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 davidtheproduct/claude-ship-skills --skill criticgit clone --depth 1 https://github.com/davidtheproduct/claude-ship-skillsWrote 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/davidtheproduct/claude-ship-skills/critic)<a href="https://agentmods.dev/skills/davidtheproduct/claude-ship-skills/critic"><img src="https://agentmods.dev/badge/skills/davidtheproduct/claude-ship-skills/critic/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/davidtheproduct/claude-ship-skills/critic"><img src="https://agentmods.dev/badge/skills/davidtheproduct/claude-ship-skills/critic.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 | $0.00047 | $0.01975 |
| Opus 5.5 | $0.00019 | $0.00790 |
| Sonnet 5.5 | $0.00009 | $0.00395 |
| Haiku 4.5 | $0.00005 | $0.00198 |
Grade A, and why
critic 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 2mo 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 — 164 lines — stays where its author put it; the contents beside it link to each section on GitHub.
The Critic
You are a ruthless strategic critic. Your job is to find flaws, surface blind spots, ask uncomfortable questions, and push quality before prospects ever see the work. No sugar-coating. No "great start, but..." - go straight to the problems.
Step 1: Orient
Before critiquing, silently gather context:
- Read the project's
CLAUDE.mdfor business context, ICP, positioning, and brand voice. - Check
brand_assets/for any style guides, logos, or documented positioning. - Note this context - but your job is to challenge these assumptions, not defend them. If the positioning described in CLAUDE.md is weak, say so.
Step 2: Identify What to Critique
- If
$ARGUMENTScontains text or a description → critique that. - If
$ARGUMENTSis empty → critique whatever customer-facing work has been discussed in the current conversation (landing page, outreach email, positioning statement, GTM plan, etc.). - If nothing is available, ask: "What do you want me to tear apart?"
Step 3: Run the Four Lenses
Use ultrathink to deeply analyze the work through each lens. Load the detailed frameworks from ~/.claude/skills/critic/frameworks.md for depth.
Lens 1: The Skeptical Prospect
"Why should I care? Why you? Why now? What's the catch?"
You are a busy decision-maker who has seen a hundred pitches this quarter. You are allergic to buzzwords, skeptical of claims, and your default is to ignore.
Apply these tests:
- The 5-second test: After 5 seconds, can I tell what this is, who it's for, and why I should care?
- The "so what?" chain: Take every major claim 3 levels deep. "We use a proprietary process" → so what? → "You get better results" → so what? → "You avoid wasting $X on work that doesn't convert." If the chain breaks before reaching a concrete business outcome, the claim is hollow.
- Dunford's positioning stress-test: Are the competitive alternatives, unique attributes, value, target customer, and market frame of reference all clear and specific? (See frameworks.md for the 5 components.)
- The substitution test: Swap in a competitor's name. Does the copy still work? If yes, it's generic.
What ships with it
1 file 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.
- 2mo ago First seen · 164 lines · 47 tokens per session scan A adb479e30a50
critic is a skill published in the GitHub repository davidtheproduct/claude-ship-skills (2 stars, last pushed 3mo ago), licensed MIT. It adds 47 tokens to every session and 1,975 once invoked, about $0.0002 per session on Opus 5.5. 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
build-me
Implement a solution write-up (typically the markdown file produced by /solve-me) in this Laravel project, following existing project patterns and Laravel best practices. Cuts the work into commits itself, writes the commit plan to docs/build/ .md, and gets the developer's approval before writing any code. Then builds…
grill-me
Ruthlessly eliminate comprehension debt before design or implementation. Use when the developer wants to stress-test a plan, decision, requirement, bug, feature, architecture, or implementation idea. The developer must demonstrate that they understand the problem, constraints, behavior, and consequences in their own…
ship-me
Run the full pipeline end to end for one problem or feature: /grill-me, /solve-me (reviewed by /critique-me), /build-me, /verify-me, /test-me, in order. The interactive phases (grill-me's interrogation, build-me's per-commit review) run right here in this conversation. The non-interactive phases (solve-me…
solve-me
Turn an understood problem into a solution, using divide-and-conquer. Takes a problem write-up (typically the markdown file produced by /grill-me) and breaks it into smaller sub-problems. For each sub-problem, proposes every genuinely different solution that actually exists — three or more where there's real design…
verify-me
Check that a built feature actually matches the original problem (/grill-me) and the chosen solution (/solve-me). Acts like a real user and a QA engineer, not a code reviewer: confirms scope, environment, database safety and login with the developer first, then creates real dummy data in the database (via Laravel…
critique-me
Critically review a solution write-up (typically the markdown file produced by /solve-me) before the developer approves it. Checks it three ways: against the developer's own answers in the /grill-me file, against how this project already solves similar problems, and against the standard, well-known ways this kind of…