BMAD-METHOD/docs/reference/dev-auto.md

title, description, sidebar

title	description	sidebar
Autonomous Development Loops	Reference for running unattended BMad development loops with bmad-dev-auto as the single-iteration worker.	order 7

To use BMad in an autonomous development loop, use the bmad-dev-auto skill. It is like Quick Dev, but designed to keep moving without human interaction. You can use it in an interactive session, but its main purpose is to be used by an orchestrator.

The important architectural boundary is this: bmad-dev-auto owns the implementation run and the spec artifact it produces, but it does not own your backlog policy. When review finds something real that is not this story's problem, the skill records that finding in the spec it owns and stops there. Deciding whether to queue it, deduplicate it, escalate it, or ignore it is the orchestrator's responsibility.

What It Does

bmad-dev-auto performs one unattended development-loop iteration:

1. Clarify the incoming intent
2. Create (or find and resume) a spec file
3. Implement the change
4. Review the result
5. Finish by writing a terminal status to the spec file or fallback result artifact.

Prerequisites

This skill relies on an ability to run subagents. If subagents are unavailable, the workflow halts blocked with no subagents. If you invoke the skill itself in a subagent session, e.g. "hey, Claude, implement stories 2-10, using a subagent running bmad-dev-auto skill for each story", that session will need to spawn its own subagents.

Version control, while optional, is strongly recommended. If present, the working tree must be clean and the agent must be able to update repository metadata.

Inputs

Primary Invocation Input

The main input is the invocation prompt. bmad-dev-auto treats that prompt as workflow input, not as a finished implementation plan.

Supported intent shapes include:

• A short free-form change request
• A ticket, issue, or story identifier
• A path to an intent file
• A path to an existing spec file generated by this workflow
• A spec folder plus a story id, with no specific spec file path (folder+id dispatch — see below)

Resume Input

If the invocation points to an existing spec file with one of the known status values in the frontmatter, the workflow resumes from that state:

Spec status	Entry point
draft	plan
ready-for-dev	implement
in-progress	implement
in-review	review
done	review again as a fresh follow-up pass
blocked	halt immediately

Folder+ID Dispatch

Instead of a spec-file path, the invocation prompt can supply a spec folder and a story id, with no specific spec file path. Any further prompt text (e.g. invoke_dev_with guidance a caller appends) is carried forward as extra planning context, not a competing description of the work.

The workflow reads <spec-folder>/stories.yaml and looks up the entry whose id matches. It takes only that entry's title and description — spec_checkpoint, done_checkpoint, and invoke_dev_with are the dispatching caller's fields and are never read from the file itself.

It then checks <spec-folder>/stories/<story-id>-*.md (id-prefix match) to tell a first dispatch from a resume:

On-disk match	Outcome
None	First dispatch. Requires <spec-folder>/SPEC.md to exist (otherwise halts blocked / no epic spec found). Loads SPEC.md and its companions, then proceeds to planning.
Exactly one	Resume: routes on that file's status exactly like the Resume Input table above. A blocked status here reports blocking condition story already blocked, not blocked spec supplied — dev-auto discovered the file by id, the caller didn't hand it a blocked spec. A missing or unrecognized status halts blocked / unrecognized status in existing story file.
More than one	Halts blocked / ambiguous story file match.

A blocked story file is permanent: every later dispatch of that id halts with story already blocked, even after the cause is fixed. To retry, delete the story file — the id then reads as pending and the next dispatch starts fresh.

Whenever planning runs — on a first dispatch, or on a resume of interrupted planning (draft) — the workflow also loads every other file matching <spec-folder>/stories/*.md and carries forward each one's Code Map, Design Notes, Spec Change Log, Tasks & Acceptance checklist state, and Auto Run Result details as extra planning context, so planning for one story can see what other stories in the same folder have already decided or produced. Resumes that skip planning skip this too.

Exactly one stories.yaml entry is dispatched per invocation: the workflow never reads another entry or advances to a different story id, regardless of outcome.

Context Inputs

On activation, the workflow resolves:

• _bmad/config.toml, _bmad/config.user.toml, and optional team/user overrides under _bmad/custom/
• Any configured workflow customizations from customize.toml, team overrides, and user overrides
• Persistent facts listed in workflow config
• project-context.md files, if present

It may also look at:

• BMAD planning artifacts
• A cached or newly compiled epic context file for epic-based work
• The most recent completed prior-story spec from the same epic for continuity
• Other stories/*.md records in the same spec folder, under folder+id dispatch (see Folder+ID Dispatch above)

Spec Status

The spec frontmatter status is the main machine-readable state for orchestration:

Spec Status	Meaning
draft	Spec exists but has not passed ready-for-dev validation
ready-for-dev	Spec is complete enough to implement
in-progress	Implementation is underway
in-review	Review/triage is underway
done	Workflow completed successfully
blocked	Workflow cannot safely continue unattended

Deferred Findings

deferred is where the skill reports real findings that are not this story's problem. Each item contains:

• summary — one-sentence description of the deferred issue
• evidence — why the finding is real
• location — optional file:line or component hint
• severity — optional final triage severity (high, medium, low)

This is intentionally not a backlog. It is a machine-readable review output. The orchestrator has to decide what happens next: create a ticket, append to a central queue, correlate duplicates across runs, or do nothing.

