Reverse Engineer MCP server

agent-skills

An opinionated development method for coding agents: every change starts as an approved Linear issue, ships test-first, passes an independent review, and reaches a pull request only when you say so.

The method is a set of skills that call each other. Next to it, the collection offers standalone skills for engineering, web, and game work that you can install one at a time. These are independent, community-maintained skills, not official vendor products.

The method · How it works · Get started · Choose by task · Requirements · All skills · Contribute

The method

Agents fail in predictable ways: they build before the decision is made, ask you what the repository already says, grade their own work, and publish without asking. The method answers each failure with a rule.

and becomes a Linear issue. implement refuses to work without one.

• No issue, no code. Every request, even a small one, goes through triage

repository, Linear, and the documentation before asking you anything. You answer only choices that change scope, acceptance, or structure.

• Facts are looked up; only decisions are asked. The agent reads the

Research or Prototype issue first, then an Interview issue that settles the decision with that evidence.

• Decide before building. When a decision needs evidence, triage plans a

boundary exists.

• Tests first. Each behavior starts with a failing test wherever a test

standards, and correctness. Agreement between agents is not proof; the implementing agent verifies every finding.

• Evidence over claims. Independent read-only reviewers check requirements,

deploying each wait for your explicit approval.

• You hold the keys. Publishing issues, opening a pull request, merging, and

verification, Git conventions, code comments) live once in a shared operating policy. Skills hold only what is specific to their task.

• One policy, focused skills. General rules (authorization, delegation,

How it works

flowchart LR
    request([Your request]) --> triage
    triage <-->|open decisions| interview
    triage -->|after your approval| issue[(Linear issue)]
    issue --> implement
    implement -->|by issue type| route{{"debug · prototype<br/>research · interview"}}
    implement --> review[code-review]
    review --> pr([Pull request you approve])
    implement -.->|Need triage| triage

triage finds existing work, picks the issue type, settles open decisions through interview, and publishes the issues in Todo once you approve the drafts. implement then runs one issue at a time and routes it by type:

Work that would change an issue's outcome or scope goes back to triage with the Need triage label instead of growing inside the current issue. improve-architecture feeds the same loop: it publishes approved refactors as Task issues ready for implement.

Get started

You need a coding agent that supports skills and subagents, Node.js and npm for the installer, and a Linear workspace your agent can reach.

Shortened. The full README is on GitHub.