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-challengegit 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-challenge)<a href="https://agentmods.dev/skills/xydisorder/shipjaw/shipjaw-challenge"><img src="https://agentmods.dev/badge/skills/xydisorder/shipjaw/shipjaw-challenge/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-challenge"><img src="https://agentmods.dev/badge/skills/xydisorder/shipjaw/shipjaw-challenge.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 | $0.00129 | $0.01075 |
| Opus 5 | $0.00064 | $0.00537 |
| Sonnet 5 | $0.00026 | $0.00215 |
| Haiku 4.5 | $0.00013 | $0.00108 |
Grade A, and why
shipjaw-challenge 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 3d 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.
shipjaw-challenge
Full challenge ritual only (durable report + lock). Everyday plan/
choice pushback is built-in in shipjaw-ask / shipjaw-build —
see ../shipjaw-build/references/challenge-built-in.md. This slash skill
escalates that into a repo artifact. Does not scaffold or implement.
Axes (score each Keep / Change / Defer + one sharp reason):
- Product — is the User can… the real core? Out of v1 ruthless enough?
- Business — value vs effort; what proves it worked?
- Tech — simpler option? clean-arch / ports / debt tradeoff sound?
- Pragmatism — shippable this phase? fallback if blocked?
- Design — fit
design-brief+design-constraints.md(not AI chrome)?
References (on demand):
../shipjaw-build/references/challenge-built-in.md ·
../shipjaw-build/references/design-constraints.md ·
../shipjaw-build/profiles/typescript-next/tech-choices.md ·
../shipjaw-build/profiles/typescript-next/project-structure.md ·
../shipjaw-build/templates/challenge-report.md
Anti-triggers
- No target plan/ADR/phase → ask once what to challenge, or stop
- One-line CSS/copy → refuse
- User wants code now with no plan →
shipjaw-ask/shipjaw-build(those skills still run built-in challenge first) - Complete rubber-stamp (“looks good”) with no Change/Defer and no rejected alternative → invalid; force at least one substantive pushback or an explicit “no viable alternative; here’s why”
Dual-agent protocol (mandatory)
Role A — Proposer (current session)
- Point at the artifact: phase file, ADR in
decisions.md, or a short pasted plan. If missing, draft a minimal phase from the template first (still do not implement). - State in ≤8 bullets: goal, User can…, stack/approach, out of scope, risks.
Role B — Challenger (separate mind)
Prefer a real second agent when the host allows it (Cursor Task /
subagent, or a second chat with only the plan + INDEX + this skill).
Prompt the challenger with:
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.
- 3d ago Changed dc0d693c9c5b
- 11d ago First seen · 97 lines · 129 tokens per session scan A f2baffe0d200
shipjaw-challenge is a skill published in the GitHub repository XyDisorder/shipjaw (2 stars, last pushed 3d ago), licensed MIT. It adds 129 tokens to every session and 1,075 once invoked, about $0.0006 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
gentle-ai-collab-perfect
Trigger: contributing to Gentleman-Programming/gentle-ai as an external collaborator. Strict issue-first workflow, honest PR bodies, contributor-vs-maintainer scope, chained-PR strategy, verification protocol, docstring coverage. Load whenever the active repo is Gentleman-Programming/gentle-ai and any part of the…
issue-creation
Trigger: issue creation, bug reports, feature requests, or issue approval. Create and triage GitHub issues from repository evidence.
sdd-tasks
Break an SDD change into implementation tasks. Trigger: orchestrator launches task planning for a change.
sdd-verify
Skill "sdd-verify" from Gentleman-Programming/gentle-ai, covering execution role, language domain contract, activation contract, hard rules and decision gates.
branch-pr
Create Gentle AI pull requests with issue-first checks. Trigger: creating, opening, or preparing PRs for review.
work-unit-commits
Plan commits as reviewable work units. Trigger: implementation, commit splitting, chained PRs, or keeping tests and docs with code.