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 XyDisorder/shipjaw --skill shipjaw-promptgit clone --depth 1 https://github.com/XyDisorder/shipjawWrote 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/xydisorder/shipjaw/shipjaw-prompt)<a href="https://agentmods.dev/skills/xydisorder/shipjaw/shipjaw-prompt"><img src="https://agentmods.dev/badge/skills/xydisorder/shipjaw/shipjaw-prompt/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/xydisorder/shipjaw/shipjaw-prompt"><img src="https://agentmods.dev/badge/skills/xydisorder/shipjaw/shipjaw-prompt.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 | $0.00147 | $0.00877 |
| Opus 5 | $0.00073 | $0.00439 |
| Sonnet 5 | $0.00029 | $0.00175 |
| Haiku 4.5 | $0.00015 | $0.00088 |
Grade A, and why
shipjaw-prompt 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 12d 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 — 72 lines — stays where its author put it; the contents beside it link to each section on GitHub.
shipjaw-prompt
Expression only. Takes messy notes / a vague idea and produces a
build-ready product prompt that shipjaw-build can consume with
almost no rediscovery. Does not scaffold an app, does not create
documentation/knowledge-base/.
Anti-triggers
documentation/knowledge-base/exists →shipjaw-ask(product already bootstrapped)- User already has a polished prompt and wants code now →
shipjaw-build - Pure CSS/copy tweak / non-TypeScript → refuse
Checklist
- [ ] Intake raw idea
- [ ] Clarify gaps only (≤2 rounds / ~8 Q); default the rest
- [ ] Craft dense prompt (references/prompt-craft.md)
- [ ] Scope trim gate (references/prompt-craft.md): Core action has no
personalization/adaptation clause; every v1 scope bullet must break
the core action if cut; no Success criterion chains multiple
features into one end-to-end checkbox — trim now, don't hedge in a
note
- [ ] Write documentation/product/source-prompt.md (never KB)
- [ ] Write documentation/handoff.md → next /shipjaw-build
- [ ] Hand off: /shipjaw-build
Workflow
- Intake — read the user's raw expression (any language, any mess).
- Clarify only gaps — max 2 rounds / ~8 questions total. Prefer
structured host questions (
AskUserQuestion/AskQuestion) else numbered chat. Use../shipjaw-build/references/discovery-questions.mdas the question bank; skip anything already answered. Then default and record defaults inside the prompt. - Craft the prompt — follow
references/prompt-craft.md, including its mandatory scope trim gate (Core action, v1 scope, and Success criteria all checked for smuggled-in scope). Output must be dense, unambiguous, and sufficient forshipjaw-buildstep 1–3. - Persist — write
documentation/product/source-prompt.mdfromtemplates/source-prompt.md(createdocumentation/product/only — never createknowledge-base/here). Overwrite only if the user confirms when a source-prompt already exists. - Hand off — show the final prompt in chat and tell the user to run
/shipjaw-build(no args if the file exists, or paste the prompt).
What ships with it
2 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.
- 12d ago First seen · 72 lines · 147 tokens per session scan A daa8cf6fe393
shipjaw-prompt is a skill published in the GitHub repository XyDisorder/shipjaw (2 stars, last pushed 4d ago), licensed MIT. It adds 147 tokens to every session and 877 once invoked, about $0.0007 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
coding-agents-prompt-authoring
To author, adapt, review, and validate prompts (skills, agents, workflows, rules, etc.) with brief, contracts, and a validation pack.
LLM Extraction & KG Construction
Core inference logic, prompt construction, and RDF/Nanopublication serialization.
ai-evaluation-engineering
An AI evaluation engineering specialist for testing models and prompts. The description does not provide enough detail to state which concrete operations it performs.
prompt-pilot
Rewrite a rough, vague prompt into a precise, context-enriched prompt. Explores the codebase read-only and weaves real file paths and symbols into the rewritten prompt — never implements the task itself. Use when the user asks to optimize, enrich, or improve a prompt before running it.
cursor-langchain
Cursor IDE rules for langchain.
ultra-max-token-burner
Expand concise requests into larger, coherent, manager-visible prompts using controlled procedural overhead.