bot

Runs a dogfood cycle against plugin-bot — tasks the plugin-engineer agent with building a plugin capability inside the plugins/dogfood sandbox, validates and reloads it, evaluates the result (skill-creator evals for skills, fixtures/BATS for hooks), and harvests rough edges in plugin-bot's own skills and agent as improvement notes. Use after changing plugin-bot to exercise it end to end.

Enforces subagent frontmatter and system-prompt conventions when a `<name>.md` agent file is opened for authoring or review — plugin-scope ignored fields, description quality, tool-restriction shape, skills preload, and the required boundaries section.

Distilled, verification-stamped reference for the official Claude Code platform contract — plugins, skills, subagents, hooks, MCP, tools, env vars and channels. Use when authoring or auditing any Claude Code plugin component, looking up a frontmatter field, hook event schema, manifest rule, permission-rule format or tool name, or whenever a platform claim needs verifying instead of recalling from memory.

Enforces the house hook-script contract when a `hooks/**/*.sh`, `hooks/**/*.bash`, or `hooks/hooks.json` file is opened for authoring or review — envelope/exit-code/JSON discipline, subdirectory-per-event layout, lib helpers, fixtures, and BATS coverage.

Use when authoring, auditing, or registering a Claude Code plugin monitor — a monitors/monitors.json entry or the background watch script it runs. Ships the typed TypeScript poll-monitor harness (self-scheduling loop, stable-streak debounce, notify-once dedup, --once mode) plus the registration rules and notification-copy doctrine; auto-loads as the enforcer when a monitors/ file is opened.

Use when writing or reviewing language meant to shape an agent's behavior — a hook's `additionalContext` payload, a SKILL.md body or description, an agent system prompt, or an enforcer checklist. Covers choosing the imperative force, structuring with XML tags, matching the urgency tier to the moment (the EXTREMELY_IMPORTANT / IMPORTANT / reminder / acceptable-anti-pattern gradient), the persuasion-principles foundation (Cialdini + Meincke), why XML beats markdown for hook injections, and concrete templates for SessionStart, PostToolUse, and PreToolUse nudges.

Enforces manifest well-formedness when `.claude-plugin/plugin.json`, `.claude-plugin/marketplace.json`, `.mcp.json`, or `.lsp.json` is opened for authoring or review — path-substitution rules, the hooks.json separation, and the house version policy.

Use when scaffolding a brand-new Claude Code plugin, retrofitting the house directory layout and hooks/lib helpers into an existing plugin that doesn't yet follow it, or bootstrapping hooks infrastructure (hooks.json registrations, fixtures, BATS coverage) for a plugin that has none. Ships the bootstrap checklist plus the tested hooks/lib/*.sh templates (hook-output.sh, hook-debug.sh, source-session-env.sh, gh-wrapper.sh).

Use when authoring or auditing Claude Code plugin scripts that invoke a third-party CLI like gh, aws, kubectl, docker, or gcloud — tool-canonical env vars in the user's shell silently override the auth, profile, or config the plugin assumed was in effect, and the failure surfaces as wrong-account writes, "not authenticated" false negatives, or commands targeting the wrong cluster, project, or repository

Enforces SKILL.md frontmatter and body conventions when a skill file (or command markdown file) is opened for authoring or review — description quality, user-invocable vs model-invocable choice, archetype fit, progressive disclosure, and the 500-line body cap.

Enforces the house contract for scripts bundled inside a skill's `scripts/` directory when one is opened for authoring or review — canonical project-root resolution, plugin-data persistence, and the dirname-walking anti-pattern.