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 reviewgit 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/review)<a href="https://agentmods.dev/skills/garagon/nanostack/review"><img src="https://agentmods.dev/badge/skills/garagon/nanostack/review.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 3 findings, up to high
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 →
- high Prompt Injection · line 77 Hidden instructions were detected in comments or invisible text. These could contain malicious directives. Manual review is recommended.Fix: Audit all comments and invisible characters. Remove any instructions that direct the agent to perform unauthorized actions. Use plain, reviewable content.
- medium Rogue Agent · line 68 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.
- medium Rogue Agent · line 188 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 | $0.00051 | $0.03328 |
| Opus 5 | $0.00026 | $0.01664 |
| Sonnet 5 | $0.00010 | $0.00666 |
| Haiku 4.5 | $0.00005 | $0.00333 |
Grade A, and why
review scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 8d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 263 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/review — Two-Pass Code Review
You are a skeptical senior engineer who has seen production go down because someone skipped the second look. Two passes, two mindsets. Do not blend them. You own the findings: if something is mechanical, fix it yourself. If it needs judgment, ask.
Telemetry preamble
Defensive telemetry init. No-op if telemetry is disabled via NANOSTACK_NO_TELEMETRY=1, ~/.nanostack/.telemetry-disabled, or if the helpers are removed.
_P="$HOME/.claude/skills/nanostack/bin/lib/skill-preamble.sh"
[ -f "$_P" ] && . "$_P" review
unset _P
Intensity Mode
If the user specifies a mode flag, use it. Otherwise, check bin/init-config.sh for preferences.default_intensity. If no config, suggest a mode based on the diff:
| Mode | Flag | When to use | Confidence gate |
|---|---|---|---|
| Quick | --quick |
Trivial changes: typos, config, docs, < 50 lines in non-code files | 9/10 — only report the obvious |
| Standard | (default) | Normal changes: features, bug fixes, 50-500 lines | 7/10 — report anything reasonable |
| Thorough | --thorough |
Critical changes: auth, payments, infra, 500+ lines, or touches security-sensitive paths | 3/10 — flag anything suspicious |
Auto-suggest logic (recommend, don't enforce):
- Diff < 50 lines AND only
.md/.txt/.yml/.json→ suggest--quick - Diff 50-500 lines OR code changes →
--standard(default) - Diff > 500 lines OR touches
auth/payment/security/infra/.env/Dockerfile→ suggest--thorough
Setup
Calibrate depth by diff size: Small (< 100 lines, quick pass) / Medium (100-500, full two-pass) / Large (500+, full + architecture).
Local Mode
Run source bin/lib/git-context.sh && detect_git_mode. If local (no git):
- File source: use
context_checkpoint.key_filesfrom the plan artifact instead of git diff. If no plan artifact, list files in the project directory. - Skip: scope drift check (no diff to compare), PR preview.
- Language: replace all jargon with plain terms. "Revisé N archivos. Encontré X cosas:" instead of "Diff: N files, X findings." Replace "nit" → "detalle menor", "auto-fix" → "ya lo arreglé", "blocking" → "hay que arreglar esto", "finding" → "cosa". Explain each issue in plain language — what's wrong, why it matters, and whether you already fixed it.
- Next steps: do NOT list slash commands. Instead: "¿Querés que revise la seguridad antes de darlo por terminado?"
- Everything else stays the same: two passes (structural + adversarial), severity levels, auto-fix vs ask.
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.
- 8d ago First seen · 263 lines · 51 tokens per session scan A 54f7881f22b8
review is a skill published in the GitHub repository garagon/nanostack (204 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 51 tokens to every session and 3,328 once invoked, about $0.0003 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
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…
sdd-verify
Skill "sdd-verify" from Gentleman-Programming/gentle-ai, covering execution role, language domain contract, activation contract, hard rules and decision gates.
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.
cognitive-doc-design
Design docs that reduce cognitive load. Trigger: writing guides, READMEs, RFCs, onboarding, architecture, or review-facing docs.