Borrowing it
Nothing to install: this file belongs to aeroxy/ast-bro. 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/aeroxy/ast-bro/main/AGENTS.mdgit clone --depth 1 https://github.com/aeroxy/ast-broWrote 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/aeroxy/ast-bro/agents-md)<a href="https://agentmods.dev/instructions/aeroxy/ast-bro/agents-md"><img src="https://agentmods.dev/badge/instructions/aeroxy/ast-bro/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/aeroxy/ast-bro/agents-md"><img src="https://agentmods.dev/badge/instructions/aeroxy/ast-bro/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 | $0.00352 | $0.00352 |
| Opus 5.5 | $0.00141 | $0.00141 |
| Sonnet 5.5 | $0.00070 | $0.00070 |
| Haiku 4.5 | $0.00035 | $0.00035 |
Grade A, and why
ast-bro 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 1mo 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
Preparing Release
- Bump the version:
make bump-patch(orbump-minor/bump-major) - Build and zip the release binary:
make release - Update
Formula/ast-bro.rbwith the new SHA256:make update-formula
WIKI
@wiki/architecture.md
The architecture page links to eight deeper wiki files — read them on-demand when your work touches that subsystem:
- wiki/deps.md — dependency-graph internals (deps / reverse-deps / cycles / graph)
- wiki/calls.md — call-graph internals (callers / callees / trace, three-pass resolver, unified graph cache, per-language extraction)
- wiki/impact.md — cross-file impact analysis (
impact): combines callers + callees + file deps + test detection in one command - wiki/context.md — token-budgeted context (
context): greedy knapsack over call graph for LLM-friendly context packs - wiki/search.md — semantic search internals (BM25 + dense, chunking, on-disk format)
- wiki/squeeze.md — log/text token compression (squeeze): multi-stage pipeline, reversible legend, degenerate fallback
- wiki/network-security.md — model download, TLS policy, mirror fallback
- wiki/file-filtering.md — what gets walked, ignore layers, escape hatches, shebang detection, test-file heuristics
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.
- 1mo ago First seen · 21 lines · 352 tokens per session scan A 55d199ecdf72
ast-bro AGENTS.md is an instructions file published in the GitHub repository aeroxy/ast-bro (232 stars, last pushed 19d ago), licensed MIT. It adds 352 tokens to every session, about $0.0014 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 2026-08-30.
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.
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).
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.