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 Insajin/autopus-adk --skill lore-commitgit clone --depth 1 https://github.com/Insajin/autopus-adkWrote 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/insajin/autopus-adk/lore-commit)<a href="https://agentmods.dev/skills/insajin/autopus-adk/lore-commit"><img src="https://agentmods.dev/badge/skills/insajin/autopus-adk/lore-commit.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 5.1 | $0.00020 | $0.00672 |
| Opus 5 | $0.00010 | $0.00336 |
| Sonnet 5 | $0.00004 | $0.00134 |
| Haiku 4.5 | $0.00002 | $0.00067 |
Grade A, and why
lore-commit 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 3d 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
Lore Commit Skill
Lore 형식으로 의사결정을 커밋 메시지에 기록하는 스킬입니다.
Lore 커밋 형식
기본 구조
<type>(<scope>): <subject>
<body>
<lore-trailers>
🐙 Autopus <[email protected]>
타입 분류
| 타입 | 설명 |
|---|---|
feat |
새로운 기능 추가 |
fix |
버그 수정 |
refactor |
기능 변경 없는 코드 개선 |
test |
테스트 추가/수정 |
docs |
문서 수정 |
chore |
빌드, 설정 변경 |
perf |
성능 개선 |
Lore 트레일러 태그
현재 프로토콜
Constraint: [지켜야 하는 제약 또는 경계]
Rejected: [버린 대안]
Confidence: [low|medium|high]
Scope-risk: [local|module|system]
Reversibility: [trivial|moderate|difficult]
Directive: [후속 작업 지침]
Tested: [검증한 항목]
Not-tested: [아직 검증하지 못한 항목]
Related: [관련 이슈/PR/SPEC]
기본 요구사항
auto check --lore -> 타입 프리픽스 + Autopus 사인오프 검사
auto lore validate -> 설정된 required_trailers 기반 Lore 트레일러 검사
예시
feat(auth): JWT 기반 인증 구현
사용자 세션 관리를 위해 JWT 토큰 방식을 도입합니다.
기존 세션 쿠키 방식에서 마이크로서비스 환경에 적합한
Stateless 인증으로 전환합니다.
Constraint: stateless 인증 흐름 유지
Rejected: 세션 저장소 기반 인증
Confidence: medium
Scope-risk: module
Reversibility: moderate
Directive: refresh token 정책은 후속 SPEC으로 분리
Tested: JWT 발급 및 검증 통합 테스트
Not-tested: 토큰 로테이션 장애 복구
Related: SPEC-AUTH-001
🐙 Autopus <[email protected]>
작성 지침
- Subject는 Lore 타입 프리픽스로 시작한다. 예:
fix(cli): ... - Body는 배경과 의도를 간결하게 남긴다.
- 새 Lore 트레일러는
Constraint중심 프로토콜을 사용한다. Why/Decision/Alternatives예시는 더 이상 표준이 아니다.
자동 검사
auto check --lore 실행 시 다음을 검사합니다:
- 커밋 메시지 형식 준수 여부
- Autopus 사인오프 존재 여부
auto lore validate 실행 시 다음을 검사합니다:
required_trailers충족 여부Confidence,Scope-risk,Reversibility값 유효성
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.
- 3d ago First seen · 93 lines · 20 tokens per session scan A 5f3e4e07d4b4
lore-commit is a skill published in the GitHub repository Insajin/autopus-adk (109 stars, last pushed today), licensed MIT. It adds 20 tokens to every session and 672 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 2026-09-03.
Other skills, from other repositories
git-commit
Create well-structured conventional commit messages following Conventional Commits standard. Use when committing changes, preparing PRs, or generating changelogs.
update-readme
Detect feature commits and update README sections (Features, API, Usage) with accurate repo-aware changes, then stage only README for a docs commit. Use when users add features/routes/components and want README maintained automatically.
atmos-git
Atmos Git and GitOps: git.repositories, clone/pull/status/diff/commit/push/clean, local Git hook shims, signed commits, managed workdirs, fork-PR trust gate, and auth via identities or github/sts.
commit-pr
Mandatory Codex/Copilot publication adapter for opencode-swarm. Use for every GitHub issue assignment that results in code changes, commits, pushes, draft PRs, PR body edits, PR readying, release notes, or CI closeout. Must be loaded before git push, gh pr create, gh pr edit, or gh pr ready. Routes to the single…
contributing
Codex adapter for the opencode-swarm contribution checklist. Use when preparing user-visible changes, release note fragments, local validation, branch hygiene, PR checklist items, or contribution-policy compliance before publishing work.
experiment-loop
Autonomous benchmark-driven experiment loop: propose a change, measure the metric, keep what improves it, revert what doesn't, repeat. Git is the ledger — every kept improvement is a commit. Every discarded attempt is a clean revert.