Borrowing it
Nothing to install: this file belongs to garagon/aguara. 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/garagon/aguara/main/CLAUDE.mdgit clone --depth 1 https://github.com/garagon/aguaraWrote 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/garagon/aguara/claude-md)<a href="https://agentmods.dev/instructions/garagon/aguara/claude-md"><img src="https://agentmods.dev/badge/instructions/garagon/aguara/claude-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 | $0.05264 | $0.05264 |
| Opus 5 | $0.02632 | $0.02632 |
| Sonnet 5 | $0.01053 | $0.01053 |
| Haiku 4.5 | $0.00526 | $0.00526 |
Grade A, and why
aguara CLAUDE.md scanned grade A with 1 finding 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 6d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
Distribution: install.sh (mandatory checksum verification, bounded curl + retry), Homebrew tap, Docker (GHCR, multi-arch `linux/amd64+arm64`, runs as non-root UID 10001, base images digest-pinned, signed at digest with C How it starts
The opening of the file, as written. The whole thing — 221 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.
Project Status
Aguara v0.27.0 (2026-06-12; aggregates the terminal UX round #220 TTY detection + #221 shared style layer + audit --verbose, the native fuzz harness #223 with 22 targets + nightly workflow, and dependency bumps). Previous: v0.26.0 (2026-06-11; C3 range-matching round: #216 measurement, #217 all-versions advisory matching, #218 npm bounded ranges, snapshot 26,268 records + 202,526 all-versions entries). Current tree: 24 fuzz targets, 192 YAML rules + 66 analyzer-emitted (258 cataloged), 13 YAML categories (+ analyzer categories incl. agent-trust), 14 per-file scan analyzers (pattern, ci-trust, pkgmeta, jsrisk, pyrisk, scriptrisk, rsbuild, npmpolicy, pnpmpolicy, agentpolicy, skillpolicy, NLP, toxicflow, rugpull) plus the skill-chain project correlation and the aguara check incident command (npm/PyPI installed trees + pre-install npm lockfiles pnpm-lock.yaml / package-lock.json / yarn.lock classic v1 / yarn.lock Berry v2+ / bun.lock text - all with npm: alias resolution to the real package - and Go/Rust/PHP/Ruby/Java/.NET lockfiles), 0 lint issues.
Distribution: install.sh (mandatory checksum verification, bounded curl + retry), Homebrew tap, Docker (GHCR, multi-arch linux/amd64+arm64, runs as non-root UID 10001, base images digest-pinned, signed at digest with Cosign + SBOM + SLSA provenance attestations), GoReleaser (releases signed via Cosign keyless, SPDX SBOM per archive, -trimpath for reproducibility), GitHub Action, go install.
GitHub: 84 stars, 15 forks. 3 awesome-list PRs pending review in external repos (sbilly/awesome-security, Puliczek/awesome-mcp-security, ottosulin/awesome-ai-security; 3 others merged, forks deleted 2026-07-01). Issue #230: external contributor building an out-of-tree ATR rule pack for --rules (welcomed; link from README when it ships).
Pattern matcher already uses an Aho-Corasick keyword prefilter (active in production since v0.14.0). Real perf is ~210ms/op on the synthetic bench (was ~770ms without AC), so do not treat "pattern matcher perf" as an open backlog item unless pprof shows a concrete regression. Pending improvements: WASM build (cmd/wasm/ incomplete), adoption/marketing.
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.
- 6d ago First seen · 221 lines · 5,264 tokens per session scan A f78d5d835a21
aguara CLAUDE.md is an instructions file published in the GitHub repository garagon/aguara (88 stars, last pushed 4d ago), licensed Apache-2.0. It adds 5,264 tokens to every session, about $0.0263 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
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.