On ready-for-dev

ready-for-dev is normally a resume state the workflow passes straight through on its way to implementation. It becomes a genuine halt outcome when the invocation prompt directs a halt after planning: once the spec passes the READY FOR DEVELOPMENT gate, the workflow sets status ready-for-dev and stops there instead of continuing to implementation. Re-dispatching the same spec (or the same spec folder and story id) resumes at implementation via the routing above.

On done

On successful completion, the workflow writes or updates the spec with:

• Final status: done
• An Auto Run Result section containing:
  • Summary of implemented change
  • Files changed
  • Review findings breakdown
  • Verification performed
  • Residual risks
• followup_review_recommended flag. True if LLM decided another review pass seems worthwhile. It's a suggestion, not a must. Simplest way to give it a second review pass is to re-run the skill pointing it at the spec file.
• baseline_revision and final_revision — the full canonical revisions before implementation and at the reviewed change's endpoint. git log baseline_revision..final_revision lists the reviewed change commits. Both are NO_VCS without version control.
• deferred frontmatter entries for review findings triaged defer. Each item records summary, evidence, and, when known, location plus severity.

The workflow commits but does not push. If the spec is tracked in the implementation repository, clean HEAD is one spec-finalization commit beyond final_revision; otherwise the implementation repository ends at final_revision.

On blocked

On blocked completion, the workflow writes:

• Final status: blocked when a spec exists
• A blocking condition
• Supporting detail in the spec or fallback result artifact

Typical blocking conditions include:

• unclear intent
• intent gap
• no subagents
• missing spec_file before implementation
• implementation verification failed
• review repair loop exceeded 5 iterations (non-convergence)
• blocked spec supplied (a directly-invoked spec file already had status: blocked)
• no stories.yaml found
• story id not found in stories.yaml
• no epic spec found
• ambiguous story file match
• unrecognized status in existing story file
• story already blocked (folder+id dispatch only — contrast with blocked spec supplied above)

An intent gap means the captured intent cannot answer a question the run hit — it can halt the planning step (before any code exists) or the review step. When review halts on it, the working tree is reverted as usual, but the attempted change is first saved as a patch file in {implementation_artifacts}, referenced from the spec's triage log and the halt output. The patch shows which reading of the intent the run implemented — concrete evidence for repairing the intent. If the attempted reading turns out to be correct, git apply the patch and set the spec status to in-review to resume review on it instead of re-running from scratch.

Output Artifacts

The workflow always tries to leave behind a durable artifact describing what happened.

Primary Spec Artifact

For new work, the workflow creates:

{implementation_artifacts}/spec-<slug>.md

That spec is the contract between planning, implementation, and review. It contains:

• Frontmatter status
• Frontmatter machine state (followup_review_recommended, warnings, deferred, revision markers)
• The immutable <intent-contract> block
• Code map
• Tasks and acceptance criteria
• Spec change log
• Review triage log
• Verification notes

Story Spec Artifact (Folder+ID Dispatch)

Under folder+id dispatch, the workflow writes to <spec-folder>/stories/<story-id>-<slug>.md instead of the primary spec or fallback result paths — including for halts before planning starts. The fallback result artifact below is never used in this mode.

When a halt happens before a slug can be derived from the story's title, the write-back falls back to a fixed slug segment instead:

Situation	Slug segment used
stories.yaml missing/unparseable, or no entry matches the story id	unresolved
More than one on-disk file already matches <story-id>-*.md	ambiguous
Entry resolved and no on-disk ambiguity	slug derived from title (and description if needed)

If the resolved path already exists, the workflow updates its status frontmatter and appends result details under ## Auto Run Result, same as the primary spec artifact. If it doesn't exist, the workflow creates a skeletal story spec: frontmatter status, a heading (the entry's title, or Story <story_id> if the entry couldn't be resolved or the on-disk match was ambiguous), and an ## Auto Run Result section.

Fallback Result Artifact

If the workflow halts before it has a valid spec_file (outside folder+id dispatch — see above), it writes:

{implementation_artifacts}/bmad-dev-auto-result-<slug-or-timestamp>.md

This records the terminal status and blocking condition.

Additional Artifacts

Depending on the route, the workflow may also write:

• {implementation_artifacts}/epic-<N>-context.md
• A patch file preserving the attempted change when the review step halts on intent gap (path recorded in the spec's triage log)

Orchestrator Responsibilities

An orchestrator integrating bmad-dev-auto should:

• Pass one coherent intent at a time
• Prefer passing a spec path when resuming prior work — or the same spec folder and story id, under folder+id dispatch
• Monitor the produced spec file, story spec artifact, or fallback result file for terminal state
• Read status, blocking condition, and followup_review_recommended rather than inferring success from chat output alone
• Read deferred findings from the spec frontmatter deferred: list
• Use baseline_revision..final_revision to identify the reviewed change commits; do not assume final_revision equals HEAD
• Expect autonomous file changes and local commits
• Handle blocked as a routing signal, not just a failure signal

In practice, blocked usually means the workflow ran into a situation where unattended execution would be unsafe. That is often the point where a higher-level orchestrator, another workflow, or a human should take over.

After resolving a blocked run, the orchestrator should usually start a fresh bmad-dev-auto run. If it reuses prior work, it should pass an explicit known-good spec path rather than relying on implicit discovery.