Borrowing it
Nothing to install: this file belongs to node9-ai/node9-proxy. 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/node9-ai/node9-proxy/main/CLAUDE.mdgit clone --depth 1 https://github.com/node9-ai/node9-proxyWrote 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/node9-ai/node9-proxy/claude-md)<a href="https://agentmods.dev/instructions/node9-ai/node9-proxy/claude-md"><img src="https://agentmods.dev/badge/instructions/node9-ai/node9-proxy/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/node9-ai/node9-proxy/claude-md"><img src="https://agentmods.dev/badge/instructions/node9-ai/node9-proxy/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 | $0.00858 | $0.00858 |
| Opus 5.5 | $0.00343 | $0.00343 |
| Sonnet 5.5 | $0.00172 | $0.00172 |
| Haiku 4.5 | $0.00086 | $0.00086 |
Grade A, and why
node9-proxy 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 1mo 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.
Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
Use `spawnSync` against `dist/cli.js` (see `src/__tests__/check.integration.test.ts` for the pattern). How it starts
The opening of the file, as written. The whole thing — 61 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Node9 Proxy — Claude Code Rules
PR Checklist (required before every commit)
Before committing or opening a PR, verify all of the following:
- New behavior has a test that fails without the change
-
npm testpasses (455+ tests) -
npm run typecheckpasses -
npm run lintpasses (catchesrequire()imports, unused vars, etc.) -
npm run format:checkpasses (runnpm run formatto fix) - No
console.login hook or proxy code paths — useconsole.error(stdout must stay clean for JSON-RPC / MCP) - Review your own diff before committing — run
git diffand check for logical correctness issues that automated checks miss: missingreturnafterres.end(), silentcatch {}blocks swallowing errors, double event-listener registration, fall-through in route handlers
Test Rules
Every bug fix must ship with a regression test. Write the failing test first, then fix the code. This proves you understood the bug and prevents silent regressions.
Integration tests are required for:
- Any command that runs as a subprocess (
check,log, proxy) - Anything that touches stdout/stderr (protocol correctness)
- Any file write (
audit.log,hook-debug.log, snapshot) - Any behavior that depends on
cwdorHOME
Use spawnSync against dist/cli.js (see src/__tests__/check.integration.test.ts for the pattern).
Always assert result.error and result.status — a silent spawn failure must not pass tests.
Unit tests with mocked fs/getConfig are not sufficient for hook commands or the proxy.
They cannot catch protocol bugs, filesystem path bugs, or exit code bugs.
Code Rules
Audit writes must happen before config loads.
In hook commands, fs.appendFileSync(auditLog, ...) must come before any getConfig() call. A config failure must never silently skip the audit entry.
Validate external path inputs before filesystem use.
Any cwd, file_path, or similar value from hook payloads must be validated (path.isAbsolute()) before being passed to getConfig(), path.join(), or fs calls. Use payload.cwd || undefined for empty-string guard, then path.isAbsolute() for traversal guard.
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.
- 1mo ago First seen · 61 lines · 858 tokens per session scan A 711a41fe6267
node9-proxy CLAUDE.md is an instructions file published in the GitHub repository node9-ai/node9-proxy (221 stars, last pushed 2d ago), licensed Apache-2.0. It adds 858 tokens to every session, about $0.0034 per session on Opus 5.5. A static security scan graded it A with 1 finding (runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other instructions, from other repositories
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
vscode model-prompts.instructions.md
Model-specific prompt authoring and registry guidelines.