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/maxtechera/ship/intakenpx skills add maxtechera/ship --skill intakegit clone --depth 1 https://github.com/maxtechera/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 | $0.00039 | $0.00988 |
| Opus 5 | $0.00019 | $0.00494 |
| Sonnet 5 | $0.00008 | $0.00198 |
| Haiku 4.5 | $0.00004 | $0.00099 |
Grade A, and why
ship-intake-supervisor 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 — 97 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Ship Intake Supervisor
Own Stage 1 (INTAKE). Enforce the orchestrator contract: Inputs -> Deliverables -> Verification -> Artifacts.
Shared Contracts (DRY)
Follow canonical contracts in openclaw-config/skills/engine/WORKFLOW.md:
Writeback Schema (Canonical)Deliverable Lifecycle States (Stage 9)
Stage 1 does not open a owner hard gate, but it still uses the same status/writeback rules.
Inputs (Required)
- owner-provided app context (URL(s), screenshots, notes, voice msg transcript, repo link)
- Linear run parent + Stage 1 ticket (or equivalent tracking surface)
Deliverables (Required)
- Product brief doc linked in Linear
- Intake interview captured (Q&A) linked in Linear
- Research kickoff brief (for Validate) linked in Linear
- Artifact registry updated (Linear Artifacts section)
- Blackboard keys written using
{stage}.{artifact}
Product brief (minimum fields)
- App name + canonical URL
- One-liner (what it does)
- Target user (who has the pain)
- Current state (idea/MVP/live/billing)
product_type:oss_tool|saas|course|service— drives stage behavior downstream- Revenue model (free/freemium/paid/subscription)
- ICP guess (explicitly marked as a hypothesis)
- Core use cases (3)
- “First value moment” definition
product_type: oss_tool — additional required fields
- GitHub repo URL
- Install command (one-liner)
- Course upsell URL (if exists — can be TBD)
- Friction point (where in the install/use flow users hit a wall → course CTA fires here)
- Conversion goal:
github_star|newsletter|course_purchase
Intake interview (minimum fields)
- Primary goal for this run (1 sentence)
- Target market + geography + language
- Current distribution channels (if any)
- Constraints (brand, compliance, pricing, timelines)
- Proof assets available (case studies, testimonials, numbers)
- Competitors / alternatives you expect
- Access constraints (login walls, demo credentials, repos)
Research kickoff brief (purpose)
- Provide enough context for Validate research agents to run immediately (no waiting on follow-ups)
- Declare unknowns explicitly so research can prioritize answering them
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 · 97 lines · 39 tokens per session scan A f85428bb1bf2
ship-intake-supervisor is a skill published in the GitHub repository maxtechera/ship (2 stars, last pushed 4mo ago), licensed MIT. It adds 39 tokens to every session and 988 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
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…
agent-host-chat-contributions
Build and review cross-cutting agent-host chat behavior through lifecycle contributions. Use when adding turn lifecycle side effects, prompt or context injection, restored-history transformation, protocol-action observation, or when reviewing changes that add code to AgentSideEffects or AgentService.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.