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 skills/husk-security/husk/using-husknpx skills add husk-security/husk --skill using-huskgit clone --depth 1 https://github.com/husk-security/huskWrote 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/skills/husk-security/husk/using-husk)<a href="https://agentmods.dev/skills/husk-security/husk/using-husk"><img src="https://agentmods.dev/badge/skills/husk-security/husk/using-husk.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 | $0.00087 | $0.02430 |
| Opus 5 | $0.00044 | $0.01215 |
| Sonnet 5 | $0.00017 | $0.00486 |
| Haiku 4.5 | $0.00009 | $0.00243 |
Grade A, and why
using-husk 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 4d 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 — 142 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Using husk
Husk is a developer security scanner installed on this machine. It
scans projects and the home directory for vulnerable/compromised packages
(~68 package ecosystems: npm, PyPI, cargo, Go, OS package managers, editor
extensions, MCP servers, and more), leaked secrets, risky automation (GitHub Actions, git
hooks, install scripts), and AI/MCP config issues. Unless --offline is set,
scans send discovered package names and versions to public advisory databases
(OSV.dev, npm, PyPI, GitHub); file contents, paths, and secrets never leave the
machine. Cloud features (account, inventory sync, telemetry) are strictly
opt-in and the scanner is complete without them.
Prefer the MCP tools
If the husk MCP server is connected, use its tools instead of the CLI:
| Tool | What it does |
|---|---|
husk_status |
Summary of the latest cached scan: timestamp, roots, severity counts, category counts, provider status. Call this first. |
husk_findings |
List cached findings, sorted by severity. Filters: min_severity, category, path_contains, limit (default 50). |
husk_packages |
Packages discovered in the cached scan with their manifest paths. Filters: ecosystem, name_contains, limit. |
husk_fix |
Read-only plan of the safe-fixable subset, each item classified auto_safe/confirm/manual. Never writes; apply changes with your own tools (or husk fix --apply for the auto-safe subset). |
husk_scan |
Run a fresh scan of given paths (defaults to cwd) and cache it. Options: home, offline, include_home_inventory (defaults false here, unlike the CLI). |
husk_policy |
Read the committed project policy (.husk/policy.toml) for a path: blocked/allowed package coordinates, suppressed finding ids, CI threshold. Call before installing/recommending a dependency to respect the team's decisions; no scan needed. |
husk_ledger |
Read the personal trust-ledger history (~/.husk/ledger.jsonl) of past approve decisions + a chain-integrity flag, so you don't re-flag what the user already triaged. Optional limit (default 50). |
husk_guide |
Read scan-backed guidance with baseline/recommendation kind, severity, control status, local evidence, related finding/remediation ids, steps, options, and sources. Progress requires read plus verified/completed/dismissed. |
husk_guide_update |
Mark a guide item read/complete/dismiss/clear (optional reason), persisted to husk's own state file (~/.husk/guide.json). |
husk_feedback |
Send free-text product feedback about husk to the husk developers (message required, optional contact reply email). Sends only the message, the contact, and the husk version. Ask the user before sending on their behalf. |
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.
- 4d ago First seen · 142 lines · 87 tokens per session scan A f9c8e787abb4
using-husk is a skill published in the GitHub repository husk-security/husk (5 stars, last pushed 2d ago), licensed MIT. It adds 87 tokens to every session and 2,430 once invoked, about $0.0004 per session on Opus 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 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.
chat-perf
Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…