Borrowing it
Nothing to install: this file belongs to huurray/fe-review-agents. 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/huurray/fe-review-agents/main/CLAUDE.mdgit clone --depth 1 https://github.com/huurray/fe-review-agentsWrote 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/huurray/fe-review-agents/claude-md)<a href="https://agentmods.dev/instructions/huurray/fe-review-agents/claude-md"><img src="https://agentmods.dev/badge/instructions/huurray/fe-review-agents/claude-md/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/instructions/huurray/fe-review-agents/claude-md"><img src="https://agentmods.dev/badge/instructions/huurray/fe-review-agents/claude-md.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 | $0.02566 | $0.02566 |
| Opus 5 | $0.01283 | $0.01283 |
| Sonnet 5 | $0.00513 | $0.00513 |
| Haiku 4.5 | $0.00257 | $0.00257 |
Grade A, and why
fe-review-agents 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 9d 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 — 124 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
Project-specific guidance for Claude Code.
What this is
fe-review-agents is a Claude Code plugin. The repo doubles as its own marketplace via .claude-plugin/marketplace.json. It ships:
- Two slash commands (
commands/diff-review.md,commands/file-review.md) that orchestrate a multi-reviewer review. - Six reviewer agents (
agents/reviewer-{react-perf,quality,bugs,ts,a11y,security}.md). - A synthesizer agent (
agents/synthesizer.md) that merges 6 reviewer outputs into a single prioritized markdown report. - A plugin manifest (
.claude-plugin/plugin.json) + a single-plugin marketplace manifest (.claude-plugin/marketplace.json).
Distribution: GitHub repo as marketplace. Users install in Claude Code via /plugin marketplace add huurray/fe-review-agents → /plugin install fe-review-agents@fe-review-agents. Claude Code only since v0.6.0.
Architecture invariants — don't break
Always dispatch all 6 reviewers in a single assistant message. The slash commands instruct the main session to issue 6 Agent tool_use blocks together. This is the parallel-dispatch pattern from huurray/parallel-test. Do NOT add triage, do NOT dispatch one-by-one. The main session is the orchestrator; sub-agents cannot spawn sub-agents, so all 6 fire from the top-level message.
Per-reviewer context isolation is the load-bearing value. Each reviewer runs in its own sub-agent with a fresh context, so findings stay independent (no cross-axis reasoning contamination, no mode collapse toward the loudest signal). This matters regardless of whether dispatch ends up wall-clock parallel or serialized at runtime — the isolation is what makes the merged report better than a single-context "review for everything" pass.
Synthesizer is markdown-in, markdown-out. Reviewers emit one-line findings: - **[axis/rule-id]** [SEVERITY] Line N: <issue> — <fix>. Synthesizer takes 6 such markdown blocks (concatenated under ## 1. Performance / ## 2. Code Quality / etc. headers) and produces a single prioritized report. No JSON merging, no overlap dedup logic — the synthesizer just sorts by severity and dedups identical rule IDs at the same line.
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.
- 9d ago First seen · 124 lines · 2,566 tokens per session scan A 35c06963705d
fe-review-agents CLAUDE.md is an instructions file published in the GitHub repository huurray/fe-review-agents (5 stars, last pushed 4mo ago), licensed MIT. It adds 2,566 tokens to every session, about $0.0128 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
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.
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).
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).
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.
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.