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-engineering-goalsgit 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-engineering-goals)<a href="https://agentmods.dev/skills/stefan-stepzero/shipkit/shipkit-engineering-goals"><img src="https://agentmods.dev/badge/skills/stefan-stepzero/shipkit/shipkit-engineering-goals/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-engineering-goals"><img src="https://agentmods.dev/badge/skills/stefan-stepzero/shipkit/shipkit-engineering-goals.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 | $0.00039 | $0.04377 |
| Opus 5.5 | $0.00016 | $0.01751 |
| Sonnet 5.5 | $0.00008 | $0.00875 |
| Haiku 4.5 | $0.00004 | $0.00438 |
Grade A, and why
shipkit-engineering-goals 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 — 441 lines — stays where its author put it; the contents beside it link to each section on GitHub.
shipkit-engineering-goals — Technical Performance Criteria
Purpose: Derive measurable technical performance criteria from the engineering blueprint. Each mechanism, component, and design decision implies criteria for "how do we know this performs?" — this skill makes those criteria explicit, measurable, and trackable.
What it does: Reads the engineering blueprint + stage context, derives technical criteria from cited signals, writes the engineering goal file, and adds engineering criteria to existing stage gates. Most criteria are grounded from engineering-definition.json, stack.json, and stage — only hard performance targets with no signal become questions.
Protocol: This skill follows the canonical elicitation protocol defined in install/shared/references/elicitation-protocol.md (the mechanics — marker, state files, resume).
Calibration: Apply install/shared/references/ground-or-ask-calibration.md (the intelligence — propose vs ask). Ground first: this is a DERIVATION skill — most criteria flow directly from engineering-definition.json (mechanisms → performance/quality/reliability targets), stack.json (stack norms), goals/strategic.json (stage gates), and goals/product.json (outcome alignment). Cite the signal for every proposed threshold and tag it with its source. Flag low-leverage guesses (guessed: true). The only HIGH-LEVERAGE ungrounded fields are hard performance/reliability TARGETS where no signal (stage, stack norms, product goals) implies the number — ask those and only those. Questions are rare (often zero for a well-defined stack); if you're generating more than 2–3, re-ground first.
Output: One JSON file:
goals/engineering.json— Technical-performance criteria (EM owns)
Strategic goals (stage, constraints, business metrics: S-) are handled by
/shipkit-stage, owned by the Visionary agent. Run that skill first — it creates the stage gates that engineering criteria are added to. Product goals (user outcomes: P-) are handled by/shipkit-product-goals, owned by the PM agent.
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.
- 1mo ago First seen · 441 lines · 39 tokens per session scan A 76425861451c
shipkit-engineering-goals is a skill published in the GitHub repository stefan-stepzero/shipkit (1 stars, last pushed 3mo ago), licensed MIT. It adds 39 tokens to every session and 4,377 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
visual-qa
Runs rigorous visual QA across web, terminal, and paginated surfaces: an Apple HIG-based checklist, paired light/dark captures at phone and desktop widths, screenshot evidence, and a per-item PASS/FAIL verdict. Use for any UI build or change, or when asked whether a page, component, or TUI looks right or follows the…
remove-ai-slops
Removes AI-generated code smells from branch changes or an explicit file list behind regression tests. Use when the user asks to clean up, deslop, or remove AI-slop patterns from recent changes.
visual-regression
Setup visual regression testing with Storybook stories, configuration, and CI/CD workflows. Supports Chromatic, Percy, BackstopJS. Auto-invoke when user says "set up visual regression", "add Chromatic tests", "add screenshot testing", or "set up Percy".
test-coverage-improver
Analyze test coverage gaps and generate tests to improve coverage. Use when improving test coverage, finding untested code, or writing missing tests.
browser-test-loop
Use to actually verify a web change in a real browser instead of assuming it works — click through a flow, catch console errors, check a form submits, confirm a fix on the page. Trigger when a UI change needs proof, a bug only reproduces in the browser, or the user asks to test, check, or screenshot the running app.
Vizra ADK Evaluation Framework
Test and evaluate AI agents with automated evaluations, assertions, and LLM-as-a-Judge patterns.