Borrowing it
Nothing to install: this file belongs to mehdiforoozandeh/crux. 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/mehdiforoozandeh/crux/main/AGENTS.mdgit clone --depth 1 https://github.com/mehdiforoozandeh/cruxWrote 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/mehdiforoozandeh/crux/agents-md)<a href="https://agentmods.dev/instructions/mehdiforoozandeh/crux/agents-md"><img src="https://agentmods.dev/badge/instructions/mehdiforoozandeh/crux/agents-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/mehdiforoozandeh/crux/agents-md"><img src="https://agentmods.dev/badge/instructions/mehdiforoozandeh/crux/agents-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 | $0.00586 | $0.00586 |
| Opus 5 | $0.00293 | $0.00293 |
| Sonnet 5 | $0.00117 | $0.00117 |
| Haiku 4.5 | $0.00059 | $0.00059 |
Grade A, and why
crux AGENTS.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 10d 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.
What it actually says
AGENTS.md — repo orientation for coding agents
crux is four agent skills under skills/ — crux, crux-wiki, crux-cockpit,
evolve-crux — plus a stdlib-only Python engine at skills/crux/scaffold/ (engine.py,
crux.py, render.py, serve.py, webui/). The root ./crux wrapper forwards
to the engine: ./crux --help for the verb tour, ./crux selftest to validate a checkout.
Contributing? The full workflow (ideate → build → validate → ship) is the
skills/evolve-crux/SKILL.md playbook; follow it.
Hard rules, gated before every PR:
./crux selftestfully green, and a behavior change adds asserts first (tests-first — the failing assert is the reproduction).- Stdlib only. The engine takes no third-party dependency; the webui is no-build vanilla JS.
- Existing vaults still load. A vault-format or verdict/roll-up/view-logic change
needs an
ENGINE_VERSIONbump inengine.pyplus migration proof. - The cockpit (
crux serve) is read-only — no route ever writes. - Never hand-edit generated files (
META.md,EXPERIMENTS.md,WIKI.md, ledger blocks) — regenerate via the engine. skills/crux/SKILL.mdstays under 34,000 bytes (wc -c skills/crux/SKILL.md). It loads on every crux session, and it grew 42% in five commits before anyone was counting. New material earns its place inline by one test: if the agent never reads it, does it do the wrong thing — or does it visibly fail? Content the engine itself refuses or validates may live inreferences/orscaffold/README.mdbehind a pointer, because the refusal is what sends the agent to go read it. Content only the agent can enforce — the leash, the voice rules, the migration guardrail, "never writeglossary.mddirectly" — must be inline, however rare the path, because a missed read there is silent. Two riders: a prohibition stays inline even when its procedure moves out, and rare content whose trigger the agent would not notice needs a one-line tripwire left behind pointing at the reference. Repetition of a prohibition at each point of temptation is load-bearing, not bloat — do not dedupe 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.
- 10d ago First seen · 34 lines · 586 tokens per session scan A 80d51ea06b8c
crux AGENTS.md is an instructions file published in the GitHub repository mehdiforoozandeh/crux (5 stars, last pushed 4d ago), licensed MIT. It adds 586 tokens to every session, about $0.0029 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
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.
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).
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.
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).
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.