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/acoyfellow/mcpu/agents-mdgit clone --depth 1 https://github.com/acoyfellow/mcpuWhat 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 | $0.00082 | $0.00082 |
| Opus 5 | $0.00041 | $0.00041 |
| Sonnet 5 | $0.00016 | $0.00016 |
| Haiku 4.5 | $0.00008 | $0.00008 |
Grade A, and why
mcpu 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
Agent instructions
Keep mcpu tiny. Version stays 0.0.1.
Describe what this commit does. Do not add README features that have no tool and no test.
Do not give the agent bash and mcpu on the same tree.
The draft is process memory. A grant is optional. No grant means the tool runs.
GET / is a reader. Writes go through tools.
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 · 12 lines · 82 tokens per session scan A e867f610dbd8
mcpu AGENTS.md is an instructions file published in the GitHub repository acoyfellow/mcpu (8 stars, last pushed 8d ago), licensed MIT. It adds 82 tokens to every session, 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 instructions, from other repositories
agents AGENTS.md
AGENTS.md instructions for cloudflare/agents, covering agents.md, project overview, repository structure, nested agents.md files and setup.
mcp AGENTS.md
Instructions for cloudflare/mcp, covering agents.md, project overview, mcp specification compliance, repository structure and setup.
cloudflare-workers-nextjs-saas-template AGENTS.md
Instructions for LubomirGeorgiev/cloudflare-workers-nextjs-saas-template, covering project context, vinext, general coding rules, control flow and comments.
MisakaNet AGENTS.md
Instructions for Ikalus1988/MisakaNet, covering misakanet agent 规则, 🛡️ 崩溃保护（强烈推荐）, 用 fatal-guard 包装你的进程，崩溃时自动捕获墓碑, 墓碑自动转为 draft lesson and 或通过管道直连.
MisakaNet CLAUDE.md
Instructions for Ikalus1988/MisakaNet, covering misakanet failure memory, quick start, search for a failure, get a specific lesson and submit via mcp (no github needed).
uploads AGENTS.md
Instructions for buildinternet/uploads, covering uploads, layout, commands, local wrangler / agent hygiene and releasing @buildinternet/uploads (changesets).