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 skills add clomia/claude-automata --skill define-purposegit clone --depth 1 https://github.com/clomia/claude-automataWrote 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/clomia/claude-automata/define-purpose)<a href="https://agentmods.dev/skills/clomia/claude-automata/define-purpose"><img src="https://agentmods.dev/badge/skills/clomia/claude-automata/define-purpose/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/clomia/claude-automata/define-purpose"><img src="https://agentmods.dev/badge/skills/clomia/claude-automata/define-purpose.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 | $0.00016 | $0.00572 |
| Opus 5 | $0.00008 | $0.00286 |
| Sonnet 5 | $0.00003 | $0.00114 |
| Haiku 4.5 | $0.00002 | $0.00057 |
Grade A, and why
define-purpose 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 9d 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.
What it actually says
Anchor file save path: $ARGUMENTS or ANCHOR.md
ploop(advisor loop)은 agent가 오랜 시간 자율적으로 작업하는 loop다. anchor는 그 loop를 붙들어 매는 기준 파일로, context가 유실되어도 항상 원문 그대로 보존된다.
Purpose는 완료 조건 없이 방향만 가진다.
agent는 Purpose로부터 스스로 요구사항을 만들며 나아가야 한다.
advisor를 소집하면 방향·Constraint 대비 상태를 감사받는다. purpose loop는 스스로 멈추지 않는다 — /ploop:off가 끝이다.
Instructions
- 사용자를 추궁해 생각과 의도를 최대한 수집하라 — 열린 질문으로 시작해 여러 번의 질의응답을 거쳐라.
- [CRITICAL] 사용자의 주장을 사실로 수용하지 마라. False assumption이 가장 위험하다. 사용자의 말은 생각이나 의도로 해석하라.
- 수집한 정보를 판단 기준으로 쓸 수 있는 축으로 종합하고, Anchor file save path에 markdown 형식으로 purpose를 작성하라.
- 사용자가 anchor를 최종 검수하게 하라 — 내용을 모두 출력하지 말고 파일 확인을 요청하라.
- 완료 후 anchor text를 복사해 별도 session에
/ploop:launch [anchor text]하라고 안내하라./ploop:launch는 파일 경로가 아닌 내용을 copy & paste해야 한다.
Purpose 규칙
- [IMPORTANT] Acceptable boundaries와 나아갈 방향이 명확히 정의되어야 한다.
- agent의 역할, 존재 이유를 정의하라.
- agent가 스스로 할 일을 찾고 판단할 수 있는 기준을 서술하라.
- harness(CLAUDE.md, rules 등)가 제공하는 내용은 중복이니 anchor에 넣지 마라.
- ROI(분량 대비 정보)가 높은 문서를 작성하라 — 중요한 단어만 남기고, 작성 후 더 irreducible하게 줄일 수 있는지 재검토하라.
- 구조는 Background → Purpose → Constraint → Reference 순이다.
# Purpose(나아갈 방향)와# Constraint(허용 범위)는 필수,# Background(방향의 배경)와# Reference(관련 link — URL·파일 경로)는 선택이며, section은 자유롭게 추가할 수 있다.
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.
- 9d ago First seen · 34 lines · 16 tokens per session scan A 0ef8d2c9a2ac
define-purpose is a skill published in the GitHub repository clomia/claude-automata (13 stars, last pushed 6d ago), licensed Apache-2.0. It adds 16 tokens to every session and 572 once invoked, about $0.0001 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.
Other skills, from other repositories
create-site
Creates a new Power Pages code site (SPA) using React, Angular, Vue, or Astro. Guides through the full process from initial concept to deployed site: requirements discovery, scaffolding, component planning, design, implementation, validation, and deployment. Use when the user wants to create, build, or scaffold a new…
google-ads-audit
Google Ads account audit and business context setup. Run this first — it gathers business information, analyzes account health, and saves context that all other ads skills reuse. Trigger on "audit my ads", "ads audit", "set up my ads", "onboard", "account overview", "how's my account", "ads health check", "what should…
review
5-pass structured code review — correctness, security, performance, readability, consistency.
alive:system-upgrade
Upgrade ALIVE to the current version. Handles v1/v2/v3.x source states, multi-surface aware (alive-mcp / Hermes / Codex), retroactive version detection, partial-failure resume, dry-run previews, and rollback inspection.
extract-resume
Parse a resume's uploaded PDF into structured JSON (basics, experience, projects, skills, education) and save it to the editor.
codex-test-gen
Generate unit tests for specified functions using Codex exec.