Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/jhlee0409/claude-pluginsnpx agentmods add commands/jhlee0409/claude-plugins/initWrote 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/commands/jhlee0409/claude-plugins/init)<a href="https://agentmods.dev/commands/jhlee0409/claude-plugins/init"><img src="https://agentmods.dev/badge/commands/jhlee0409/claude-plugins/init/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/commands/jhlee0409/claude-plugins/init"><img src="https://agentmods.dev/badge/commands/jhlee0409/claude-plugins/init.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 | $0.00007 | $0.07146 |
| Opus 5.5 | $0.00003 | $0.02858 |
| Sonnet 5.5 | $0.00001 | $0.01429 |
| Haiku 4.5 | $0.00001 | $0.00715 |
Grade A, and why
init 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 1mo 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 — 978 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/fsdarch:init
프로젝트의 FSD 구조를 분석하고 설정 파일을 생성합니다.
Prerequisites
- 프로젝트 루트 디렉토리에서 실행
src/또는 유사한 소스 디렉토리 존재
EXECUTION INSTRUCTIONS
When /fsdarch:init is invoked, Claude MUST perform these steps in order:
- Check existing config - Verify
.fsd-architect.jsondoesn't exist (unless --force) - Detect source directory - Find src/, app/, lib/, or ask user
- Use skill: layer-detector - Scan for FSD layer directories
- Analyze patterns - Detect naming, segments, import aliases
- Generate config - Write
.fsd-architect.json - Security check - Verify .gitignore includes cache files
- Report summary - Show detected structure and next steps
Flow Overview
┌───────────────────────────────────────────────────────────────┐
│ /fsdarch:init │
├───────────────────────────────────────────────────────────────┤
│ Step 0. Check if .fsd-architect.json exists │
│ ├─ Exists + no --force → Error E103 │
│ └─ Not exists OR --force → Continue │
│ │
│ Step 1. Detect source directory │
│ ├─ Check src/, app/, lib/ in order │
│ ├─ If found → Use it │
│ └─ If not found → Ask user (AskUserQuestion) │
│ │
│ Step 1.5. Detect framework (Next.js, etc.) │
│ ├─ Check package.json for "next" │
│ ├─ If Next.js → Detect router mode (Step 1.6) │
│ └─ If not → Use standard names (app, pages) │
│ │
│ Step 1.6. Detect Next.js router mode (if Next.js) │
│ ├─ Check for App Router: app/layout.tsx, app/page.tsx │
│ ├─ Check for Pages Router: pages/_app.tsx, pages/index │
│ ├─ If BOTH exist → HYBRID MODE │
│ │ └─ Both app/ and pages/ reserved for routing │
│ ├─ If only App Router → Single mode (app reserved) │
│ ├─ If only Pages Router → Single mode (pages reserved) │
│ └─ Ask user for FSD layer aliases │
│ │
│ Step 2. Invoke skill: layer-detector │
│ ├─ Scan for FSD layers in srcDir (with aliases) │
│ ├─ If layers found → Continue to Step 3 │
│ └─ If no layers → Ask "Create new FSD structure?" │
│ │
│ Step 3. Analyze existing patterns (if code exists) │
│ ├─ Naming convention (kebab-case/camelCase/PascalCase) │
│ ├─ Segment usage (ui/, model/, api/, lib/) │
│ ├─ Index file patterns │
│ └─ Import aliases from tsconfig.json │
│ │
│ Step 4. Generate .fsd-architect.json │
│ │
│ Step 4.5. Configure tsconfig.json paths (Optional) │
│ ├─ Ask user if they want path aliases │
│ ├─ If YES → Generate/merge paths in tsconfig.json │
│ └─ Apply layerAliases to path generation │
│ │
│ Step 4.6. Suggest bundler config (Vite only) │
│ └─ Display vite.config.ts alias suggestions │
│ │
│ Step 5. Check .gitignore for cache files │
│ │
│ Step 6. Display summary and next steps │
└───────────────────────────────────────────────────────────────┘
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.
- 1mo ago First seen · 978 lines · 7 tokens per session scan A 14be16b1fe22
init is a command published in the GitHub repository jhlee0409/claude-plugins (4 stars, last pushed 9mo ago), licensed MIT. It adds 7 tokens to every session and 7,146 once invoked, about $0.0000 per session on Opus 5.5. 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 commands, from other repositories
skill-refresh
You are running inside a headless Claude Code session in the neo4j-skills repository. Goal: scan Neo4j release notes and deprecation pages, then update any SKILL.md and references/ files that are stale, outdated, or missing new features. Open no PRs or commits — output only file edits. The workflow will handle git and…
speckit.md-doctor.drift
Re-evaluate since the last run: compute the git/.memsearch/TDD delta, re-score previously graded files in light of what changed, and report which past suggestions were resolved or are now stale/false.
speckit.tdd.plan
Derive the feature's test list by delegating to zfa tdd plan (deterministic engine); falls back to LLM-guided derivation only when zfa is unavailable.
speckit.gym.drop
Record a drop card from a mis-fire. A mis-fire is not a mistake to punish — it is a discovery to keep. Drop cards capture what was done, what was expected, and what happened, persisted to the configured redundant stores (default /drops/ plus the extension's append-only .drop-ledger.md).
speckit.spec-stats.open
On-demand view of everything not complete: what stage each is stuck at, what the immediate next artifact/command is, oldest-untouched first, stale warnings past staleafterdays.
new-month
Start a new month for a brand: folder and settings; a calendar to load -> parse-calendar; ideas -> ideate-month. "start a new month for this brand".