Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add instructions/chainstacklabs/performance-tool-client/claude-mdgit clone --depth 1 https://github.com/chainstacklabs/performance-tool-clientWhat 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 | $0.01360 | $0.01360 |
| Opus 5 | $0.00680 | $0.00680 |
| Sonnet 5 | $0.00272 | $0.00272 |
| Haiku 4.5 | $0.00136 | $0.00136 |
Grade A, and why
performance-tool-client 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 2d 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 — 50 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Repository guide for AI agents
AGENTS.md symlinks here. Edit this file.
Single-page Next.js app showing RPC provider performance. One route /, rendered force-dynamic, with ?protocol= and ?range= (24h or 7d). Data comes from the Grafana that compare-dashboard-functions feeds; this app only reads.
Checks
npm run lint and npm run build. There is no test suite, so these are the only automated checks — run both before calling work done. For interactive changes, also load the page and click through it; the build passes on plenty that is broken at runtime.
Needs GRAFANA_API_TOKEN in .env.local or every metric reads as unavailable — a local run without it exercises the render path, not the data path, so clicking through proves less than it appears to.
Deeper sweeps are a one-off, not a per-PR gate, and deliberately not devDependencies — they add ~157 packages to a 433-package tree for something run a few times a year, against a repo that keeps npm audit at zero on purpose. Reach for them with npx when doing dead-code or dependency work:
npx knip— unused files, exports and dependencies. The one that finds what grep misses, because it tells a function apart from a same-named property.npx tsc --noEmit --noUnusedLocals --noUnusedParameters— unused locals and parameters, which the committedtsconfig.jsondoes not enable.npx eslint . --max-warnings 0— fails on warnings thatnpm run lintprints but tolerates.npx madge --circular --extensions ts,tsx --ts-config tsconfig.json src/— import cycles.--ts-configis required: without it the@/alias goes unresolved and every aliased module is falsely reported as an orphan.npx depcheck— reportstailwindcss,@tailwindcss/postcssand the@types/*packages as unused. It cannot see CSS@import, a.mjsconfig, or ambient types, so treat those as noise;knipis right where the two disagree.
Constraints
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.
- 2d ago First seen · 50 lines · 1,360 tokens per session scan A 0ea87c01fb46
performance-tool-client CLAUDE.md is an instructions file published in the GitHub repository chainstacklabs/performance-tool-client (2 stars, last pushed 18d ago), licensed Apache-2.0. It adds 1,360 tokens to every session, about $0.0068 per session on Opus 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.
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).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
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 oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.