devkit

Unified project health audit — dependencies, vulnerabilities, outdated packages, licenses, lint, and security in one report.

Full lifecycle bug fix — reproduce, diagnose, fix, regression test, verify.

Decompose a high-level goal into a task DAG — break down, assign to agents, resolve dependencies, execute in order.

ACH-enhanced deep research — perspective discovery, competing hypotheses, directed disconfirmation, evidence matrix, sensitivity analysis.

Full lifecycle feature development — brainstorm, plan, implement, test, lint, review.

Post-PR review monitor — watches CI, fetches reviewer comments, iteratively resolves them, and pushes fixes.

Full PR preparation pipeline — necessity check, DRY review, lint, test, security, changelog, and create PR.

Full lifecycle refactor — analyze code smells, plan transformations, restructure, verify nothing broke.

Build an AST-based symbol index of the repository — exports, functions, classes, imports — cached for fast agent navigation.

Automated self-audit — measure the codebase, rank improvement hypotheses by evidence, present actionable plan. Inspired by karpathy/autoresearch.

Self-recursive improvement loop — automated refactoring with test gate. Uses native improver agent in worktree isolation. Propose → measure → keep/discard → repeat.

Self-improvement loop targeting lint and type errors. Iteratively fixes issues until zero remain or iterations exhausted.

Self-improvement loop for incremental codebase migrations. Iteratively migrates code with tests as the safety gate.

Hypothesis-driven performance investigation — analyze, hypothesize, test one theory at a time, measure against baseline.

Self-improvement loop targeting test coverage. Iteratively generates and improves tests until a coverage target is met or iterations exhausted.

Check devkit health — which external CLIs are installed, which agents are available, and which commands are ready to use.

Multi-agent debugging — send a bug report to available agents (Claude + Codex + Gemini) via plugin or CLI, get independent root-cause hypotheses, and a consensus fix.

Dispatch a task to all three agents (Claude, Codex, Gemini) in parallel and compare results. Claude uses native background agent, others via plugin or CLI.

Triple-agent PR/code review. Claude runs as native background agent (token-efficient), Codex and Gemini via plugin or CLI. Consolidates findings.

Multi-agent security audit — independent security reviews from available agents, consolidated with severity-ranked findings.

Multi-agent test generation — each available agent generates tests independently, then merge for maximum coverage.

Run a user-defined YAML workflow. Multi-step pipelines with loops, approval gates, and branching.

Generate a structured changelog from git history — use when asked to create a changelog, release notes, or summarize what changed between versions/tags/branches.

Clean code principles — meaningful names, small functions, single responsibility, stepdown rule, flat nesting.

How to create devkit workflow YAML files — schema reference, step types, variable interpolation, and examples.

Deep research with Analysis of Competing Hypotheses — use when asked to do deep research, deeply investigate, validate claims, or when correctness is critical and the user wants rigorous analysis with disconfirmation testing.

Generate documentation for code — use when asked to document a module, generate API docs, create a README for code, or write reference documentation.

Don't reinvent the wheel — use existing libraries, tools, and stdlib before building custom solutions. Every custom solution is maintenance burden.

Don't Repeat Yourself — Rule of Three, when duplication is fine, extracting the right abstraction.

Execute implementation plans — work through steps methodically, verify each one, keep changes small and reviewable.

Google Workspace CLI (Gmail, Calendar, Drive) via gcli — use --for-ai flag for token-efficient structured output.

Generate a codebase onboarding guide — use when asked to explain this codebase, help understand the architecture, give a tour of the repo, or onboard a new contributor.

Research workflow — use when asked to research a topic, investigate options, compare approaches, or find the best solution to a technical question. NOT for "deep research" or "validate" requests — those go to deep-research. For complex or high-stakes questions where correctness is critical, use deep-research instead.

Scrape a URL to clean Markdown — use when asked to scrape, fetch, extract content from, or read a webpage and convert it to Markdown. Uses Jina Reader, Firecrawl, or WebFetch.

Persistent iteration memory — prevents Groundhog Day loops by recording what was tried, what failed, and what to try next.

Detect when an agent is looping or failing repeatedly, and trigger structured recovery — backtrack, simplify, or escalate.

Generate tests for code — use when asked to write tests, create a test suite, add test coverage, or generate unit/integration tests for a file or module.

You Aren't Gonna Need It — build only what's needed now, no speculative features or premature abstractions.

12 hooks across 4 events