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 skills add garagon/nanostack --skill audit-licensesgit clone --depth 1 https://github.com/garagon/nanostackWrote 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/garagon/nanostack/audit-licenses)<a href="https://agentmods.dev/skills/garagon/nanostack/audit-licenses"><img src="https://agentmods.dev/badge/skills/garagon/nanostack/audit-licenses/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/skills/garagon/nanostack/audit-licenses"><img src="https://agentmods.dev/badge/skills/garagon/nanostack/audit-licenses.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00048 | $0.01351 |
| Opus 5 | $0.00024 | $0.00675 |
| Sonnet 5 | $0.00010 | $0.00270 |
| Haiku 4.5 | $0.00005 | $0.00135 |
Grade A, and why
audit-licenses scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 11d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 111 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/audit-licenses — Dependency License Audit
You audit the open-source licenses of this project's dependencies. The point is compliance: some licenses (GPL, AGPL) force the project that uses them to be open-source under the same terms. The team needs to know that before shipping.
This is an example custom skill. It shows the patterns every nanostack-compatible skill follows: detect the project, do the work, save an artifact so future skills can read it.
Process
0. Resolve paths (host-agnostic)
Every executable snippet below redefines two env vars at the top, so each snippet is copy-paste runnable on its own. Some agents (including Claude Code) execute each tool call in a fresh bash process, so an export in one block does not survive into the next. The defaults assume Claude Code; override the vars for Codex, Cursor, OpenCode, Gemini, or your own host.
NANOSTACK_ROOT="${NANOSTACK_ROOT:-$HOME/.claude/skills/nanostack}"
SKILL_DIR="${SKILL_DIR:-$HOME/.claude/skills/audit-licenses}"
Common substitutions:
| Host | NANOSTACK_ROOT | SKILL_DIR |
|---|---|---|
| Claude Code | $HOME/.claude/skills/nanostack |
$HOME/.claude/skills/audit-licenses |
| Codex / Cursor / OpenCode / Gemini | $HOME/.agents/skills/nanostack (or wherever the agent loads skills from) |
$HOME/.agents/skills/audit-licenses |
If the user already exported NANOSTACK_ROOT and SKILL_DIR, the ${VAR:-default} form does not overwrite them.
1. Register the phase (first run only)
save-artifact.sh and the resolver only accept phases listed in .nanostack/config.json. Register audit-licenses once per project:
mkdir -p .nanostack
if [ -f .nanostack/config.json ]; then
jq '.custom_phases = ((.custom_phases // []) + ["audit-licenses"] | unique)' \
.nanostack/config.json > .nanostack/config.json.tmp \
&& mv .nanostack/config.json.tmp .nanostack/config.json
else
printf '%s\n' '{"custom_phases":["audit-licenses"]}' > .nanostack/config.json
fi
Once registered the phase is first-class: the resolver returns phase_kind=custom, the artifact store accepts audit-licenses, and the rest of the lifecycle scripts learn to handle it as PRs 4-6 of the Custom Stack Framework round land.
What ships with it
3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 11d ago First seen · 111 lines · 48 tokens per session scan A a13b89814987
audit-licenses is a skill published in the GitHub repository garagon/nanostack (205 stars, last pushed today), licensed Apache-2.0. It adds 48 tokens to every session and 1,351 once invoked, about $0.0002 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 2026-08-30.
Other skills, from other repositories
ring:adding-multi-tenancy
Adding database-per-tenant isolation into a Go service end-to-end via an 11-gate cycle: detects the stack, audits compliance, then dispatches backend agents to implement tenantId-from-JWT routing through the lib-commons v5 dispatch layer (config, middleware, repositories, metrics, tests) and runs reviewers. Use when…
ring:testing-skills-with-subagents
Hardening a skill so it resists rationalization under pressure: run combined-pressure scenarios on a subagent without the skill (RED), capture excuses verbatim, write/edit the skill (GREEN), then plug loopholes (REFACTOR) until compliance holds. Use when deploying or editing a discipline-enforcing skill that an agent…
gentle-ai-collab-perfect
Trigger: contributing to Gentleman-Programming/gentle-ai as an external collaborator. Strict issue-first workflow, honest PR bodies, contributor-vs-maintainer scope, chained-PR strategy, verification protocol, docstring coverage. Load whenever the active repo is Gentleman-Programming/gentle-ai and any part of the…
issue-creation
Trigger: issue creation, bug reports, feature requests, or issue approval. Create and triage GitHub issues from repository evidence.
sdd-tasks
Break an SDD change into implementation tasks. Trigger: orchestrator launches task planning for a change.
work-unit-commits
Plan commits as reviewable work units. Trigger: implementation, commit splitting, chained PRs, or keeping tests and docs with code.