Fabro is an open-source system for defining software-development workflows as graphs that AI coding agents execute with verification steps and opportunities for human intervention. Expert engineers and teams use it to coordinate agent tasks, combine models, share version-controlled processes, run agents in isolated sandboxes, and queue work through an API server. The catalogue entries are Fabro-specific skills, instructions, hooks, and settings for working with the system.
Borrowing it
Nothing to install: this file belongs to fabro-sh/fabro. 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/fabro-sh/fabro/main/AGENTS.mdgit clone --depth 1 https://github.com/fabro-sh/fabroWrote 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/fabro-sh/fabro/agents-md)<a href="https://agentmods.dev/instructions/fabro-sh/fabro/agents-md"><img src="https://agentmods.dev/badge/instructions/fabro-sh/fabro/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/fabro-sh/fabro/agents-md"><img src="https://agentmods.dev/badge/instructions/fabro-sh/fabro/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 | $0.07248 | $0.07248 |
| Opus 5.5 | $0.02899 | $0.02899 |
| Sonnet 5.5 | $0.01450 | $0.01450 |
| Haiku 4.5 | $0.00725 | $0.00725 |
Grade A, and why
fabro 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.
How it starts
The opening of the file, as written. The whole thing — 331 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
Build and test commands
Rust
cargo build --workspace— build all cratescargo nextest run --workspace— run all unit testscargo nextest run -p fabro-server— test a single cratecargo nextest run -p fabro-workflow -- test_name— run a single testset -a && source .env && set +a && cargo nextest run --workspace --profile e2e --run-ignored only— run all E2E live tests (requires credentials in.env, see.env.example)set -a && source .env && set +a && cargo nextest run -p fabro-llm --profile e2e --run-ignored only— run E2E tests for a single cratecargo +nightly-2026-04-14 fmt --check --all— check formatting (pinned nightly required for rustfmt config; CI uses the same date)cargo +nightly-2026-04-14 fmt --all— auto-formatcargo +nightly-2026-04-14 clippy --workspace --all-targets -- -D warnings— lint (CI runs nightly clippy to match; install withrustup toolchain install nightly-2026-04-14 --profile minimal --component clippy,rustfmt)
macOS note: if cargo nextest run fails with Too many open files (os error 24) / EMFILE, raise the shell's soft FD limit before running tests, for example ulimit -n 4096 && cargo nextest run --workspace. Some terminals and inherited agent sessions start with ulimit -n 256, which is too low for the shared CLI test daemon under parallel nextest load.
TypeScript (fabro-web)
cd apps/fabro-web && bun run dev— rebuild web assets on change for the Rust server; refresh the browser manuallycd apps/fabro-web && bun test— run testscd apps/fabro-web && bun run typecheck— type checkcd apps/fabro-web && bun run build— production build (writes toapps/fabro-web/dist/only; does NOT update the bundled SPA that ships in the Rust binary)cargo dev build [-- <cargo args>]— refreshes the embedded SPA assets from the production build, verifies SPA asset budgets, and then runscargo buildwith forwarded args. The embedded assets are gitignored except for.gitkeep; use this when building a Rust binary that should include a populated SPA bundle.bun run devfor local development is unchanged because debug builds preferapps/fabro-web/dist/on disk via the server fallback.
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 Changed · +26 lines · +412 tokens per session c71d04f11fec
- 1mo ago Changed · +4 tokens per session 9a991f141b71
- 1mo ago Changed · -2 lines · -265 tokens per session 4a56724fd08f
- 1mo ago Changed · +106 lines · +2,590 tokens per session bdab1f0b214d
- 1mo ago Changed · -1 lines · +74 tokens per session ced2fec32565
- 1mo ago Changed · +2 lines · +95 tokens per session dfa70108b46a
- 2mo ago First seen · 200 lines · 4,338 tokens per session scan A 7fb941a21b75
fabro AGENTS.md is an instructions file published in the GitHub repository fabro-sh/fabro (1,812 stars, last pushed yesterday), licensed MIT. It adds 7,248 tokens to every session, about $0.0290 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.
fabro AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| fabro AGENTS.mdfabro-sh/fabro | Instructions file | 1.8k | yesterday | MIT | A | 7,248 | Codex, OpenCode |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | today | MIT | A | 7,461 | Codex, OpenCode |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | yesterday | MIT | A | 4,680 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 5,516 | GitHub Copilot |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 3,093 | GitHub Copilot |
| deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness | Instructions file | 274k | 2d ago | MIT | A | 4,313 | Codex, OpenCode |