Borrowing it
Nothing to install: this file belongs to keenableai/keenable-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/keenableai/keenable-mcp/main/CLAUDE.mdgit clone --depth 1 https://github.com/keenableai/keenable-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/keenableai/keenable-mcp/claude-md)<a href="https://agentmods.dev/instructions/keenableai/keenable-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/keenableai/keenable-mcp/claude-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/keenableai/keenable-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/keenableai/keenable-mcp/claude-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 | $0.00285 | $0.00285 |
| Opus 5.5 | $0.00114 | $0.00114 |
| Sonnet 5.5 | $0.00057 | $0.00057 |
| Haiku 4.5 | $0.00028 | $0.00028 |
Grade A, and why
keenable-mcp CLAUDE.md scanned grade A with 1 finding 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 today.
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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- **Docs reference the SDKs.** Code examples use the official SDKs, with the HTTP API (curl) shown next to them. If the docs describe something the SDK can't do, that's an SDK gap: fix it or file an issue. What it actually says
Keenable MCP
MCP server for live web search and clean-markdown page fetch over the Keenable web index. See README.md for setup and how the bridge to the hosted server works.
Public Docs and SDK
Every user-facing change ships with its docs. A change is user-facing when it alters a tool, a tool parameter or description, the server instructions, a response shape, an install or client config, or an error message.
- Docs: update keenable-external-docs in the same change set: open a docs PR alongside this one and link it in the description.
- SDK: if the change touches the API surface the SDKs wrap, also update keenable-sdk (Python, TypeScript and Go), or open an issue there when it can't land in the same change set.
- Docs reference the SDKs. Code examples use the official SDKs, with the HTTP API (curl) shown next to them. If the docs describe something the SDK can't do, that's an SDK gap: fix it or file an issue.
- If it isn't in the public docs, it doesn't exist in the product. Don't ship an undocumented user-facing feature: document it, or remove it.
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.
- today First seen · 13 lines · 285 tokens per session scan A 2a580e8f7644
keenable-mcp CLAUDE.md is an instructions file published in the GitHub repository keenableai/keenable-mcp (6 stars, last pushed yesterday), licensed MIT. It adds 285 tokens to every session, about $0.0011 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-11-06.
keenable-mcp CLAUDE.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| keenable-mcp CLAUDE.mdkeenableai/keenable-mcp | Instructions file | 6 | yesterday | MIT | A | 285 | Claude Code |
| 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 |