Borrowing it
Nothing to install: this file belongs to joseph0926/prompt-shield. 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/joseph0926/prompt-shield/main/CLAUDE.mdgit clone --depth 1 https://github.com/joseph0926/prompt-shieldWrote 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/instructions/joseph0926/prompt-shield/claude-md)<a href="https://agentmods.dev/instructions/joseph0926/prompt-shield/claude-md"><img src="https://agentmods.dev/badge/instructions/joseph0926/prompt-shield/claude-md.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 | $0.01198 | $0.01198 |
| Opus 5 | $0.00599 | $0.00599 |
| Sonnet 5 | $0.00240 | $0.00240 |
| Haiku 4.5 | $0.00120 | $0.00120 |
Grade A, and why
prompt-shield CLAUDE.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 7d 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.
How it starts
The opening of the file, as written. The whole thing — 138 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PromptShield
Prompt Quality Gate + PromptOps 표준 패키지 Claude Code + MCP 생태계의 프롬프트 품질 관리 표준
포지셔닝
이 프로젝트는 "Prompt improver"가 아닙니다.
우리의 목표:
- 훅(작성 시점 강제) + 레지스트리(자산화) + 테스트(회귀) + CI(게이트)
- 개발 조직이 원하는 "프롬프트 품질 표준"을 제공
- Eval/Red-team은 promptfoo와 연동으로 해결
아키텍처 개요
┌─────────────────────────────────────────────────────────────┐
│ Developer Workflow │
├─────────────────────────────────────────────────────────────┤
│ [작성] ──→ [Hook: lint] ──→ [Commit] ──→ [CI: Gate] ──→ [Merge]
│ ↓
│ [Registry: Save]
│ ↓
│ [Eval: Regression]
└─────────────────────────────────────────────────────────────┘
핵심 모듈:
├── lint-engine/ # 단일 규칙 엔진 (Hook/CI 공유)
├── registry/ # MCP 서버 (버전/롤백/디프)
├── eval/ # 회귀 테스트 러너
├── pack/ # PromptPack 패키징
└── adapters/ # promptfoo 연동
개발 원칙
1. 결정적 제어 (Deterministic Control)
- Hook과 CI는 같은 규칙 엔진을 사용해야 함
- "환경마다 점수가 다름"은 신뢰를 깨뜨림
- 결과는 항상 예측 가능해야 함
2. Gate > Report
- "리포트만 남김"은 Gate가 아님
- 품질 기준 미달 시 빌드 실패 (exit 1)
- 경고만 남기는 기능은 Gate로 인정하지 않음
3. 로컬 우선
- 모든 기능은 로컬에서 먼저 동작해야 함
- Claude CLI 기반 실행 지원
- 외부 서비스 의존성 최소화
4. 연동 > 구현
- 이미 강력한 도구가 있으면 연동
- promptfoo: eval/red-team
- Claude Code: hooks
- 중복 구현 금지
코드 컨벤션
파일 구조
skills/prompt-shield/
├── playbooks/ # 스킬 실행 플레이북
├── scripts/ # CI/실행 스크립트
├── plugins/ # MCP 서버 플러그인
│ └── prompt-registry/ # Registry MCP 서버
└── docs/ # 문서
스크립트 작성
- CI 스크립트는 exit code 정책 명확히
- threshold는 config 파일로 (하드코딩 금지)
- 실패 메시지에 원인 포함 (파일/점수/기준)
MCP 서버
- MCP spec 준수: tools/resources/prompts capability
- 에러 메시지 표준화 (isError=true로 self-correct 유도)
- 버전 히스토리 유지 (rollback/diff 지원)
테스트
- 결정적 assertion 우선 (contains/regex/json schema)
- LLM judge는 보조적 (나중에)
- 캐시 지원 (동일 입력 재실행 비용 절감)
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.
- 7d ago First seen · 138 lines · 1,198 tokens per session scan A e1dfebfed734
prompt-shield CLAUDE.md is an instructions file published in the GitHub repository joseph0926/prompt-shield (5 stars, last pushed 7mo ago), licensed MIT. It adds 1,198 tokens to every session, about $0.0060 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.
Other instructions, from other repositories
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.