# Everything, in one place.

Start with install, learn the DAIC loop and the gates that enforce it, then reach for the reference pages when you need the exact tool surface. For the workflows themselves, see the [protocols overview](https://team.management/protocols.md).

There are three groups below, and they answer three different questions.

Getting started is the shortest path from nothing to a working setup. Add the marketplace, install the plugin, run init. Your team picks it up from a single committed file, so nobody has to be talked through it. If you are new here, read this group and come back for the rest later.

Concepts explains why it behaves the way it does. DAIC is the loop everything else hangs off — discuss before you build, with hooks that hold the line rather than asking politely. Around it sit the pieces that make a long session survivable: what happens when context runs out, when a test is worth writing first, what the spec gate checks before work can be called done, how knowledge accumulates instead of being re-derived every morning, and how to change any of it when the defaults do not suit you.

Reference is what you open with a specific question in mind. The exact tool surface, the functions you can wire into a step, how issues move between the engine and your tracker, and how a second or third model joins the work.

Read them in that order the first time. After that, most people live in Reference.

## Getting started

[Install in five minutes](https://team.management/docs/install.md)

[A native Claude Code plugin: add the marketplace, install, run init — your team follows via one committed file.](https://team.management/docs/install.md)

## Concepts

[DAIC — the loop on rails](https://team.management/docs/daic.md)

[Discuss → Align → Implement → Document → Commit, enforced by hooks that can’t be bypassed.](https://team.management/docs/daic.md)

[Context preservation & auto-compact](https://team.management/docs/context-preservation.md)

[A PreCompact hook checkpoints the session before compaction; on restart, task, branch, protocol step, and DAIC mode all reload.](https://team.management/docs/context-preservation.md)

[Test-driven, when it applies](https://team.management/docs/tdd.md)

[Write the test, watch it fail, then implement. The applicability matrix, honestly drawn.](https://team.management/docs/tdd.md)

[The spec-compliance gate](https://team.management/docs/spec-review.md)

[A SPEC_REVIEW: PASSED sentinel the agent can’t advance past until the diff matches the spec.](https://team.management/docs/spec-review.md)

[LLM Wiki — a compounding knowledge base](https://team.management/docs/llm-wiki.md)

[Claude writes and maintains a structured, interlinked wiki from your raw sources — knowledge compounds instead of being re-derived on every query.](https://team.management/docs/llm-wiki.md)

[Your protocols, your rules](https://team.management/docs/customization.md)

[Fork any protocol into custom/ — it overrides the system copy and is never touched on upgrade.](https://team.management/docs/customization.md)

## Reference

[Plugin tools reference](https://team.management/docs/mcp.md)

[Reference documentation for the 42 plugin tools (8 modules) that run locally in your session. The hosted docs MCP is a separate server at /mcp/docs.](https://team.management/docs/mcp.md)

[Engine functions reference](https://team.management/docs/functions.md)

[The 45 pre_funcs / post_funcs you wire into protocol steps — branch setup, gates, issue sync, archiving, the optimize loop — grouped by what they do.](https://team.management/docs/functions.md)

[Issue tracking — four providers, one interface](https://team.management/docs/issue-tracking.md)

[GitLab, Jira, GitHub, Gitea — import issues as tasks, sync status bidirectionally, ship MRs and PRs from the completion step.](https://team.management/docs/issue-tracking.md)

[AI providers — Codex & Antigravity](https://team.management/docs/ai-providers.md)

[Codex and Antigravity join Claude as parallel collaborators across six workflow phases.](https://team.management/docs/ai-providers.md)