Borrowing it
Nothing to install: this file belongs to NO-Product/knowledgebase-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/NO-Product/knowledgebase-mcp/main/AGENTS.mdgit clone --depth 1 https://github.com/NO-Product/knowledgebase-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/no-product/knowledgebase-mcp/agents-md)<a href="https://agentmods.dev/instructions/no-product/knowledgebase-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/no-product/knowledgebase-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/no-product/knowledgebase-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/no-product/knowledgebase-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 | $0.00283 | $0.00283 |
| Opus 5.5 | $0.00113 | $0.00113 |
| Sonnet 5.5 | $0.00057 | $0.00057 |
| Haiku 4.5 | $0.00028 | $0.00028 |
Grade A, and why
knowledgebase-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 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
Agent Instructions
This repository is a public-ready MCP knowledgebase engine. Keep changes generic, configurable, and safe for open-source use.
Priorities
- Preserve the zero-database default path.
- Keep content in
content/user-owned and portable. - Keep private/provider-backed features optional.
- Use clear names for surfaces, content sources, search, skills, and integrations.
- Prefer small, explicit modules over hidden framework magic.
- Add tests around safety boundaries: auth, path traversal, schema validation, surface registration, search, skills, and provider scope guards.
- Preserve MCP protocol integrity. For stdio servers, stdout is reserved for JSON-RPC protocol messages only; diagnostics must go to stderr through the shared logger.
Do Not Add
- Personal project content.
- Private deployment domains.
- Secret manager assumptions.
- Required paid providers for the default path.
- Raw provider resource ids in MCP tool input.
console.logorprocess.stdout.writein MCP runtime code. Use the shared logger or an MCP protocol response/notification.- Query-string secrets as the normal production auth path.
?api_key=is an opt-in compatibility fallback only.
Verification
Run these before considering a change complete:
pnpm test
pnpm typecheck
pnpm lint
pnpm validate
pnpm build
Run heavy commands sequentially.
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 · 38 lines · 283 tokens per session scan A adb7fc15caa4
knowledgebase-mcp AGENTS.md is an instructions file published in the GitHub repository NO-Product/knowledgebase-mcp (0 stars, last pushed 4mo ago), licensed MIT. It adds 283 tokens to every session, about $0.0011 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.
knowledgebase-mcp AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| knowledgebase-mcp AGENTS.mdNO-Product/knowledgebase-mcp | Instructions file | 0 | 4mo ago | MIT | A | 283 | 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 |