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 shipgit 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/ship)<a href="https://agentmods.dev/skills/garagon/nanostack/ship"><img src="https://agentmods.dev/badge/skills/garagon/nanostack/ship/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/ship"><img src="https://agentmods.dev/badge/skills/garagon/nanostack/ship.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Rogue Agent · line 149 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
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 | $0.00036 | $0.04253 |
| Opus 5.5 | $0.00014 | $0.01701 |
| Sonnet 5.5 | $0.00007 | $0.00851 |
| Haiku 4.5 | $0.00004 | $0.00425 |
Grade A, and why
ship scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 415 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/ship — Ship to Production
You get code from "done" to "verified in production" in one pass. You own the full pipeline: pre-flight, PR, CI, deploy, verification. If something breaks after merge, you rollback first and debug second.
Telemetry preamble
Defensive telemetry init. No-op if telemetry is disabled via NANOSTACK_NO_TELEMETRY=1, ~/.nanostack/.telemetry-disabled, or if the helpers are removed.
_P="$HOME/.claude/skills/nanostack/bin/lib/skill-preamble.sh"
[ -f "$_P" ] && . "$_P" ship
unset _P
Session state
Read profile, run_mode, autopilot, and plan_approval per reference/session-state-contract.md BEFORE doing any pre-flight or pipeline work. This is required for /ship because every subsequent step in this skill mutates state (commit, push, PR, deploy, rollback) and the contract forbids that when run_mode == report_only.
SESSION=$NANOSTACK_STORE/session.json
[ -f "$SESSION" ] || SESSION="$HOME/.nanostack/session.json"
PROFILE=$(jq -r '.profile // (if (.capabilities // null) == null then "guided" else "professional" end)' "$SESSION" 2>/dev/null || echo "professional")
RUN_MODE=$(jq -r '.run_mode // "normal"' "$SESSION" 2>/dev/null || echo "normal")
AUTOPILOT=$(jq -r '.autopilot // false' "$SESSION" 2>/dev/null || echo "false")
PLAN_APPROVAL=$(jq -r '.plan_approval // (if .autopilot then "auto" else "manual" end)' "$SESSION" 2>/dev/null || echo "manual")
Report-only mode
When RUN_MODE == "report_only", /ship enters Shipping report mode and MUST NOT mutate anything. The session-state contract is explicit: report-only sprints exist so the user can see what /ship would do without committing the agent to action.
Allowed in report-only:
- Read session state, artifacts, git status, branch info.
- Inspect what would change: list files staged, the branch name, the commit message that would be used, the PR title/body that would be filed, the deploy target.
- List blockers: missing review/security/qa artifacts, uncommitted changes that need attention, broken README links from
quality-check.sh. - Print a final "Shipping report" summary that names every action the user can take to ship for real.
What ships with it
5 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.
- 1mo ago First seen · 415 lines · 36 tokens per session scan A 169005240fcb
ship is a skill published in the GitHub repository garagon/nanostack (207 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 36 tokens to every session and 4,253 once invoked, about $0.0001 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.
Other skills, from other repositories
explain-pr
Explain a PR: the background problem and the proposed solution.
release
Release gentle-pi through GitHub and npm. Trigger: release, publish, npm publish, GitHub release, version bump.
releasing-code
Prepare, publish, or repair a software release and write its release notes. Use for cutting a versioned release or editing release notes. NOT for updating an installed package, publishing articles, or discussing a release; for general documentation use documenting-code.
upload
Pre-upload gate for track handoff. Verifies review status, HLD approvals, deploy checklist, and validator chain before git upload or PR submission.
plate
Turn finished local work into a commit, an ordinary pull request, or a pull request stack. Use this skill to commit changes or to publish a branch. Use it to open or update a pull request. Use it to create, sync, restack, or submit a pull request stack. You can also run /plate. This skill owns all staging, commits…
release-docs
Diff-driven documentation sync after a release. Determines what source files changed, delegates changelog to zuvo:docs, updates only docs whose source changed. Flags: --dry-run, explicit range argument.