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 calneymgp/solodev --skill dev-shipgit clone --depth 1 https://github.com/calneymgp/solodevWrote 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/calneymgp/solodev/dev-ship)<a href="https://agentmods.dev/skills/calneymgp/solodev/dev-ship"><img src="https://agentmods.dev/badge/skills/calneymgp/solodev/dev-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/calneymgp/solodev/dev-ship"><img src="https://agentmods.dev/badge/skills/calneymgp/solodev/dev-ship.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 | $0.00121 | $0.01141 |
| Opus 5.5 | $0.00048 | $0.00456 |
| Sonnet 5.5 | $0.00024 | $0.00228 |
| Haiku 4.5 | $0.00012 | $0.00114 |
Grade A, and why
dev-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 — 98 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/dev-ship — Pronto é estado verificado, não sensação
Task ✅ ≠ feature ✅. Esta skill é a barreira entre "terminei as tasks" e "isso pode ir pra produção". Roda no fim de um PLAN.md ou standalone sobre qualquer diff que o usuário queira fechar.
Processo
1. Verificação dura (must_pass global)
Rode, na ordem, o que o projeto tiver (CLAUDE.md diz quais):
- Typecheck / build
- Suite de testes completa (não só os módulos tocados)
- Lint
Qualquer vermelho para o ship aqui. Vermelho vira fix-task (ou /dev-fix) — nunca "é flaky, ignora".
2. Must-Haves do PLAN.md (goal-backward)
Se existe .plans/<feature>/PLAN.md:
- Truths: cheque cada behavior listado — idealmente via smoke test, não inspeção visual
- Artifacts: cada arquivo existe? min_lines? exports/contains corretos?
- Key Links: rode os regex declarados — devem casar
- Demo script: execute os passos. A feature demonstra em 60s ou não demonstra?
Falhou qualquer um → diagnostique por que a task "completed" não satisfez o goal, crie fix-task no PLAN.md, execute, re-verifique. Loop até verde. Não mascare.
3. Revisão do diff (você é o reviewer agora)
Leia o diff completo da feature (git diff <base>...HEAD ou working tree) com olhos de reviewer, não de autor:
Caçada a restos:
console.log/print/dbg!de debug, prefixos[DEBUG-*]TODO/FIXME/HACKnovos sem issue ou justificativa- Código comentado, imports não usados, arquivos órfãos
- Dependência adicionada que só se usa em 1 linha trocável
Caçada a bugs de autor:
- Edge cases dos Goals que nenhuma task cobriu
- Error paths que engolem erro em silêncio (catch vazio)
- Async sem await / promise solta / race óbvia
- Off-by-one em paginação/slice/loop
4. Lente de segurança (só arquivos tocados)
Não é auditoria completa — é o mínimo que evita vergonha:
- Segredo/chave/token hardcoded? (inclusive em teste e fixture)
- Input externo chegando em query/comando/path sem validação?
- Endpoint novo sem auth/permissão onde os vizinhos têm?
- Dado sensível indo pra log?
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 · 98 lines · 121 tokens per session scan A 3d373dc1071f
dev-ship is a skill published in the GitHub repository calneymgp/solodev (2 stars, last pushed 1mo ago), licensed MIT. It adds 121 tokens to every session and 1,141 once invoked, about $0.0005 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 2026-08-31.
Other skills, from other repositories
validate-release-green
Run or inspect the local Release-Green observer for an exact base or combined PR candidate, separating hard failures, advisory drift and incomplete evidence. Use for maintainer preflight; full CI acceptance remains a separate requirement.
api-tester
A tool for creating and checking API tests from the real API contract and implementation. An API is the agreed way that software sends requests and receives responses.
changelog-gen
A changelog generator that turns Git history into a version-by-version record of project changes. A changelog is a readable summary of new features, fixes, breaking changes, documentation, and other updates.
publish
Publish oh-my-opencode to npm by triggering the GitHub Actions publish workflow and verifying its artifacts. Ship-only: never runs pre-publish-review or re-reviews merged code unless the user explicitly asks. Argument: . Triggers: publish, release, deploy, npm publish.
pre-publish-review
Nuclear-grade 12-agent pre-publish release gate. Runs /get-unpublished-changes to detect all changes since last npm release, spawns up to 10 ultrabrain agents for deep per-change analysis, invokes /review-work (orchestrator manual QA plus one gate reviewer) for holistic review, and 1 oracle for overall release…
ship
Pre-release gate — run the full gate, responsive + render checks, then produce the release checklist (README badge/current/changelog). Use before tagging a release.