Start with the project README for the overview and quick start. The guides below go deeper, roughly in the order you'll need them.

• Native development campaigns — parallel unit scheduling, planning, draft PR delivery, GitHub synchronization and native Paradev reflection.
• The open-runtime fork — fork capabilities, parallel epic runs, TeamRouter routing, and installing this fork.
• Setup guide — install the tools, pick a CLI, initialize a project, pass preflight, and uninstall.
• TUI guide — the dashboard: layout, key bindings, the settings editor, and troubleshooting.
• Ticket-tree mode — driving a BMAD v7 initiative ticket tree: prerequisites, store layouts, pick order, every pause and how to clear it, marking done, checkpoints, the epic retrospective and closure, parking and resolve, and the v7 ledger and sweep.
• Deferred-work sweeps — running a sweep, answering decisions, closing entries from stories, hard gates, and recovering from stale answers, publication refusals and an unreadable ledger.
• Loop recovery — the open-runtime fork's [recovery] table: post_story for stories a resume finishes, plan baseline re-stamps, the smart stall check, turn-error pauses, nudges over hcom, session resume, and policy reload at story boundaries.
• Recovering paused runs — escalations and resolve (re-arm, --adopt-branch, --reverify, --abandon), preserved attempts, plateau-defer, confirm for human-only actions, environment faults, and worktree merge-back failures.
• Features — what the tool does: the feature catalog, with each feature's stability, guarantees, tests and docs.
• Terminal multiplexer backends — which backend drives your agent sessions (tmux bundled; externals like the herdr adapter install as packages), how selection works, and how external backends arrive.

• Configuration — .bmad-loop/policy.toml location and precedence, the BMAD_LOOP_* environment variables, and every policy setting with its type, default and allowed values (generated from the settings schema).
• CLI — every bmad-loop subcommand and its options, the --json document shapes, exit codes, and the validate check ids.
• Run state — where run state lives, the run and task directory layout, session naming and teardown, stopping a run, and what cleanup, clean, delete and archive remove.

• Authoring CLI adapters & profiles — using bmad-loop probe-adapter to collect + sanitize the hook payload shape, transcript location, and token schema a new CLI profile needs, plus the CodingCLIAdapter ABC and how an adapter class (and the profile selecting it) ships out-of-tree.
• Writing a bmad-loop plugin — the plugin system: plugin.toml manifest, hooks, lifecycle stages, settings, the trust model, and workflow injection, with a worked walkthrough.
• Writing a Game Engine plugin — the game-engine layer (built on the plugin system): driving a live engine Editor, the editor_mode ↔ [scm] isolation coupling, a minimal Godot example.
• Writing a plugin for a specific Editor MCP — Editor-MCP specifics for the bundled Unity plugin: IvanMurzak vs CoplayDev, readiness probes, per_worktree isolation, and the full BMAD_LOOP_* env-var reference.
• Porting bmad-loop to a new OS — the four OS seams (terminal multiplexer, process lifecycle, hook interpreter, validate preflight), their registries and override env vars, and native Windows as the reference port.
• The Test Architect (TEA) plugin — the bundled tea plugin: installing TEA, the six advisory test-architecture steps it injects across runs and sweeps, the enable/blocking settings, and the escalate-on-gate behavior.

• Roadmap — planned and intentionally-deferred work.
• Architecture decision records — design decisions with the options weighed and the reasons, starting with the multiplexer env transport.

For released changes, see the CHANGELOG.

• Contributing guide — dev setup (uv + trunk), PR guidelines, and conventional commits.
• Testing strategy — the layer model, fixture and ablation doctrines, quality guards, the zero-token invariant, and the CI/flake policy behind the suite.
• Code of Conduct — the Contributor Covenant we follow.
• Security policy — how to report a vulnerability and what's in scope.
• Trademark guidelines — proper use of the BMad name and brand.