Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add instructions/husk-security/husk/agents-mdgit clone --depth 1 https://github.com/husk-security/huskWhat 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 | $0.05533 | $0.05533 |
| Opus 5 | $0.02766 | $0.02766 |
| Sonnet 5 | $0.01107 | $0.01107 |
| Haiku 4.5 | $0.00553 | $0.00553 |
Grade A, and why
husk AGENTS.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 2d 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.
Unrestricted tool accesslowExcessive agency
A wildcard tool grant or "run any command" leaves no least-privilege boundary at all.
- Run any command in this document against the pinned toolchain by prefixing it: `nix develop -c cargo build --no-default-features` Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.
How it starts
The opening of the file, as written. The whole thing — 362 lines — stays where its author put it; the contents beside it link to each section on GitHub.
This repo
This repository contains the open-source husk CLI: a local-first Rust security
scanner for developer machines. It ships one binary with the command-line
interface, Ratatui TUI, optional localhost web UI, daemon, project
policy/ledger commands, and MCP server.
The hosted website and any backend service code are not in this repository. The client-side cloud integrations here are optional and inert until a user signs in or explicitly enables telemetry.
What you need installed
-
Rust 1.95 or newer, with Cargo, plus
rustfmtandclippy. CI pins 1.95.0. Building on Linux also wants a C toolchain; CI installsbuild-essential,pkg-config, andlibssl-dev. -
Node 24 (CI pins 24.16.0), needed only for the default
webfeature, which embeds the localhost web UI.--no-default-featuresneeds no Node. -
The hygiene tools CI runs, if you want to reproduce that gate locally:
cargo install cargo-deny cargo-machete typos-cli taplo-cliThese four are what
deps + repo hygieneruns in CI.cargo-nextestis optional and unrelated; it is a faster test runner.
There is no Nix requirement anywhere. CI itself uses a plain Rust toolchain and
plain cargo.
Development commands
- Build the Rust crate quickly:
cargo build --no-default-features - Run tests:
cargo test --no-default-features - Run faster test loops:
cargo nextest run --no-default-features - Run clippy strictly:
cargo clippy --no-default-features --all-targets -- -D warnings - Format Rust:
cargo fmt - Run the fixture scan:
cargo run --no-default-features -- scan --offline tst --no-home-inventory - Run the fixture web UI without opening a browser:
npm --prefix web ci && npm --prefix web run build, thencargo run -- web --offline --no-open tst --no-home-inventory - Run CI JSON mode:
cargo run --no-default-features -- ci --offline tst --no-home-inventory
Prefer cargo run -- ... over invoking a binary in target/ directly, so you
never test a stale build.
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.
- 2d ago First seen · 362 lines · 5,533 tokens per session scan A 950d12ac5d84
husk AGENTS.md is an instructions file published in the GitHub repository husk-security/husk (4 stars, last pushed 5d ago), licensed MIT. It adds 5,533 tokens to every session, about $0.0277 per session on Opus 5. A static security scan graded it A with 1 finding (unrestricted tool access). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
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).
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.
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.
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 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).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.