Selfcheck — AI skill for Claude Code
Run the deterministic config integrity linter that guards the foreman setup against regressions.
How to install Selfcheck
Installs to ~/.claude/skills/eugenezhangco-spec-foreman-selfcheck/SKILL.md
mkdir -p ~/.claude/skills/eugenezhangco-spec-foreman-selfcheck && curl -fsSL https://raw.githubusercontent.com/eugenezhangco-spec/foreman/HEAD/commands/selfcheck.md -o ~/.claude/skills/eugenezhangco-spec-foreman-selfcheck/SKILL.md Restart Claude Code, or start a new session, for it to be picked up.
What Selfcheck does
description: Run the deterministic config integrity linter that guards the foreman setup against regressions. Zero LLM cost.
/selfcheck — Config Integrity Self-Test
Runs the deterministic config linter that guards the foreman setup against regressions. Zero LLM cost.
When to Use
- AUTO: after editing CLAUDE.md, any
.claude/rules/*, hooks,settings.json, oragents/*(the claude-code-config rule reminds you) - When the user says "check yourself", "are you still wired right", "
Alternatives in AI
- Manifest — Real-time cost observability for OpenClaw agents — track tokens, costs, messages, and model usage 4.1k ★
- ClaudeR — Connect RStudio to Claude Code, Codex, Gemini, and other LLM agents via MCP 328 ★
- PRD Taskmaster V2 — Zero-config goal-to-tasks engine 187 ★
Full documentation available on GitHub
View Source RepositoryRelated Skills
UX Lint
Deterministic regex-based linter for AI fingerprints. No LLM, no API, no network. CI-friendly — exits non-zero
Agentbill
Track token usage and dollar cost across Claude Code, Cursor, Codex and other AI coding agents. Zero-config, t
Evolve Skill
SPIKE — GEPA/DSPy-style offline A/B evolution of ONE prompt-only skill's SKILL.md body against a small fixture
Harness Lint
Run the quality lint (advice rules + system-level analysis) on the agent setup; add --all for every one of the
Code Context Control
Local MCP code-intelligence for AI coding tools: surgical search/read/edit, agent-config version history, path
Reflex
Pre-execution risk gate for AI coding agents (Claude Code, Codex, opencode, pi, Hermes). Blocks or asks on ris
Related Agents
Compositor
Invoked for PDF rendering, text-layer setup, and annotation anchoring / coordinate math. Guards against coordi
Code Review Anchored
Anchored code reviewer for canon code_review. Applies Stage 1 AC compliance, Stage 2 quality, and test-integri
Claude Code Currency
Claude Code setup currency expert. Researches the latest official Claude Code config practices (subagents, set