Borrowing it
Nothing to install: this file belongs to hamc/blastproof. 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/hamc/blastproof/main/AGENTS.mdgit clone --depth 1 https://github.com/hamc/blastproofWrote 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/hamc/blastproof/agents-md)<a href="https://agentmods.dev/instructions/hamc/blastproof/agents-md"><img src="https://agentmods.dev/badge/instructions/hamc/blastproof/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/hamc/blastproof/agents-md"><img src="https://agentmods.dev/badge/instructions/hamc/blastproof/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 | $0.06286 | $0.06286 |
| Opus 5.5 | $0.02514 | $0.02514 |
| Sonnet 5.5 | $0.01257 | $0.01257 |
| Haiku 4.5 | $0.00629 | $0.00629 |
Grade A, and why
blastproof 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 today.
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 — 168 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md — blastproof
Central context for AI agents and contributors. Read this before touching code.
Mission
blastproof is an open-source AI testing agent for pull requests. Given a code diff, it maps the blast radius, generates plain-English E2E tests, executes them on a real browser through an agentic self-healing loop, and reports a score that can gate merges. 100% local, BYOK (bring your own LLM key). MIT licensed.
Pipeline: git diff → impact mapping → test generation → agentic execution → report + score
Capabilities and scope
| Capability | blastproof MVP |
|---|---|
| PR diff analysis | ✅ blastproof run --impacted --base main, blastproof plan --base main |
| Blast radius mapping | ✅ deterministic (config routes: globs). Catches unclassified files, not misclassified ones — import-graph impact is the open gap |
| Plain-English YAML tests | ✅ .blastproof/tests/*.yaml (summary, steps, priority, tags, routes) — handwritten or generated by plan |
| Scriptless agentic execution | ✅ own loop: Playwright ariaSnapshot() + LLM structured output |
| Self-healing (no static selectors) | ✅ elements re-read from a fresh snapshot every step, acted on by the ref that snapshot gave them |
| Score with merge threshold | ✅ priority-weighted (P0=3, P1=2, P2=1), --min-score gate |
| JUnit/HTML reports | ✅ JUnit XML and a self-contained HTML report with embedded screenshots |
| CI integration | ✅ published to npm and a composite GitHub Action; PR comments still post-MVP |
| Authentication | ✅ sign in once per run — login journey, captured session, or static headers/cookies |
| Unclassified-change gate | ✅ ignore: globs + --fail-on-unmapped for files whose blast radius nobody declared |
| Run budget & deadline | ✅ optional budget: (calls/tokens/duration) + matching flags; exhaustion stops the run as incomplete, never as a failed test — exits 1 regardless of --min-score |
| SaaS backend, credits, dashboards | ❌ never — local-first BYOK |
| VS Code extension, Flutter, session replay | ❌ post-MVP |
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.
- today Changed · -20 tokens per session 51c50c178d12
- yesterday First seen · 168 lines · 6,306 tokens per session scan A f618f5233e83
blastproof AGENTS.md is an instructions file published in the GitHub repository hamc/blastproof (10 stars, last pushed today), licensed MIT. It adds 6,286 tokens to every session, about $0.0251 per session on Opus 5.5. 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 2026-10-14.
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.
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.
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).