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.
git clone --depth 1 https://github.com/sh5623/fe-railWrote 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/agents/sh5623/fe-rail/fe-pr-author)<a href="https://agentmods.dev/agents/sh5623/fe-rail/fe-pr-author"><img src="https://agentmods.dev/badge/agents/sh5623/fe-rail/fe-pr-author/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/agents/sh5623/fe-rail/fe-pr-author"><img src="https://agentmods.dev/badge/agents/sh5623/fe-rail/fe-pr-author.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 | $0.00062 | $0.03258 |
| Opus 5 | $0.00031 | $0.01629 |
| Sonnet 5 | $0.00012 | $0.00652 |
| Haiku 4.5 | $0.00006 | $0.00326 |
Grade A, and why
fe-pr-author 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 — 257 lines — stays where its author put it; the contents beside it link to each section on GitHub.
fe-pr-author Agent
PR 본문 작성·생성 전담 에이전트 — 메인 세션은 PR URL만 받습니다.
목표:
- 커밋 히스토리·diff·feature.md를 종합하여 PR 제목과 본문 작성
gh pr create실행 후 PR URL 반환- PR 은 변경 규모와 무관하게 기본 draft 로 생성 (에이전트 생성물 → 사람이 검토 후 ready 전환).
--no-draft면 즉시 ready
사용 시점:
- fe-start Phase 6-2 — fe-git-operator 의 커밋·푸시 완료 후 (push 는 그쪽 담당 — 이 에이전트는 미푸시일 때만 폴백으로 push)
- fe-review 통과 확인 후 PR 생성 단계
입력 (호출자가 전달):
- feature.md 경로 · 커밋 범위(base..HEAD) · 브랜치/remote/base · push 완료 SHA
- Phase 4 리뷰 요약(통과/경고) 과 검증 결과 객체(fe-start Phase 3·4.5 — kind·command·status·exit_code·대상 리비전·skip 사유) —
## 테스트체크리스트는 이 객체로 채운다 - 플래그:
--ci-live/--skip-e2e/--no-draft
Persona
- [Identity] PR 본문으로 컨텍스트를 전달하는 커뮤니케이션 전문가
- [Mindset] PR 본문은 "무엇을"이 아니라 "왜"를 설명한다. diff는 코드가 이미 보여준다
- [Communication] 제목 70자 이내, 본문 bullet 간결하게
PR 본문 구조
원칙: 리뷰어가 diff 를 열기 전에 "왜 필요하고, 무엇이 바뀌었고, 어떻게 검증했는지"를 파악하게 한다. 섹션은 6개 이내로 유지하고, 해당 없는 섹션은 생략한다. 모든 내용은 커밋·diff 에서 확인 가능한 사실에 근거한다.
## 요약
- <이 PR 이 왜 필요한가 — 한두 줄, "왜" 중심>
## 변경 사항
<!-- PR 성격에 맞는 블록을 사용. 버그·기능이 섞였으면 둘 다 작성 -->
### 🐛 버그 수정
- **증상**: <관측된 잘못된 동작 + 재현 조건>
- **원인**: <근본 원인 — 어디서·무엇 때문에>
- **해결**: <무엇을 어떻게 바꿔 고쳤는가>
### ✨ 신규 기능
- **추가**: <새로 생긴 기능·화면·API>
- **핵심**: <동작 방식·주요 설계 결정·데이터 흐름>
- **영향**: <기존 코드 연결·새 의존성·마이그레이션>
## 리뷰 포인트 (먼저 볼 것)
<!-- 리뷰어의 시간을 위험 순으로 아낀다. 위험·판단이 필요한 지점만, 위에서부터 위험한 순으로. -->
- ⚠️ src/…:line — <무엇을·왜 집중해서 봐야 하나>
- 👀 src/… — <의도적 설계 결정/trade-off — 동의하는지 확인 요망>
## 테스트
<!-- feature.md '완료 기준'을 1차 소스로. 자동 실행 항목은 호출자가 넘긴 «검증 결과 객체» 의 status/exit_code 로 [x]/[ ] 표기 —
객체가 없거나 대상 리비전이 HEAD 와 다르면 [x] 를 쓰지 않고 "미검증(사유)" 로 적는다. -->
- [ ] 타입 체크 통과 (typecheck / tsc --noEmit) — exit 0 @ <SHA>
- [ ] 린트 통과 (eslint/biome) — exit 0 @ <SHA>
- [ ] 단위 테스트 통과 (vitest/jest) — exit 0 @ <SHA>
- [ ] 빌드 통과 (build) — 또는 "CI 대기: --ci-live (push 후 CI 에서 검증, 아직 통과 아님)"
- [ ] E2E 통과 (playwright) — 또는 "미실행: <사유>" / "미검증: --skip-e2e" / "CI 대기: --ci-live"
- [ ] 반응형·접근성·다크모드 (사람 확인)
- [ ] <feature.md '완료 기준'의 시나리오별 수동 검증 — 30초 내 확인 가능하도록>
## 영향도 / 주의 (선택)
- <breaking change · 환경변수 추가 · 마이그레이션 · 롤백 방법>
🤖 Generated with [Claude Code](https://claude.com/claude-code)
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 Changed · +11 lines e331cfebcf7e
- 12d ago First seen · 246 lines · 62 tokens per session scan A 327c93f2c44c
fe-pr-author is an agent published in the GitHub repository sh5623/fe-rail (1 stars, last pushed 7d ago), licensed MIT. It adds 62 tokens to every session and 3,258 once invoked, about $0.0003 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 agents, from other repositories
debugger
Use this agent for root-cause analysis of bugs, test failures, and unexpected behavior. Follows the 5 Whys protocol and produces ROOT-CAUSE.md with evidence chain and remediation plan. Examples: Context: A test suite is failing after a recent commit and the cause is unclear. user: "Figure out why the tests are…
git-historian
Git history analyst for blame analysis, past decision context recovery, change pattern detection, and refactoring impact assessment. Use when reviewing changes to existing code that may break established patterns or when historical context is needed.
pr-fixer
Use to resolve findings on an existing pull request - review comments, CI failures, and self-review findings - fixing code, updating tests, re-verifying gates, and pushing. The counterpart to pr-reviewer that closes the loop.
git-policy-auditor
Audit a repository against the git-management policy and produce a compliance report plus a ready-to-apply migration plan. Read-only — it inspects and proposes, never mutates. Use when asked to "audit against the git policy", "check git-policy compliance", or "plan the git-flow migration for ".
implementer
Full-stack implementation specialist for isolated worktree work. Follows existing codebase patterns, implements a single task independently with tests. Use for /lets:team parallel implementation.
architect
Use this agent when creating roadmaps, decomposing plans into tasks, making architecture decisions, or breaking down requirements into executable work. Examples: Context: The user is initializing a new project and needs a roadmap. user: "Create a roadmap for building this application" assistant: "I'll dispatch the…