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 | $0.00023 | $0.00988 |
| Sonnet 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 11d 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.
- 11d 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 1mo ago), licensed MIT. It adds 47 tokens to every session and 1,975 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
loop-setup
Session 0. Sets up the loop in this project - detects the stack, checks which connections actually work (git, database, browser, payments sandbox), asks the few decisions only the owner can make, and writes the .loop/ files. Run this once per project, before any planning or building.
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…
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…
loop-plan
The planning session. Turns a goal into an ordered list of thin complete slices, decides which role and model runs each following session, and writes it all to the plan file. Use at the start of an epic, before any code.
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…