project-legibility AGENTS.md

Repository instructions for project-legibility, including its documentation language rules, source-of-truth process, release practices, and validation commands.

In plain words
What is it for?
Use them when changing project-legibility documentation, skills, bundles, tests, synchronization scripts, or release-related files.
Why use it?
They help an agent keep generated bundles, English and Korean documents, versions, and release records consistent with the canonical skill repository.

Instructions file for CodexOpenCode

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.

agentmods
npx agentmods add instructions/perhapsspy/project-legibility/agents-md
Clone the repo
git clone --depth 1 https://github.com/perhapsspy/project-legibility

Made for: Codex, OpenCode.

Per session 449 This file is loaded in full into every session.
When invoked 449 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
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 $0.00449 $0.00449
Opus 5 $0.00225 $0.00225
Sonnet 5 $0.00090 $0.00090
Haiku 4.5 $0.00045 $0.00045

Measured 2d ago against content hash 3a5eb0aca9ba, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

project-legibility AGENTS.md 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 2d 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.

AGENTS.md · 16 lines

What it actually says

AGENTS.md

  • 일반 문서와 작업 기록은 한국어를 기본으로 쓰고, 공개 진입 문서는 *.en.md 영어 pair를 함께 유지한다.
  • 요청 범위 안의 구현과 검증은 직접 완료한다. 새 제품 정책, 영구 검증이나 release 전환처럼 별도 수명주기를 만드는 변경은 사용자 요청 또는 현재 정본의 승인된 결정에 연결한다.
  • 개별 스킬 저장소가 정본이다. 제품 약속이나 bundle 구성을 바꿀 때는 docs/PRODUCT.md를 먼저 갱신한다. 정본 스킬 내용을 바꿨다면 해당 저장소에서 검증·push하고, 이후 scripts/sync_skills.py로 생성 bundle과 lock을 맞춘다. plugins/project-legibility/skills/는 직접 수정하지 않는다.
  • 폐기할 실험·브라우저 검증 코드, 실행 상태와 원시 출력은 사용자 환경과 분리한 저장소 밖 임시 위치에 두고 확인 뒤 정리한다. 보존할 코드와 증거는 정식 소스, 테스트, 런북 또는 산출물 owner에 둔다.
  • docs/tasks/에는 사람이 읽는 현재 상태, 목적, 방법, 결과, 결정과 간결한 근거 요약만 둔다.
  • 삭제·교체는 현재 정본과 구성에서 대상을 제거해 표현한다. denylist나 tombstone은 현재 외부 안전·호환성 계약이 요구하고 범위와 해제 조건이 정해진 경우에만 둔다.
  • plugin version, 한영 CHANGELOG, tag와 publisher pin은 실제 게시를 수행하는 별도 release 작업에서 릴리스 런북에 따라 함께 갱신한다. publisher marketplace는 perhapsspy/codex-plugins에서 push된 Project Legibility release commit만 고정한다.

검증

  • python3 scripts/sync_skills.py check --offline
  • python3 scripts/validate_bundle.py
  • python3 -m unittest discover -s tests -v
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. 2d ago First seen · 16 lines · 449 tokens per session scan A 3a5eb0aca9ba

Subscribe to this mod's changes

project-legibility AGENTS.md is an instructions file published in the GitHub repository perhapsspy/project-legibility (5 stars, last pushed 4d ago), licensed MIT. It adds 449 tokens to every session, about $0.0022 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 2026-08-31.

Related

Other instructions, from other repositories