Borrowing it
Nothing to install: this file belongs to qelos-io/better-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/qelos-io/better-mcp/main/CLAUDE.mdgit clone --depth 1 https://github.com/qelos-io/better-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/qelos-io/better-mcp/claude-md)<a href="https://agentmods.dev/instructions/qelos-io/better-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/qelos-io/better-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/qelos-io/better-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/qelos-io/better-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 | $0.00821 | $0.00821 |
| Opus 5.5 | $0.00328 | $0.00328 |
| Sonnet 5.5 | $0.00164 | $0.00164 |
| Haiku 4.5 | $0.00082 | $0.00082 |
Grade A, and why
better-mcp CLAUDE.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 17d 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.
How it starts
The opening of the file, as written. The whole thing — 86 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
Project-specific guidance for Claude Code working in this repo.
Testing
Always add unit tests for new behavior. Any time you add a new function, exported helper, or non-trivial code path, ship a test for it in the same PR. Pure wiring (one-line pass-throughs that TypeScript already validates) is the only exception — and even then prefer extracting a small testable helper.
If something is hard to test, that's a signal to refactor — extract the pure
core (like buildListedTools in src/services/proxy.service.ts) so the test
can call it directly without spinning up an MCP server, Express app, or child
process.
Test convention
Tests live next to the source they cover, in a tests/ subfolder:
src/lib/slim.ts → src/lib/tests/slim.test.ts
src/middleware/compact.middleware.ts → src/middleware/tests/compact.middleware.test.ts
src/services/proxy.service.ts → src/services/tests/proxy.service.test.ts
One .test.ts file per source file. When you add a new source file, create
its tests/ sibling and write the test there. Tests are TypeScript, run
directly from src/ via Node's built-in test runner + tsx loader — no
compile step needed for tests.
Pattern to follow (see src/lib/tests/slim.test.ts):
import { test } from "node:test";
import assert from "node:assert/strict";
import { thing } from "../thing.js"; // .js extension is the project import convention
test("describes the behavior", () => {
assert.equal(thing(1), 2);
});
test("async case", async () => {
assert.equal(await thing.async(1), 2);
});
Running tests
npm test # node --import tsx --test 'src/**/*.test.ts'
npm run test:build # build first, then test (catches type errors too)
The test script globs every *.test.ts under src/; you don't need to
register individual test files anywhere. Tests are excluded from tsc build
(see tsconfig.json exclude), so they never land in dist/ and never ship
in the npm package.
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.
- 17d ago Changed · +9 lines · +132 tokens per session 49620334fac0
- 2mo ago First seen · 77 lines · 689 tokens per session scan A 329c1dd93845
better-mcp CLAUDE.md is an instructions file published in the GitHub repository qelos-io/better-mcp (3 stars, last pushed 11d ago), licensed MIT. It adds 821 tokens to every session, about $0.0033 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.
better-mcp CLAUDE.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| better-mcp CLAUDE.mdqelos-io/better-mcp | Instructions file | 3 | 11d ago | MIT | A | 821 | Claude Code |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 144k | today | MIT | A | 7,461 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 5,685 | GitHub Copilot |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | today | MIT | A | 4,680 | Codex, OpenCode |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 3,086 | GitHub Copilot |
| deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness | Instructions file | 281k | today | MIT | A | 4,335 | Codex, OpenCode |