 tokens per session scan A dbd92f90b752

Subscribe to this mod's changes

project-commands is a skill published in the GitHub repository tigu77/tiguclaw (9 stars, last pushed yesterday), licensed Apache-2.0. It adds 84 tokens to every session and 1,041 once invoked, about $0.0003 per session on Opus 5.5. 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 2026-10-09.

Related

Other skills, from other repositories

tmux

Manage long-running shell sessions with tmux — start a detached session, run a long task, reattach later, capture output. Use when a task takes longer than a single tool call (build, test, log tail).

Team-Commonly/commonly · 48 tokens

community-research-insight

Extract structured insight briefs from community research transcripts or notes. Produces pain points, stakeholder needs, opportunity maps, risks, and follow-up questions. Requires human review before publication.

clawdotnet/openclaw.net · 41 tokens

telegram-userbot

A skill for connecting to and working through the owner's personal Telegram account, rather than a Telegram bot. It can read personal chats, search messages, and send messages as the account owner after setup and consent.

smixs/iva-agent · 29 tokens

email-triage

Triage inbox into “needs reply”, “FYI”, “urgent”, and “safe to archive”, with a short plan for each.

clawdotnet/openclaw.net · 33 tokens

watch

A monitoring and briefing workflow that checks unread Telegram messages, email, failed checks, and failed scheduled units, then decides what needs the owner's attention. It can also explain actions such as creating a task, delaying a reminder, ignoring an item, or fixing a failure.

smixs/iva-agent · 176 tokens

insight

A scheduled daily practice that looks for a repeated manual task, builds and tests a small tool for it, and suggests the result. It can instead report a development issue when the agent cannot solve its own problem.

smixs/iva-agent · 113 tokens