Skip to content

Repository files navigation

Team-Ops

A compiler for AI dev teams. Point it at a repository; it reads the actual code, asks a short interview, and generates a small, project-specific team of review agents — in the native format of whatever AI tool you use (Claude Code, Codex, Gemini CLI, Cursor) — plus deterministic verification hooks that enforce the checkable part of each agent's checklist.

It runs once and exits. It is not a persistent chatbot team. It produces files.

status: experimental version: 0.1.0 license: MIT platforms

Status: experimental (v0.1.0). Interfaces and output formats will change. Treat generated agents as a strong first draft to review, not gospel — and always read generated hook scripts before enabling them (see SECURITY.md).

Why this exists

Static agent libraries give everyone the same "Security Engineer" whether they're building a landing page or a telehealth app. Team-Ops generates a Security agent that names your payment integration and your auth middleware — or doesn't include one at all if your project has no reason for it.

The one rule the generator lives by: if a generated line could apply to any project, it's deleted. A shipped eval set (evals/) and a mechanical specificity linter (specificity-linter.md) enforce that.

How it's different from what's out there

  • gstack — a fixed, excellent team of skills. Team-Ops sits above it: it can generate the project-specific team, and if gstack is installed, the generated agents delegate execution to its commands. Complementary, not competitive.
  • Static subagent collections — curate or recommend from a fixed roster. Team-Ops generates, grounded in your repo.
  • Skill-from-codebase tools (e.g. Repomix) — produce reference docs about a codebase. Team-Ops produces a build team with enforced review discipline.

Install

Claude Code — clone straight into your project's skills folder:

git clone https://github.com/saar2u/team-ops .claude/skills/team-ops

Restart Claude Code (or /reload-plugins), then run /team-ops or say "Set up a Team-Ops team for this project." It will scan the repo, ask you an interview and wait, propose a roster, then generate on your approval.

Codex / Gemini CLI / other tools — point the tool at SKILL.md and give the same instruction; it emits the portable targets (AGENTS.md / GEMINI.md + a git pre-commit gate) instead of Claude-native files.

What it emits

Your tool Files written
Claude Code .claude/agents/<role>.md + a Stop hook in .claude/settings.json
Codex / Copilot / generic AGENTS.md
Gemini CLI GEMINI.md
Cursor .cursor/rules/<role>.mdc
all .team-ops/checks/*.sh + run.sh, .githooks/pre-commit, .team-ops/manifest.json

How it works

  1. Scan the repo into grounded PROJECT FACTS (references/detection-signals.md).
  2. Interview — a mandatory stop; up to five questions, then wait.
  3. Decide a 4–6 role team by rule; cut roles the project has no work for.
  4. Generate each agent from templates/agent.template.md, grounded in real paths.
  5. Lint every agent through specificity-linter.md (no generic filler survives).
  6. Emit hooks — turn enforceable checklist lines into scripts via hooks-emitter.md, each passing hook-linter.md (drop anything that could cry wolf).
  7. Emit native files per platform (emitters.md) + a manifest for cheap re-runs.

Repository layout

File Purpose
SKILL.md the generator / entry point
references/detection-signals.md concrete repo-scan table
templates/agent.template.md per-agent output template
specificity-linter.md mechanical gate against generic agents
hooks-emitter.md checklist → portable verification scripts + per-host wiring
hook-linter.md keeps generated hooks from false-positiving
emitters.md canonical → native, one section per platform
evals/eval-set.md six cases + rubric proving output is project-specific

Contributing

See CONTRIBUTING.md. The short version: any change to a template or the generator must keep the eval set passing, and any new check must pass the hook linter. Specificity is the product — PRs that add generic filler will be asked to make it concrete or drop it.

License

MIT.

About

Compile a project-specific AI dev team from your repo. Reads your code, runs a short interview, and generates grounded review agents + deterministic verification hooks for Claude Code, Codex, and Gemini CLI etc

Topics

Resources

Code of conduct

Contributing

Security policy

Stars

1 star

Watchers

0 watching

Forks

Releases

Packages

Contributors