thermite
01Plugin Claude Code
AI driven solutions that nearly always mostly work.
Plugin Claude Code
AI driven solutions that nearly always mostly work.
Plugin Claude Code
Autonomous AI development skills, agents, and hooks for Claude Code.
Instructions file
Instructions for thermiteau/maverick, covering claude.md, project overview, build & run commands, install dependencies and run cli from source.
Agent
Autonomous code reviewer that performs two-stage review — spec compliance first, then code quality (correctness, test coverage, maintainability). Security is out of scope; do-cybersecurity-review handles that as a mandatory pre-push gate. Dispatched after completing implementation steps or before creating PRs.
Agent
Takes a solution design and produces an ordered task list. Dispatched by do-issue-solo and do-issue-guided as a subagent so that planning does not consume the caller's context window.
Agent
Reads a GitHub issue, explores the codebase, and produces a solution design. Dispatched by do-issue-solo and do-issue-guided as a subagent so that codebase exploration does not consume the caller's context window.
Agent
Reviews Claude Code session activity and git diffs to identify missed opportunities, duplicated code, and quality issues.
Agent
Autonomous technical documentation writer. Dispatched when documentation needs to be created or updated — architecture, services, data flows, design decisions, or technology choices. Produces professional markdown with Mermaid diagrams.
Hook
Runs when a session starts, executing install_check.py via python3. From thermiteau/maverick.
Hook
Runs before the agent uses a tool for Bash, Edit, Write, NotebookEdit, WebFetch and Skill tool calls, executing scope_guard.py and subagent_report.py via python3 (2 commands). From thermiteau/maverick.
Hook
Runs when a subagent starts, executing subagent_report.py via python3. From thermiteau/maverick.
Hook
Runs when a subagent finishes, executing subagent_report.py via python3. From thermiteau/maverick.
Hook
Runs when a session ends, executing session_release.py via python3. From thermiteau/maverick.
Skill Claude CodeCodex
Scan a project for missing best-practice areas and implement the top recommendation for each gap (linting, unit testing) — installs tools, writes configs, verifies, and commits. Pass 'recommend' to stop after writing recommendations without implementing (replaces the old do-recommend skill).
Skill Claude CodeCodex
Implement a focused code change. Use this skill as the wrapper for any implementation work so the Maverick workflow report captures what was done and so the agent applies the project's coding standards before editing. Intended to be invoked once per task from inside a do-issue- or do-epic phase, not standalone.
Skill Claude CodeCodex
Audit a codebase for security risks in one of two modes. In full-audit mode it scans the entire codebase and writes a findings report to docs/security-audit.md (run as part of do-init or on demand). In update mode it reviews only a diff plus the code it could impact, returning a structured findings list as a pre-push…
Skill Claude CodeCodex
Create, restructure, or update technical documentation. Handles greenfield projects, refactoring non-compliant docs, and incremental updates after code changes.
Skill Claude CodeCodex
Work on a multi-story GitHub epic end-to-end. Builds a DAG from the child stories, groups them into waves, runs waves in parallel via per-story worktrees, ejects PRs that fail agent-code-review for human handling, and propagates blocks to downstream stories. Requires git worktrees.
Skill Claude CodeCodex
Initialise a project for use with Maverick — verifies the GitHub App, installs the CLI if needed, writes the project config with integration tracking, scaffolds docs, generates project skills, runs an initial cybersecurity audit, then commits the changes and opens a PR.
Skill Claude CodeCodex
Install the maverick CLI tool system-wide from the plugin directory.
Skill Claude CodeCodex
Work on a GitHub issue interactively with the user. Proceeds autonomously through routine work but pauses for confirmation at key decision points and when uncertain.
Skill Claude CodeCodex
Work on a GitHub issue end-to-end autonomously, only pausing when blocked or when clarification is needed.
Skill Claude CodeCodex
Analyze a project's codebase against Maverick standard practices and write a findings report. Checks linting, unit tests, integration tests, documentation, CI/CD, security, dependency management, observability, source control, and more. Run when onboarding an existing project or on demand.
Skill Claude CodeCodex
How to process code review feedback — verify before implementing, push back when wrong, clarify before acting on partial understanding. Applied when receiving review from the agent-code-reviewer or human reviewers.