The orchestration layer that turns Claude Code, OpenCode, and other AI coding CLIs into autonomous engineers — driving real work from task intake to merged pull request, with humans in the loop only where it counts. Swappable plugins for any trigger, chat, agent, or git host.
This repository also configures its own agents. See what the-engineer tells them →
Skill Claude Code
Assess a run of The Engineer on this machine — investigate what its daemon actually did on a task and judge how well it did it, end to end, to find what to improve in The Engineer itself. Reads the run's own artifacts (the /.engineer SQLite store, traces, journals), the commits, and the PR. Use this whenever the user…
Skill Claude Code
Analyze code changes, group them into logical packages where appropriate, to create sequential, clear, descriptive commits with effective titles and detailed descriptions.
Skill Claude Code
Synthesizes requirements and research into robust implementation plans through structured decision-making and expert panel stress-testing. Calibrates process depth to risk level — low stakes get a light plan, full stakes get hard decision gates and a pre-mortem. The plan is a decision record with actionable tasks, not…
Skill Claude Code
Run code, architecture, systems, or proposed changes through a panel of world-class engineering perspectives. Each panelist reads the ACTUAL source files before judging. Use this skill whenever the user asks to: review code quality, get expert opinions, assess architecture decisions, evaluate a refactor plan, critique…
Skill Claude Code
Executes an approved plan by ALWAYS orchestrating the build through focused agent workflows, then taking the role of orchestrator and co-owner to independently verify every change, hunt gaps, and fix whatever was missed until the work is fully home — no gaps, bugs, or loose ends. This is the "I" (Implement) of RRPIR…
Skill Claude Code
Perform end-to-end investigation, analysis, and comparative review of an external open-source project against The Engineer. Use this skill whenever the user wants to analyze, investigate, review, or compare an external project, GitHub repository, or open-source tool. Also trigger when the user mentions adding to…
Skill Claude Code
Conducts structured requirements gathering through sequential questioning before any research, planning, or implementation begins. Extracts true intent, constraints, edge cases, unknowns, and acceptance criteria from the user through focused one-at-a-time questions. Use this skill whenever the user mentions a new…
Skill Claude Code
Investigates codebases with a facts-before-opinions discipline — building a complete factual picture before interpreting what it means for the work ahead. Produces a structured research document saved to disk, split into observations and implications. Use when you need to understand existing code, patterns…
Skill Claude Code
Conducts post-implementation review covering test coverage, lint, type checks, test fixes, and local testing preparation. Runs all automated verification, identifies gaps, fixes issues, and presents a testing checklist so the user can verify the work manually. Use this skill after implementation and commits are done …
Skill Claude Code
Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.
Skill Claude Code
Deep architectural investigation that extracts, documents, and maps every system in a codebase. Use this skill whenever the user asks to: extract layers, map systems, analyze architecture, investigate codebase structure, document system boundaries, create a system map, understand how systems relate, audit…
Skill Claude Code
Take on a substantial, multi-step effort as a strategic orchestrator — intake the goal, research and plan it solo, execute it through parallel/sequential agent workflows, then personally verify the result end to end. Use this whenever the user wants to tackle something big or ambitious: a large feature, a…
Skill Claude Code
Wrap up the current session by updating active.md, logging the session, committing, and providing the next session's starter prompt. Use at the end of every working session.
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: