Borrowing it
Nothing to install: this file belongs to minipuft/claude-prompts-mcp. 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/minipuft/claude-prompts-mcp/main/AGENTS.mdgit clone --depth 1 https://github.com/minipuft/claude-prompts-mcpWrote 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/minipuft/claude-prompts-mcp/agents-md)<a href="https://agentmods.dev/instructions/minipuft/claude-prompts-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/minipuft/claude-prompts-mcp/agents-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/minipuft/claude-prompts-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/minipuft/claude-prompts-mcp/agents-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 | $0.04757 | $0.04757 |
| Opus 5.5 | $0.01903 | $0.01903 |
| Sonnet 5.5 | $0.00951 | $0.00951 |
| Haiku 4.5 | $0.00476 | $0.00476 |
Grade A, and why
claude-prompts-mcp 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 yesterday.
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 — 186 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Rules · Claude Prompts MCP
Canonical ownership and loading
- Edit
CLAUDE.mdand.claude/rules/*.md; do not edit this generated file. - This compact file is the default Codex/OpenCode context. It preserves the project-wide decisions that change most tasks while staying within Codex's documented default 32 KiB project guidance budget.
- Claude Code applies rule
paths:natively. Codex and OpenCode do not, so use the dispatch table below: when a task touches a matching path, read that canonical rule before editing. - For project details not projected here, consult
CLAUDE.mdand its documentation pointers.
Core Principles
- MCP Tooling Only -- Prompts, templates, chains flow through MCP tools. Manual edits under
server/prompts/**forbidden. - Contract ownership -- Hand-written schemas in
src/mcp/tools/schemas/own runtime validation;tooling/contracts/*.jsonown descriptions/parameter metadata generated intosrc/mcp/contracts/schemas/_generated/. Runnpm run generate:contracts, never edit_generated/.config.schema.json<-ConfigFile(generate:config-schema). - Transport Parity -- Runtime changes must work in STDIO and Streamable HTTP. The two differ in instance lifetime, and that difference is load-bearing: STDIO pins one
McpServerper connection, while HTTP builds a fresh one per request. A change that mutates a registered instance passes STDIO and silently no-ops over HTTP. HTTP+SSE was removed in the SDK v2 upgrade. - Docs/Code Lockstep -- Update relevant doc in
docs/when behavior changes. - Validation Discipline -- CI owns the full test suite; local checks are a subset chosen by who is running them. A change's own check (the test, validator or probe that reads what the change wrote) runs with the change, and nothing wider. Before a push:
npm run typecheck && npm run lint:ratchet && npm run typecheck:tests:ratchet && npm run validate:all.test:all(unit, integration and e2e) runs once, in CI, at the pull request; a red run is fixed on the branch, never merged around. Runtest:alllocally only to reproduce a CI failure or when no pull request will carry the change.typecheck:tests:ratchetis not optional:tsconfig.jsonexcludestests/, sotypecheckis blind to every call site a signature change breaks.test:ciis an alias fortest:unitand says nothing about the integration or e2e jobs. Owner ruling 2026-10-05, after a profile measured the full suite running three times in series per change while CI was green on 32 of 33 pull requests. (flips when a defect reachesmainthat a localtest:allwould have caught and the pull request's CI did not)
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.
- yesterday Changed · -10 lines · -1,575 tokens per session 7ce8fbcc5996
- 17d ago Changed · +13 lines · +239 tokens per session 8255fbed410d
- 1mo ago Changed · +5 lines · +119 tokens per session c688939a3e1f
- 1mo ago Changed · +216 tokens per session e0bb68584842
- 1mo ago Changed · +1 lines · +53 tokens per session a7f6c4dfb606
- 1mo ago Changed · -42 lines · -795 tokens per session 7c9db298fae9
- 1mo ago Changed · +3 tokens per session 8ae5e8b4a01e
- 1mo ago Changed · +17 tokens per session 5d3aa31aa159
- 1mo ago Changed · +6 lines · +385 tokens per session efdb5bf5d75b
- 1mo ago First seen · 213 lines · 6,095 tokens per session scan A 5c00b52b53be
claude-prompts-mcp AGENTS.md is an instructions file published in the GitHub repository minipuft/claude-prompts-mcp (192 stars, last pushed yesterday), licensed MIT. It adds 4,757 tokens to every session, about $0.0190 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 2026-08-30.
claude-prompts-mcp AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| claude-prompts-mcp AGENTS.mdminipuft/claude-prompts-mcp | Instructions file | 192 | yesterday | MIT | A | 4,757 | Claude Code, Codex, OpenCode |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | yesterday | MIT | A | 7,461 | Codex, OpenCode |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | yesterday | MIT | A | 4,680 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 5,516 | GitHub Copilot |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 3,093 | GitHub Copilot |
| deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness | Instructions file | 274k | 2d ago | MIT | A | 4,313 | Codex, OpenCode |