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 sh5623/fe-rail --skill fe-doc-syncgit 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/skills/sh5623/fe-rail/fe-doc-sync)<a href="https://agentmods.dev/skills/sh5623/fe-rail/fe-doc-sync"><img src="https://agentmods.dev/badge/skills/sh5623/fe-rail/fe-doc-sync/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/skills/sh5623/fe-rail/fe-doc-sync"><img src="https://agentmods.dev/badge/skills/sh5623/fe-rail/fe-doc-sync.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 | $0.00077 | $0.02947 |
| Opus 5 | $0.00039 | $0.01473 |
| Sonnet 5 | $0.00015 | $0.00589 |
| Haiku 4.5 | $0.00008 | $0.00295 |
Grade A, and why
fe-doc-sync 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 10d 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 — 260 lines — stays where its author put it; the contents beside it link to each section on GitHub.
fe-doc-sync — 사용자 프로젝트 문서 동기화 스킬
이 스킬은 fe-rail 플러그인 자체가 아니라, 이 플러그인을 설치한 사용자 프로젝트
(예: Vibe App, 모노레포 등)에서 호출됩니다.
호출 시점의 작업 디렉토리(cwd)를 기준으로 프로젝트 전반을 스캔해
해당 프로젝트의 CLAUDE.md / README.md 가 실제 코드와 일치하도록 동기화합니다.
중요: 사용자 프로젝트에
CLAUDE.md또는README.md가 없다면 생성을 제안한다. 단, 새 파일을 임의로 만들지 말고 Phase 4 수정안 → Phase 5 승인 절차를 거친다.
Phase 1: 프로젝트 식별 및 전체 스캔
(A) 프로젝트 타입 감지
package.json 을 읽어 프레임워크와 구조를 판별한다.
# 루트 + 모노레포 앱들의 package.json 위치
fd -t f -e json --max-depth 4 --hidden -E node_modules -E .next -E dist 'package.json' . 2>/dev/null \
|| find . -maxdepth 4 -name package.json -not -path '*/node_modules/*' -not -path '*/.next/*' -not -path '*/dist/*'
# 워크스페이스 여부
cat package.json 2>/dev/null | grep -E '"workspaces"|"packageManager"'
판별 매트릭스:
| package.json 의존성 | 판별 |
|---|---|
next |
Next.js 앱 (App Router 여부는 app/ vs pages/ 존재로 추가 판별) |
vite + @tanstack/react-router |
Vite SPA (TanStack Router) |
vite + (react-router 또는 react-router-dom) v7 이상 |
Vite SPA (React Router 7·8) — 데이터는 TanStack Query 단독 소유. v8 은 react-router-dom 제거됨 |
vite + react-router-dom v6 이하 |
Vite SPA (React Router 레거시) |
workspaces 필드 존재 + apps/·packages/ |
모노레포 |
react-native |
RN Web (참고만, fe-rail 주 대상 아님) |
(B) 프로젝트 구조 스캔
# 핵심 디렉토리 트리 (깊이 3까지)
fd -t d --max-depth 3 -E node_modules -E .next -E dist -E .git . 2>/dev/null \
|| find . -maxdepth 3 -type d -not -path '*/node_modules/*' -not -path '*/.next/*' -not -path '*/dist/*' -not -path '*/.git/*'
# 라우트 파일 카운트
# - Next App Router
fd 'page\.(tsx|ts|jsx|js)$' app 2>/dev/null | wc -l
# - Next Pages Router
fd '\.(tsx|ts|jsx|js)$' pages 2>/dev/null | wc -l
# - TanStack Router
fd '\.(tsx|ts)$' src/routes 2>/dev/null | wc -l
# 주요 디렉토리 카운트
for d in components hooks lib services stores api features; do
count=$(fd -t f --max-depth 5 . "$d" 2>/dev/null | wc -l | tr -d ' ')
[ "$count" != "0" ] && echo "$d: $count"
done
# 모노레포면 apps/ packages/ 목록
ls -1 apps/ packages/ 2>/dev/null
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.
- 10d ago First seen · 260 lines · 77 tokens per session scan A 628cd3251229
fe-doc-sync is a skill published in the GitHub repository sh5623/fe-rail (1 stars, last pushed 5d ago), licensed MIT. It adds 77 tokens to every session and 2,947 once invoked, about $0.0004 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 skills, from other repositories
git-workflow
Use when starting feature work that needs a branch, creating worktrees for isolation, making atomic commits during development, or completing a development branch via merge, PR, preserve, or discard. Also use when the user says "set up worktree", "create PR", "finish this branch", "start feature", or when you need an…
context-review
Skill "context-review" from morodomi/dev-crew, covering context review, usage, workflow, question categories and resolution values.
mode-interactive
The interactive implementation posture (/foundry:mode-interactive) — the default lean direct loop. The operator drives edit→verify→merge in one accountable context; the operator reviews the diff at the merge button (the Regular-mode segregation). Sibling of mode-autonomous; they differ ONLY at the two ends (who paces…
stagent
Drive the dev workflow state machine: read state.md, execute the current stage (inline or subagent), transition via update-status.sh, loop until terminal. Precondition: state.md already exists (some upstream caller bootstrapped it). Does NOT bootstrap.
create
Create a new workflow suite from a natural-language description, or edit an existing one when --flow= is passed. Dispatches the create-workflow stagent (plan → write → validate loop) — does not write files directly.
stagent-setup
Bootstrap a dev workflow session (for /stagent:start): parse flags, derive a topic from the task description, call setup-workflow.sh, and hand off to the workflow loop skill. Does NOT drive the state machine — that's stagent:stagent's job.