Honesty — Development skill for Claude Code
Reviews your own report before delivering — separates what was verified from what was assumed, and declares the limit.
How to install Honesty
Installs to ~/.claude/skills/mateusands-claude-code-crew-kit-honesty/SKILL.md
mkdir -p ~/.claude/skills/mateusands-claude-code-crew-kit-honesty && curl -fsSL https://raw.githubusercontent.com/mateusands/claude-code-crew-kit/HEAD/commands/honesty.md -o ~/.claude/skills/mateusands-claude-code-crew-kit-honesty/SKILL.md Restart Claude Code, or start a new session, for it to be picked up.
What Honesty does
description: Reviews your own report before delivering — separates what was verified from what was assumed, and declares the limit.
Before saying "done", rewrite your own report through these filters:
**1. Suite × runtime, kept separate.** Say the two things in different sentences: what the suite covered and what you **exercised by hand**, with what data. Never let "the tests pass" do the job of both. If you did not actually open/run it, **declare that there is no runtime proof**.
**2
Alternatives in Development
- Claude Swap — Switch between multiple Claude Code accounts, with automatic rate-limit rotation, usage dashboard, and paralle 2k ★
- /validate — Run full validation on the current finding before writing a report 927 ★
- Memory Search — Search through Claude's persistent memories for specific content, patterns, or keywords 332 ★
Full documentation available on GitHub
View Source RepositoryRelated Skills
Econ Paper Review Skill
Referee report on your economics paper before a real referee sees it — verified comments and a revision plan y
Professor Ethos
Get expert alignment advice grounded in Claude's Constitution and the Sabotage Risk Report. Ask about honesty
Prompt Injection Benchmark
A reproducible prompt-injection benchmark that measures which defenses actually work: each payload is replayed
Nightmux
Your night crew, on Telegram. Run Claude Code, Codex or any terminal agent from a Telegram topic — one topic p
Claumon
Claude Code dashboard: see where your limits are headed before you hit them. Calibrated usage forecasts, live
Claude Code Usage Quota Mod
Know your Claude limits before they hit you (Live band above the Claude Code prompt): 5 Hour and Weekly usage
Related Agents
Leak Review
Security review of commits by OTHER contributors before they are built — data exfiltration, key material and w
Conventions
Markers: [V] tool-verified; [I] inferred; [A] assumed; [U] unknown.
Hydra Repository Cartographer
Map an unfamiliar repository area and report verified structure, technologies, and conventions. Use for scoped