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 stefan-stepzero/shipkit --skill shipkit-review-directiongit clone --depth 1 https://github.com/stefan-stepzero/shipkitWrote 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/stefan-stepzero/shipkit/shipkit-review-direction)<a href="https://agentmods.dev/skills/stefan-stepzero/shipkit/shipkit-review-direction"><img src="https://agentmods.dev/badge/skills/stefan-stepzero/shipkit/shipkit-review-direction/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/stefan-stepzero/shipkit/shipkit-review-direction"><img src="https://agentmods.dev/badge/skills/stefan-stepzero/shipkit/shipkit-review-direction.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 | $0.00046 | $0.00720 |
| Opus 5.5 | $0.00018 | $0.00288 |
| Sonnet 5.5 | $0.00009 | $0.00144 |
| Haiku 4.5 | $0.00005 | $0.00072 |
Grade A, and why
shipkit-review-direction 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 — 58 lines — stays where its author put it; the contents beside it link to each section on GitHub.
shipkit-review-direction - Direction Assessment
Purpose: Read all direction artifacts and assess whether they are coherent, complete, and internally consistent. Write a structured assessment for the direction orchestrator.
Input
Required artifacts (the direction loop must produce all of these):
.shipkit/why.json(contains vision, purpose, stage).shipkit/product-discovery.json.shipkit/product-definition.json.shipkit/engineering-definition.json.shipkit/architecture.json.shipkit/design-system/(DIRECTION.md, PRINCIPLES.md, tokens/).shipkit/goals/strategic.json.shipkit/goals/product.json.shipkit/goals/engineering.json
Optional context (read if present, don't flag as missing):
.shipkit/metrics/latest.json— only exists after implementation
Coherence Checks
- Completeness: Are ALL 9 required direction artifacts present with non-placeholder content? Missing artifacts are gaps.
- Vision coherence: Does why.json state a vision that fulfills its stated purpose? (vision and purpose both live inside why.json)
- Goals ↔ Vision: Do goals, if achieved, realize the vision stated in why.json?
- Goals ↔ Stage: Are thresholds realistic for the current stage? Do all goals have rubrics?
- Internal consistency: Do goals reference capabilities the vision describes?
- Architecture ↔ Engineering Definition: Are architecture decisions consistent with the mechanisms and components defined?
- Design System ↔ Vision: Do principles align with the vision? Does aesthetic direction fit the target audience? Does token format match the stack?
- Design System specificity: Does DIRECTION.md use concrete values (hex codes, exact font names, px values, CSS easing functions) for every field? Flag any field that uses vague language ("clean", "modern", "intuitive", "user-friendly", "seamless", "elegant") without a measurable specification alongside it. Flag any missing source citations. Every dimension must trace back to a specific
.shipkit/field.
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 · 58 lines · 46 tokens per session scan A 7594483bebce
shipkit-review-direction is a skill published in the GitHub repository stefan-stepzero/shipkit (1 stars, last pushed 3mo ago), licensed MIT. It adds 46 tokens to every session and 720 once invoked, about $0.0002 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
lint-drupal-module
Lint review completo de un módulo Drupal 11 combinando 4 fuentes en paralelo — PHPStan level 5 + phpstan-drupal, PHPCS Drupal/DrupalPractice, agente drupal-qa (estándares) y agente drupal-security (OWASP). Dos modos — completo (todo el módulo) y diff (solo archivos cambiados vs develop). Genera informe markdown…
codex-diff-develop
Revisa el diff de la rama actual frente a develop en proyectos Drupal 11 siguiendo la metodología Codex (lógica de negocio, edge cases de hooks/queries, seguridad, performance, completitud). Genera un informe .md en la carpeta del IDE detectado (.antigravity/, .cursor/, .vscode/ o docs/) con hallazgos por severidad y…
codex-pr-review
Revisa pull requests en proyectos Drupal 11 (u otro) siguiendo la metodología Codex (lógica de negocio, edge cases de hooks/queries, seguridad, performance, completitud). Genera un informe .md en la carpeta del IDE detectado (.antigravity/, .cursor/, .vscode/ o docs/) con hallazgos por severidad y soluciones…
la-chancla
Use only when the user explicitly requests a strict review of one named task, change, plan, release, or invariant. Never self-selected, never auto-loaded, never invoked by another skill or by the mexican-mom router. NOT a session-wide mode and NOT a warning counter.
frijoles-en-el-tupper
Use when writing or reviewing names — functions, variables, types, files, schemas, API fields, config keys — and the comments attached to them, to check that each label predicts what is actually inside. NOT for whether failure paths are handled; use pero-ponte-sueter.
pero-tu-primo
Use after a substantial implementation works and before claiming it is good, clean, idiomatic, or optimal. Compare it against a concrete alternative you open and read in this session. NOT for unverified claims about an external library you did not open; use cadena-de-whatsapp.