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/hyper3labs/clawdrive/agents-mdgit clone --depth 1 https://github.com/Hyper3Labs/clawdriveWhat 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 | $0.00241 | $0.00241 |
| Opus 5 | $0.00120 | $0.00120 |
| Sonnet 5 | $0.00048 | $0.00048 |
| Haiku 4.5 | $0.00024 | $0.00024 |
Grade A, and why
clawdrive AGENTS.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 2d 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.
What it actually says
AGENTS.md
ClawDrive is an agent-native local file platform.
Rules:
- Use
context/only for external references and scratch work. Do not commit it. - Keep durable decisions in tracked root docs such as
PLAN.md, not incontext/. - Prefer small, reviewable changes and preserve user-authored work.
- Treat external projects as references, not code to copy.
Develop (VS Code tasks — run both):
- Frontend task:
cd packages/web && npm run dev(Vite on :5173) - Backend task:
node packages/cli/dist/bin/clawdrive.js serve --port 7432
Vite proxies /api → localhost:7432. Open http://127.0.0.1:5173.
NASA demo: run the Backend (NASA demo) task instead of Backend.
Startup workflow:
/office-hoursbefore new features or pivots./plan-ceo-reviewafter the initial plan./plan-design-reviewbefore UI work./autoplanfor the full review pass./retroat the end of the week.
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.
- 2d ago First seen · 25 lines · 241 tokens per session scan A 394f910d507f
clawdrive AGENTS.md is an instructions file published in the GitHub repository Hyper3Labs/clawdrive (5 stars, last pushed 5mo ago), licensed MIT. It adds 241 tokens to every session, about $0.0012 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
agentrq-gemini-extension GEMINI.md
Instructions for agentrq/agentrq-gemini-extension: You are connected to the AgentRQ platform via the supervisor MCP server. You have access to manage workspaces, tasks, and communicate with human operators.
ClawRouter CLAUDE.md
Instructions for BlockRunAI/ClawRouter, covering clawrouter, commands, project structure, key dependencies and conventions.
botmux CLAUDE.md
Instructions for deepcoldy/botmux, covering botmux, 构建 & 运行, bun 开发链路, worktree 的 nodemodules：共享还是独立（改前必读） and 编译态（单文件二进制）注意.
SearChat CLAUDE.md
Claude Code instructions for yokingma/SearChat, covering claude.md, project overview, architecture, monorepo structure and key technologies.
ai AGENTS.md
AGENTS.md instructions for vercel/ai, covering agents.md, project overview, repository structure, key directories and core package dependencies.
InvestSkill GEMINI.md
Instructions for yennanliu/InvestSkill, covering investskill — gemini cli setup & usage guide, installation & setup, quick start, navigate to the investskill directory and start gemini cli (loads gemini.md automatically).