Borrowing it
Nothing to install: this file belongs to granoflow/granoflow-mcp-server. 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/granoflow/granoflow-mcp-server/develop/AGENTS.mdgit clone --depth 1 https://github.com/granoflow/granoflow-mcp-serverWrote 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/granoflow/granoflow-mcp-server/agents-md)<a href="https://agentmods.dev/instructions/granoflow/granoflow-mcp-server/agents-md"><img src="https://agentmods.dev/badge/instructions/granoflow/granoflow-mcp-server/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/granoflow/granoflow-mcp-server/agents-md"><img src="https://agentmods.dev/badge/instructions/granoflow/granoflow-mcp-server/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 | $0.00435 | $0.00435 |
| Opus 5.5 | $0.00174 | $0.00174 |
| Sonnet 5.5 | $0.00087 | $0.00087 |
| Haiku 4.5 | $0.00044 | $0.00044 |
Grade A, and why
granoflow-mcp-server 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 2mo 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
Project Role
This repository is the public Granoflow MCP server. It exposes Granoflow's Local HTTP API to AI agents.
Hard Rules
- Keep the MCP server thin. Do not reimplement Granoflow business logic here.
- Call the Granoflow Local HTTP API directly. Do not add an execution dependency on external command-line wrappers.
- Do not print API tokens or secrets in logs, tool results, test snapshots, or documentation.
- For npm publish 2FA, check repo-local private
.npm*.txtfiles before asking the user for an OTP. Read codes only into shell-local variables, never print them, and never include them in docs, commits, screenshots, logs, or chat. - Keep tool results structured and predictable for Cursor, Codex, Claude Code, and OpenCode/OpenClaw-compatible MCP clients.
- Do not add direct SQLite, Drift, app build, app run, screenshot, or release orchestration logic.
Skill Testing
Follow popular Agent Skills practice (structure + script tests; behavior via evals):
- Allowed in CI:
SKILL.mdfrontmatter structure (tests/skills-structure.test.ts); realskills/*/scriptstests undertests/python/; MCP skill tools assertingok/path/ non-empty body / reference ids only. - Forbidden: reading
skills/**/SKILL.mdorreferences/**and locking prose, gate copy, or activation phrases withtoContain/toMatch. That is not conventional skill testing and must not be reintroduced. - Behavior: validate agent compliance with LLM evals when needed. This repository does not require an eval harness in CI today — do not replace evals with markdown snapshot locks.
See .cursor/rules/skill-testing.mdc.
Quality Gate
Run before handoff after code changes:
npm run check
The gate includes Prettier, ESLint, TypeScript, Vitest, and Python skill-script checks.
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.
- 2mo ago First seen · 42 lines · 435 tokens per session scan A 1893c98599ee
granoflow-mcp-server AGENTS.md is an instructions file published in the GitHub repository granoflow/granoflow-mcp-server (0 stars, last pushed yesterday), licensed MIT. It adds 435 tokens to every session, about $0.0017 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 2026-08-31.
granoflow-mcp-server AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| granoflow-mcp-server AGENTS.mdgranoflow/granoflow-mcp-server | Instructions file | 0 | yesterday | MIT | A | 435 | 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 |