Claimcheck Agents — Development skill for Claude Code
List the coding agents claimcheck can measure, and what has actually been verified.
How to install Claimcheck Agents
Installs to ~/.claude/skills/pawankumar94-claimcheck-claimcheck-agents/SKILL.md
mkdir -p ~/.claude/skills/pawankumar94-claimcheck-claimcheck-agents && curl -fsSL https://raw.githubusercontent.com/pawankumar94/claimcheck/HEAD/commands/claimcheck-agents.md -o ~/.claude/skills/pawankumar94-claimcheck-claimcheck-agents/SKILL.md Restart Claude Code, or start a new session, for it to be picked up.
What Claimcheck Agents does
description: List the coding agents claimcheck can measure, and what has actually been verified
Show the user which agents claimcheck can drive.
Call the `list_agent_profiles` MCP tool.
Present a compact table: agent name, the CLI command it drives, the policies it defines, and whether it is verified.
For any profile where `verified` is false, say what is unverified — quote the `verificationNote`. An unverified profile can still run, but a failure may be a wrong CLI
Alternatives in Development
- Skill Creator — Create new skills, modify existing skills, and measure skill performance 94.1k ★
- Domxss — Confirm DOM XSS in a real headless browser — injects canary payloads into params + URL fragment and only repor 4.5k ★
- Fidelity — Measure how faithfully a clone reproduces a site — pixel-diff plus motion-fidelity into one 0-100 score, a let 3.6k ★
Full documentation available on GitHub
View Source RepositoryRelated Skills
How They Built It
You saw a screen you liked. Measure how it was actually built — asset types, motion timing, gradient structure
Token Consumer
Measure and shrink the token cost of Claude Code skills, tier by tier: the always-on system-prompt tax, the pe
Benchmark Rerankers
Measure whether adding a reranker actually improves retrieval, by scoring reranked vs. un-reranked results on
Skill Usage Counter
Measure which Claude Code/Codex skills you actually invoke. Hook + backfill + report; privacy-safe.
Cross Session Reachability
Empirically verified capability matrix for Claude Code's cross-session/cloud primitives (SendMessage, ListAgen
Asolaria Civilisation Scoreboard
The orchestrators ledger. Measures what each agent actually did on the shared matrix: ticks spent, cells grown
Related Agents
Red First Verifier
Independently PROVE a regression/feature test actually fails without the fix. Use after writing a test-for-a-b
Claude Md Writer
Writes or updates a CLAUDE.md that actually helps agents work in this repo. Verified commands, conventions, go
Kb Synthesist
Combine several single-tool gap analyses into one cross-tool comparison and a consolidated capability gap list