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 agentmods add instructions/joseph0926/prompt-shield/agents-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/agents-md)<a href="https://agentmods.dev/instructions/joseph0926/prompt-shield/agents-md"><img src="https://agentmods.dev/badge/instructions/joseph0926/prompt-shield/agents-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 | $0.02456 | $0.02456 |
| Opus 5 | $0.01228 | $0.01228 |
| Sonnet 5 | $0.00491 | $0.00491 |
| Haiku 4.5 | $0.00246 | $0.00246 |
Grade A, and why
prompt-shield 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 5d 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 — 337 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PromptShield Agents
멀티 에이전트 워크플로우를 위한 역할 정의 각 에이전트는 특정 스프린트/모듈에 특화됨
에이전트 목록
| Agent | 담당 영역 | 주요 스프린트 |
|---|---|---|
gate-agent |
CI Gate, threshold 관리 | Sprint 1, 6 |
lint-agent |
규칙 엔진, Hook 통합 | Sprint 2 |
registry-agent |
MCP Registry, 버저닝 | Sprint 3, 8 |
pack-agent |
PromptPack 패키징 | Sprint 4 |
eval-agent |
평가 러너, assertion | Sprint 5, 6, 7 |
adapter-agent |
promptfoo 연동 | Sprint 7 |
gate-agent
<agent_definition> CI Gate 전문가 prompt-shield의 CI Gate는 "리포트만 남김"이 아니라 "머지 차단"이 목표입니다. 품질 기준 미달 시 exit 1로 빌드를 실패시켜야 합니다.
-
실패 출력 시:
- 실패한 파일 top N 출력
- 각 파일의 주요 감점 항목 2~3개
- 전체 점수/기준/실패 조건 요약
-
PR 요약 시:
- 리뷰어가 링크/로컬 재현 없이 원인 이해 가능하게
- 수정 방향 제안 포함
lint-agent
<agent_definition> 규칙 엔진 전문가 Hook과 CI가 동일한 규칙 엔진을 사용해야 합니다. "환경마다 점수가 다름"은 신뢰를 깨뜨립니다.
-
룰 구현 시:
- 정규식 기반 체크
- 필수 섹션 체크
- 금칙어/패턴 체크
- 각 룰에 심각도(error/warning/info) 부여
-
통합 시:
- CI: 엔진 결과 → CI 요약 포맷 변환
- Hook: 엔진 결과 → warn/block 결정
- 동일 입력에 동일 결과 보장
registry-agent
<agent_definition> MCP Registry 전문가 프롬프트를 코드처럼 관리하려면 버저닝이 핵심입니다. Registry v2는 버전 히스토리/롤백/디프를 지원합니다.
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.
- 5d ago First seen · 337 lines · 2,456 tokens per session scan A 6704d5f94d77
prompt-shield AGENTS.md is an instructions file published in the GitHub repository joseph0926/prompt-shield (5 stars, last pushed 7mo ago), licensed MIT. It adds 2,456 tokens to every session, about $0.0123 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
pg-aiguide CLAUDE.md
Claude Code instructions for timescale/pg-aiguide, covering tiger docs mcp server - development guidelines, build, test & run commands, code style guidelines and python (ingest/).
markifact-mcp GEMINI.md
Instructions for markifact/markifact-mcp, covering markifact, the 8 tools, discover → inspect → run, connection vs account and reporting workflow.
supergraph AGENTS.md
AGENTS.md instructions for datit309/supergraph, covering supergraph — mandatory workflows, skills, auto language detection, tiered workflow — pick the right tier first and full pipeline (tier 3).
bundles-forge AGENTS.md
Instructions for OdradekAI/bundles-forge, covering project knowledge base, structure, where to look, conventions and anti-patterns (this project).
embedded-systems-architect AGENTS.md
Instructions for Zachariah9420/embedded-systems-architect: This repository ships an agent skill for embedded-systems and edge-AI development work.
frankfurter-api AGENTS.md
Instructions for NanookAI/frankfurter-api, covering agent instructions, layout, conventions, known live-api facts worth preserving and validation checklist before committing.