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/fancy1108/clutch/agents-mdgit clone --depth 1 https://github.com/fancy1108/ClutchWhat 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 | $0.01585 | $0.01585 |
| Opus 5 | $0.00792 | $0.00792 |
| Sonnet 5 | $0.00317 | $0.00317 |
| Haiku 4.5 | $0.00159 | $0.00159 |
Grade B, and why
Clutch AGENTS.md scanned grade B with 2 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 3d 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.
Sends data to an external URLmediumData exfiltration
A POST to an outside endpoint may be telemetry or may be exfiltration; either way the mod talks to somewhere, and you should know where.
- **Web mode has no folder picker.** Workspace/folder selection needs Tauri desktop APIs, so onboarding blocks core features (chat, workflows). To unblock in the browser, authorize a workspace directly against the sideca Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- Frontend: `pnpm dev` (Vite on `:3000`, proxies `/api`, `/ws`, `/health` → `8124`). Health check: `curl -s http://127.0.0.1:8124/health` → `{"status":"ok",...}`. How it starts
The opening of the file, as written. The whole thing — 53 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Clutch — Agent Instructions Index
跨 AI 工具的统一入口。不要在本文件维护实质规则——规则只写在权威源里，本文件只做指针。
| 文档 | 读者 | 用途 |
|---|---|---|
CLAUDE.md |
Claude Code、全体开发者 | 唯一权威：铁律、命令、Check-in、日志规范 |
memory/PROGRESS.md |
所有 Agent | 跨会话进度接力棒 |
memory/DELIVERABLES.md |
所有 Agent | Task 交付索引（Commit / Verification / 证据） |
memory/DECISIONS.md |
所有 Agent | 最新决策与开放问题（唯一汇总地） |
memory/FILEMAP.md |
所有 Agent | 文件路径速查（Check-in 用） |
specs/core/proposal.md |
产品追溯 | 历史快照，非权威 |
specs/core/tasks.md |
全体开发者 | M0–M4 开发任务清单 |
specs/core/clutch-agent-capability-plan.md |
Chat Agent 开发者 | Chat 自研 Clutch Agent 能力交付表 D0–D53（D44） |
specs/core/prd-one-click-interactive-prototype.md |
全体开发者 | 一键原型生成与交互契约规格 (PRD) |
specs/core/hybrid-runtime-plan.md |
Hybrid 开发者 | D25 HRT Task 与验收（权威） |
specs/core/frontend-modules-plan.md |
全体开发者 | 前端可点验模块 FM-01…FM-22（D56） |
docs/FRONTEND_MODULES_ACCEPTANCE.md |
PM / 验收 | FM-01…22 桌面点验剧本（入口、步骤、期望） |
specs/core/design.md |
前端开发者 | 视觉设计快照 → docs/UI_UX_GUIDELINES.md |
docs/UI_UX_GUIDELINES.md |
前端开发者 | React + Tailwind UI/UX 规范 |
docs/DESIGN_WORKSPACE_GUIDE.md |
产品与业务人员 | Design 模式产品功能与业务逻辑分析指南 |
.cursor/rules/base.mdc |
Cursor Agent | 精简指针（alwaysApply）→ CLAUDE.md |
.github/copilot-instructions.md |
GitHub Copilot | 精简指针 → CLAUDE.md |
docs/document-governance.md |
架构评审 | 五层架构、权威真相、文档生命周期 |
docs/agents/issue-tracker.md |
Agent skills | 问题追踪器配置（GitHub） |
docs/agents/triage-labels.md |
Agent skills | 标签词表映射 |
docs/agents/domain.md |
Agent skills | 领域文档消费规则 |
docs/ARCHITECTURE.md |
架构评审 | 系统设计详述（叙事 + ADR） |
For Claude Code users: see CLAUDE.md.
For Cursor Agent users: .cursor/rules/base.mdc applies automatically; canonical rules remain in CLAUDE.md.
For GitHub Copilot users: see .github/copilot-instructions.md.
For frontend UI work: see docs/UI_UX_GUIDELINES.md.
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.
- 3d ago First seen · 53 lines · 1,585 tokens per session scan B c6ac7b8bb942
Clutch AGENTS.md is an instructions file published in the GitHub repository fancy1108/Clutch (87 stars, last pushed 5d ago), licensed MIT. It adds 1,585 tokens to every session, about $0.0079 per session on Opus 5. A static security scan graded it B with 2 findings (sends data to an external url, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other instructions, from other repositories
DeepSeek-Harness-Desktop AGENTS.md
Instructions for web-casa/DeepSeek-Harness-Desktop, covering agents.md — dsh desktop, 项目本质, 不可违背的安全不变量, 版本单一事实源（改动版本时必须同时改全部） and harness 升级启动契约（bump pin 前必读）.
speech-studio AGENTS.md
Instructions for soniqo/speech-studio, covering agent instructions, project, stack, sibling repos under /repos/ and build.
bili-music AGENTS.md
Instructions for Jmiao11/bili-music: 技术栈:Tauri(Rust 后端 + 网页前端);取音频以免登录游客直链为主、yt-dlp 兜底;目标打包成单个 exe.
silent-Tiangong CLAUDE.md
Instructions for silent-rs/silent-Tiangong, covering claude.md, 项目概述, 常用开发命令, 构建 and 检查（快速验证）.
clawsuite AGENTS.md
Instructions for outsourc-e/clawsuite, covering clawsuite agent roster, how aurora uses this file, routing table, aurora-coder — frontend specialist and aurora-daemon — backend specialist.
Hermes-CN-Desktop AGENTS.md
AGENTS.md instructions for Eynzof/Hermes-CN-Desktop, covering codex 工作指引, 项目概述, 项目结构, 后端事实来源 and 后端版本同步.