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/stefan-stepzero/shipkit/shipkit-engineering-definitionnpx skills add stefan-stepzero/shipkit --skill shipkit-engineering-definitiongit clone --depth 1 https://github.com/stefan-stepzero/shipkitWhat 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 | $0.00044 | $0.05323 |
| Opus 5 | $0.00022 | $0.02661 |
| Sonnet 5 | $0.00009 | $0.01065 |
| Haiku 4.5 | $0.00004 | $0.00532 |
Grade A, and why
shipkit-engineering-definition 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 — 494 lines — stays where its author put it; the contents beside it link to each section on GitHub.
shipkit-engineering-definition — Technical Approach
Defines HOW we build the product defined in product-definition.json. For each feature, designs the technical mechanisms, captures design decisions, recommends stack direction (greenfield), and defines component structure.
This is the engineering blueprint — it takes the product's features and UX patterns and defines the technical approach to implement them. Downstream skills (goals, spec) read both product-definition.json and engineering-definition.json. Architecture decisions are captured directly in this file.
When to Invoke
User triggers:
- "How should we build this?", "Technical approach", "Engineering design"
- "Define mechanisms", "Component structure", "Technical decisions"
- "Stack direction", "What technologies?"
Workflow position:
- After
/shipkit-product-definition(needs features and UX patterns) - Before
/shipkit-product-goalsand/shipkit-engineering-goals(goals derive criteria from mechanisms)
Prerequisites
Required (fail gracefully if missing):
.shipkit/product-definition.json— features, UX patterns, differentiators
Recommended (enrich the proposal):
.shipkit/why.json— project purpose and vision.shipkit/goals/strategic.json— project stage and constraints.shipkit/stack.json— existing technology constraints.shipkit/product-discovery.json— pain points for traceability
Optional (for existing projects):
.shipkit/codebase-index.json— existing code structure
If product-definition.json is missing, tell the user: "Run /shipkit-product-definition first — I need to know what features to design mechanisms for." and stop.
Process
Completion Tracking
After reading prerequisites, create tasks:
TaskCreate: "Design 2-5 mechanisms mapped to features"TaskCreate: "Define 2-6 components mapped to mechanisms"TaskCreate: "Capture cross-cutting design decisions"TaskCreate: "Write engineering-definition.json"TaskCreate: "Derive and dual-write architecture.json (lean) + architecture-archive.json (full)"
What ships with it
9 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.
- references/architecture-log-schema.md 11 KB
- references/ecosystem-defaults/nextjs-fullstack.md 3.0 KB
- references/ecosystem-defaults/python-api.md 2.9 KB
- references/ecosystem-defaults/python-llm.md 5.8 KB
- references/ecosystem-defaults/react-spa.md 2.5 KB
- references/example.json 6.2 KB
- references/mechanism-standards.md 5.1 KB
- references/output-schema.md 6.9 KB
- references/README.md 2.0 KB
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 · 494 lines · 44 tokens per session scan A e15a467734b2
shipkit-engineering-definition is a skill published in the GitHub repository stefan-stepzero/shipkit (1 stars, last pushed 1mo ago), licensed MIT. It adds 44 tokens to every session and 5,323 once invoked, about $0.0002 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
opencli-sitemap-author
Use when creating or maintaining OpenCLI site sitemaps: agent-facing navigation, page-state, action, workflow, API-reference, pitfall, and fallback knowledge for a website. Use after browser exploration discovers durable site context, when a sitemap is stale, or when promoting local site knowledge into the repo.
golden-rss
Use when testing the rss golden build.
omh-buzz
This is a Hermes-native buzz workflow skill.
omh-code-review
This is a Hermes-native code-review workflow skill.
redteam-api-detail-pack
Domain routing and boundary guidance for authorized API security testing, including BOLA/IDOR, authentication bypass, mass assignment, missing rate limits, and GraphQL issues. Use when a task belongs to the API testing domain and needs scope, evidence, pivot, or exit criteria.
redteam-postex-detail-pack
Domain routing and boundary guidance for authorized post-exploitation testing after initial access, including privilege escalation, persistence, lateral movement, data collection, and cleanup considerations. Use when a task belongs to the post-exploitation domain and needs scope, evidence, pivot, or exit criteria.