Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/XyDisorder/shipjawnpx agentmods add skills/xydisorder/shipjaw/shipjaw-askWrote 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-ask)<a href="https://agentmods.dev/skills/xydisorder/shipjaw/shipjaw-ask"><img src="https://agentmods.dev/badge/skills/xydisorder/shipjaw/shipjaw-ask/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-ask"><img src="https://agentmods.dev/badge/skills/xydisorder/shipjaw/shipjaw-ask.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 | $0.00000 | $0.02804 |
| Opus 5 | $0.00000 | $0.01402 |
| Sonnet 5 | $0.00000 | $0.00561 |
| Haiku 4.5 | $0.00000 | $0.00280 |
Grade A, and why
shipjaw-ask 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 — 197 lines — stays where its author put it; the contents beside it link to each section on GitHub.
shipjaw-ask
Continuation-only. Do not reload bootstrap discovery/architecture or
the full shipjaw-build SKILL body. Trust project tooling + docs.
Challenge plans/choices (built-in — not slash-only)
Agents must challenge non-trivial plans and choices in this session
(prefer a separate Task/subagent as Challenger). Do not wait for the
user to type /shipjaw-challenge.
Before coding a new phase, new auth/persistence, primary UI, money/
authz, or any ADR/stack fork not forced by tech-choices.md:
- Ensure the phase (or ADR) exists.
- Built-in pass: Proposer ≤8 bullets → Challenger attacks (5 axes: product / business / tech / pragmatism / design). Prefer subagent; else same-session hard role flip. ≥1 Change/Defer or “no alternative + why”. No rubber-stamp.
- Apply plan edits; note pass in the phase Challenge section
(
built-in <date>is enough unless escalating). - Only then implement.
Escalate to /shipjaw-challenge when the user asks, the plan stays
unstable, or you want a durable challenge-report.md. Detail:
../shipjaw-build/references/challenge-built-in.md (open only if unsure).
Skip only for tiny fixes inside an already-challenged phase (cite prior).
Binding defaults (do not open principles unless conflict)
- State lives in committed
documentation/— update before done. - Progressive disclosure — INDEX → handoff.md → ≤2 files; Grep + offset reads.
- Project owns conventions after bootstrap (tsconfig/eslint/CI/docs).
- Core User can… first; no Out-of-v1 / drive-by scope.
- Types / consts / helpers by ownership (
domain/application/features/<f>/lib) — no grab-baglib/utils.ts. - Ports in
application/ports/; wire incomposition.ts; actions stay thin (validate → use-case → map errors). - Bug ⇒ failing-then-passing regression test; never weaken tests to green.
- Gate once; stop after 2 failed fix attempts; ask the human.
- End every run by overwriting
documentation/handoff.md(template../shipjaw-build/templates/handoff.md) with next slash command. - On doc↔code drift, stop and resolve (see below) — don’t invent.
- Challenge non-trivial plans/choices in-session (prefer
Task/subagent);
/shipjaw-challengeonly for full report / escalate. - Stamp lag: if
scaffolded-with/adopted-withis behind the installedshipjaw-build/VERSION, tell the user once and prefer/shipjaw-upgradebefore heavy product work (unless they insist on the feature now). Run../shipjaw-build/scripts/changelog-since-stamp.sh <root>when explaining what changed. - Session-size budget (no agent can trigger
/compactitself — saying it early is the only lever): a request needing more than one phase is not one session — finish the current phase (gate + docs + handoff), then suggest/compact/fresh chat before starting the next phase, even if nothing failed. Chasing a non-gate bug past ~6 file reads without root cause → same reminder, before going deeper.
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 Changed 174dd554364a
- 10d ago First seen · 197 lines · 0 tokens per session scan A 899c4a33f085
shipjaw-ask is a skill published in the GitHub repository XyDisorder/shipjaw (2 stars, last pushed 3d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 2,804 tokens. 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
react-best-practices
React development guidelines with hooks, component patterns, state management, and performance optimization.
vercel-deploy
Deploy applications to Vercel with edge functions, serverless, and ISR.
agents-md
Generate and safely maintain an AGENTS.md file (the cross-tool standard for guiding AI coding agents, backed by the Linux Foundation's Agentic AI Foundation and read natively by Codex, Cursor, Copilot, Gemini CLI, Aider, Windsurf, Zed, and more). Use this skill when the user wants to document a repo for AI agents…
skillcraft
Skill "skillcraft" from cloudroad-io/skillcraft, covering skillcraft, install, or: pip install skillcraft, commands and how it works.
debugging-loop
Systematic reproduce-isolate-fix-verify loop for bugs, test failures, and unexpected behavior. Use when something is broken and the cause is not yet known.
implementation-loop
Disciplined plan-build-verify loop for implementing a feature or change. Use when building something new or modifying existing behavior, especially across multiple files.