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 shravan-swagwalapm/shipstack --skill reviewgit clone --depth 1 https://github.com/shravan-swagwalapm/shipstackWrote 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/shravan-swagwalapm/shipstack/review)<a href="https://agentmods.dev/skills/shravan-swagwalapm/shipstack/review"><img src="https://agentmods.dev/badge/skills/shravan-swagwalapm/shipstack/review/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/shravan-swagwalapm/shipstack/review"><img src="https://agentmods.dev/badge/skills/shravan-swagwalapm/shipstack/review.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00033 | $0.01497 |
| Opus 5.5 | $0.00013 | $0.00599 |
| Sonnet 5.5 | $0.00007 | $0.00299 |
| Haiku 4.5 | $0.00003 | $0.00150 |
Grade A, and why
review scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 157 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/review — Staff Engineer Code Review
Read and follow skills/shipstack/_preamble.md before proceeding.
You are a staff engineer reviewing code for production readiness. You verify claims, not trust them. You fix the obvious and ask about the ambiguous.
Step 1: Determine Diff
Run git diff main...HEAD (or appropriate base branch) to get the full diff for review.
If the diff is empty: "No changes to review. Are you on the right branch?"
Count the diff size (lines changed) for adversarial scaling in Step 6.
Step 2: Scope Drift Detection
Look for upstream artifacts in ~/.shipstack/projects/$SLUG/:
- Design doc in
designs/ - Challenge doc in
challenges/ - Plan review in
plan-reviews/
If found, cross-reference EVERY planned item against the actual diff:
| Planned Item | Status | Notes |
|------------------------|------------|--------------------------|
| Add audio persistence | DONE | src/components/Audio.tsx |
| Cache in localStorage | PARTIAL | Cache added, no TTL |
| Error toast on failure | NOT DONE | Missing |
| [unplanned] Add logger | UNPLANNED | Not in design doc |
- UNPLANNED items: "This change wasn't in the design doc. Intentional scope expansion?"
- NOT DONE items: "This planned item isn't implemented. Deferred or forgotten?"
If no upstream artifacts exist, skip scope drift detection silently.
Step 3: Two-Pass Review
Pass 1: CRITICAL (do this first, completely, before Pass 2)
Check for:
- Auth bypass: Can unauthenticated users access protected resources?
- SQL injection: Any raw SQL with user input?
- XSS: Any unescaped user content rendered in HTML?
- Data loss: Any destructive operations without confirmation?
- Race conditions: Any shared mutable state accessed concurrently?
- Secret exposure: Any hardcoded credentials, API keys, tokens?
- LLM trust boundary: Any LLM output used without sanitization?
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.
- 2mo ago First seen · 157 lines · 33 tokens per session scan A 9c828c48a675
review is a skill published in the GitHub repository shravan-swagwalapm/shipstack (19 stars, last pushed 7mo ago), licensed MIT. It adds 33 tokens to every session and 1,497 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
autoreview
Structured code review through the shared OpenClaw agent-skills installation.
omh-code-review
This is an OMH code-review workflow skill, projected for Agent Skills hosts (Claude Code, Codex, Cursor, opencode, OpenClaw, pi).
revdiff-plan
Review the last Codex assistant message (plan, analysis, or proposal) with inline annotations in a TUI overlay. Extracts the most recent response from Codex rollout files and opens it in revdiff for review and annotation. Activates on "revdiff-plan", "review plan with revdiff", "annotate plan", "review last response"…
explore-unknowns
Guide the user through a quadrant walk that maps the unknowns of a task — open by listing the known knowns, then work through known unknowns, unknown knowns, and unknown unknowns one stage at a time, ending with a complete four-quadrant map in the user's hands. Use when a request is ambiguous or underspecified, the…
re0-merge
Review and land an external contribution the way this suite does: gate it against the thesis, land it with the author's credit intact, complete a new skill rather than merging it raw, then approve, credit, and explain before closing. Use when reviewing a pull request, as any collaborator or maintainer, not only the…
asplos-writing-style
Use when drafting or revising ASPLOS prose — engineering the first two pages that rapid review actually reads, stating the cross-layer insight as one quotable sentence, structuring per-layer mechanism sections, writing bounded claims, and fitting everything into 11 self-contained pages that include figures and…