Borrowing it
Nothing to install: this file belongs to FlorianBruniaux/ctxharness. 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/FlorianBruniaux/ctxharness/main/CLAUDE.mdgit clone --depth 1 https://github.com/FlorianBruniaux/ctxharnessWrote 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/florianbruniaux/ctxharness/claude-md)<a href="https://agentmods.dev/instructions/florianbruniaux/ctxharness/claude-md"><img src="https://agentmods.dev/badge/instructions/florianbruniaux/ctxharness/claude-md.svg" alt="Measured on agentmods" 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 | $0.01228 | $0.01228 |
| Opus 5 | $0.00614 | $0.00614 |
| Sonnet 5 | $0.00246 | $0.00246 |
| Haiku 4.5 | $0.00123 | $0.00123 |
Grade A, and why
ctxharness 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 7d 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 — 115 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ctxharness — AI Agent Instructions
Framework for detecting AI documentation drift (L1/L2/L3 context engineering testing).
Repository structure
packages/
├── core/ @florianbruniaux/ctxharness-core — lib (extractors, scanners, runner, reporter)
└── cli/ ctxharness — CLI binary (commander)
action.yml GitHub Action wrapper
templates/ Husky hooks + CI workflow templates
Commands
pnpm build # compile all packages
pnpm test # vitest (164 tests)
pnpm test:watch # watch mode
pnpm lint # tsc --noEmit
pnpm fmt # prettier --write
Key files
| File | Purpose |
|---|---|
packages/core/src/config.ts |
Zod schema — .ctxharness.yml format |
packages/core/src/extractors/index.ts |
20 extractors (ground truth from code) |
packages/core/src/scanners/index.ts |
15 scanners (find mentions in docs) |
packages/core/src/runner.ts |
Orchestrates run, returns RunResult |
packages/core/src/reporter.ts |
text / json / gha output formats |
packages/core/src/trend.ts |
Trend history — appendTrendRecord, loadTrendHistory, summarizeTrend |
packages/core/src/snapshot.ts |
Snapshot save / load / diff for trend tracking |
packages/core/src/populate.ts |
populateFromConfig + assertionsToYaml — claim→Assertion mapping |
packages/core/src/plugin.ts |
Plugin API — register custom extractors/scanners |
packages/cli/src/index.ts |
CLI entry point (run / check / scan / score / fix / doctor / init / snapshot / diff / trend / populate) |
packages/core/src/__tests__/fixtures/ |
Test fixture files |
Architecture rules
- TypeScript strict + ESM only (
"type": "module") - All internal imports use
.jsextension (NodeNext resolution) - No
any— useunknown+ type guards noUncheckedIndexedAccesson — always null-check array access- Extractors return
string(ground truth value) - Scanners return
ScanResult[](one per mention found) - New extractor or scanner: add to the union in
config.ts+ registry in the module
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.
- 7d ago First seen · 115 lines · 1,228 tokens per session scan A 4beb433d33ed
ctxharness CLAUDE.md is an instructions file published in the GitHub repository FlorianBruniaux/ctxharness (21 stars, last pushed 5d ago), licensed MIT. It adds 1,228 tokens to every session, about $0.0061 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 2026-08-30.
Other instructions, from other repositories
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.
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.
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).
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.