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/moasq/agentic-ship/testingnpx skills add moasq/agentic-ship --skill testinggit clone --depth 1 https://github.com/moasq/agentic-shipWhat 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 | $0.00068 | $0.01585 |
| Opus 5 | $0.00034 | $0.00792 |
| Sonnet 5 | $0.00014 | $0.00317 |
| Haiku 4.5 | $0.00007 | $0.00159 |
Grade A, and why
testing 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 2d 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 — 110 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Testing & self-healing
Downstream contract: paths like
src/andconvex/refer to the product workspace that adopts Agentic Ship, not this tool repo.
A failure is allowed to happen once. Gates catch it, the heal loop repairs it with
evidence, and the repair graduates into a rule (.agents/heal-ledger.md) so the class
cannot return.
The gates, in order
| Gate | Command | Proves |
|---|---|---|
| G0 | pnpm health |
required tool assets present, no bundled application residue, Node 20+ (in the downstream product: also SSOT, pins, secrets, mirrors) |
| G1 | pnpm verify |
the offline definition of done — G0 plus the generated host adapters (check:agents), the pinned MCP mirror (check:mcp), the UI tooling (check:ui), downstream backend postconditions (check:backend), and the unit contracts (pnpm test). No lint and no product build run in this tool repo, because neither exists here |
| G2 | pnpm test |
deterministic tool contracts (vitest), in memory, no network |
| G3 | pnpm test:e2e |
downstream product only — the app in a real browser: pages, headers, SEO surface. There is no Playwright config or product build in this tool repo, so this gate runs in the product workspace |
| all | pnpm verify:full |
verify + the fail-closed production dependency audit (pnpm audit:supply-chain) |
| launch | pnpm preflight [--prod] |
production readiness — see the production-preflight skill |
A gate runs only when the ones above it are green. pnpm verify is the definition of
done for every completion; verify:full is for PRs and before a deploy.
GitHub consumers can run the same gate through the pinned reusable action. Installation,
permissions, audit opt-in, updates, and removal are documented in
references/github-action.md.
In the downstream product workspace the same gate names extend: CI there splits G0–G2
plus the product build across macOS, Linux and Windows, and G3 on Linux. Every gate runs
with no network beyond the install — fonts are committed rather than fetched, which is
what lets the production build inside Playwright's webServer succeed on a runner with
no egress.
What ships with it
1 file 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.
- 2d ago First seen · 110 lines · 68 tokens per session scan A fcd3e4781f35
testing is a skill published in the GitHub repository moasq/agentic-ship (10 stars, last pushed 3d ago), licensed MIT. It adds 68 tokens to every session and 1,585 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 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
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…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…