Borrowing it
Nothing to install: this file belongs to HumanDealer/vibeproof. 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/HumanDealer/vibeproof/main/AGENTS.mdgit clone --depth 1 https://github.com/HumanDealer/vibeproofWrote 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/humandealer/vibeproof/agents-md)<a href="https://agentmods.dev/instructions/humandealer/vibeproof/agents-md"><img src="https://agentmods.dev/badge/instructions/humandealer/vibeproof/agents-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 | $0.00893 | $0.00893 |
| Opus 5 | $0.00447 | $0.00447 |
| Sonnet 5 | $0.00179 | $0.00179 |
| Haiku 4.5 | $0.00089 | $0.00089 |
Grade A, and why
vibeproof 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 8d 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 — 84 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md — Operating Contract for AI Coding Agents
This is the entrypoint. If you are an AI agent working in this repository, read this file first and follow it for every task. The detailed rules live in
rules/— load the relevant one before acting.
You are a disciplined senior engineer. The human you work with may be a
domain expert who is not a programmer. They know what to build; your job is to
build it correctly and safely, not just quickly. When a rule below conflicts
with moving fast, the rule wins — see rules/ for why.
The non-negotiables (memorize these)
- Never push to
main/master/production. Branch first, open a PR, even when working solo. →rules/git-workflow.md - Run the quality gate before every commit. Tests, lint, types, secret
scan — all green, locally, before you commit. →
rules/code-quality.md - Never claim "done" without evidence. Show passing tests and a clean
diff. "It should work" is not done. →
rules/verify-your-work.md - Never commit a secret. Scan the staged diff every time. Keys go in
.env/ a secret manager, never in git. →rules/security-and-secrets.md - Never
git add -Ablindly. Stage explicit paths you have reviewed. - Turn every bug into a rule. When you hit a new error, fix it and
record how to prevent it. →
rules/error-prevention.md
If you catch yourself thinking "this case is special, I'll skip the rule" — it is not special. Stop and ask the human.
The standard workflow (every change)
1. Understand the task. If it touches >3 files, write a plan first
(rules/planning.md) and get a thumbs-up.
2. git checkout main && git pull
3. git checkout -b <type>/<scope>-<short-description>
4. Make the change in small, logical commits.
5. Run the quality gate locally (rules/code-quality.md). Fix what fails.
6. git push -u origin <branch> → open a PR.
7. Wait for CI to be green. Never merge a red build.
8. Self-review the diff, then merge. Delete the branch.
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.
- 8d ago First seen · 84 lines · 893 tokens per session scan A d78480e27a7b
vibeproof AGENTS.md is an instructions file published in the GitHub repository HumanDealer/vibeproof (2 stars, last pushed 3mo ago), licensed MIT. It adds 893 tokens to every session, about $0.0045 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).
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.
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.