Agenting Check — Development skill for Claude Code
Verify agent routing is wired up and actually working (end-to-end, not config-reading).
How to install Agenting Check
Installs to ~/.claude/skills/furkanzt-claude-agenting-agenting-check/SKILL.md
mkdir -p ~/.claude/skills/furkanzt-claude-agenting-agenting-check && curl -fsSL https://raw.githubusercontent.com/furkanzt/claude-agenting/HEAD/commands/agenting-check.md -o ~/.claude/skills/furkanzt-claude-agenting-agenting-check/SKILL.md Restart Claude Code, or start a new session, for it to be picked up.
What Agenting Check does
allowed-tools: Bash(python3:*) description: Verify agent routing is wired up and actually working (end-to-end, not config-reading)
Health check output
!`python3 "${CLAUDE_PLUGIN_ROOT}/scripts/check-setup.py" 2>&1 || true`
Your task
Report the result above to the user, concisely.
- If everything passed, say so in one line with the counts. Do not restate every check.
- If anything FAILED, explain what is broken and what to do about it. A failing guard check means workflows are
Alternatives in Development
- Check 1: Cache Exists? — CLAUDE_DIR="${CLAUDE_CONFIG_DIR:-$HOME/.claude}" CACHE_EXISTS=$(ls -d "$CLAUDE_DIR/plugins/cache/claude-hud" 2 10.9k ★
- Octo Doctor — Environment diagnostics — check providers, auth, config, hooks, scheduler, and more 2.8k ★
- Tentacle Context Init — You are working on the {{tentacleName}} section 1.4k ★
Full documentation available on GitHub
View Source RepositoryRelated Skills
Apply Airtight
Take this docs template to the current repo. Research it (including what is actually wired), plan the docs lay
Bar Doctor
Live health check — is BAR Observatory's recorder actually working, and what did it capture?
New Widget
Scaffold a new EA widget end-to-end via the new-widget skill — PHP class, SCSS, optional JS, config.php, build
Pcb New
Start a new PCB project from a text description. Sources parts, generates a wired .kicad_pcb, and hands off to
Bootstrap New Project
Guided walkthrough to spin up a new project with Power Pack governance pre-wired. Eliminates the onboarding cl
Tripwire
Run the Playbook §6 Tripwire — verify every plan deliverable is BUILT + WIRED-IN + ACTIVATED + EXERCISED, prov
Related Agents
Akinator Librarian
Use at the end of every batch, before it is called done, to verify the knowledge delta. Reviews taxonomy routi
Aid Test Agent
Autonomously exercises the AID methodology end to end (Phases 0-5) and reports where it breaks. Use for /aid-t
Deploy Smoke Test
Deploy an IRIS interop production and smoke-test it end-to-end — start the production, feed a sample input, th