sprint command
Feature Forge — preview
--farm — preview. This flag is part of the Feature Forge and ships dormant by default. Promotion to stable is driven by real-world evidence.
Run an autonomous sprint from maintained specs and plans, with truthful verification and no duplicate artifact approval ceremonies.
/ca:sprint$ca-sprint/ca-sprintAvailability is read from each shipped host catalog. Preview-only commands are marked on the page.
What it does
Section titled “What it does”Your sprint request establishes the working scope. codeArbiter maintains a specification and plan, implements coherent tasks, verifies their outcomes and prepares a pull request without default pauses between batches. It asks about consequential missing choices and honors review pauses you explicitly request.
Material decisions and uncertainty are recorded in the sprint log. SMARTS supports difficult trade-offs when useful. Tests and reviews follow the affected work; current results can be reused while their relevant inputs match. A progress label does not certify passing checks or a release.
/ca:sprint [goal] [--farm]A short goal seeds the spec conversation that opens the sprint. New full-lane
sprints author typed HTML by default. --farm remains blocked for HTML plans
until its separate current-model qualification closes; the flag continues to
name the existing legacy Markdown backend without changing that boundary.
Example
Section titled “Example”> /ca:sprint limit the public webhook to 60 requests per IP per minute; return 429 above that limit using our existing store
The request supplies the limit, window and rejection behavior.Spec saved to .codearbiter/specs/webhook-rate-limit.html; plan contains 5 tasks.Executing the independent tasks and recording observed checks.Security review covers the changed limiter and its input handling.The inspected results remain current through commit and PR preparation.Five tasks implemented; checks and remaining limitations reported.Routing through the authorized commit and PR handoff. Merge remains a separate decision.When to reach for it
Section titled “When to reach for it”Reach for /ca:sprint for autonomous work across a maintained plan. Use /ca:feature for a
single bounded capability. Both provide progress reports and respect explicit review pauses;
neither requires another artifact approval to continue ordinary authorized work.
For the complete source-traced sequence and its actual endpoint, use the operator guide and Compare workflow routes.
| Gate | When | Effect |
|---|---|---|
| working scope | specifying or resuming the sprint | maintain the requested outcome and ask only about consequential missing choices; reuse settled decisions |
| hard gates | an explicit stop, consequential unresolved choice, host denial, applicable security control or unauthorized irreversible action prevents affected work | stop affected work at its actual boundary and continue independent authorized tasks |
Related
Section titled “Related”Route context
Section titled “Route context”Find this entry in the workflow atlas. Compare its related teaching maps, host spelling and context inputs. The exact procedure below remains the owner.
Source
Section titled “Source”Source — plugins/ca/commands/sprint.md (v3.7.0)
---description: "Run an autonomous sprint from maintained specs and plans, with truthful verification and no duplicate artifact approval ceremonies."argument-hint: "[goal] [--farm]"---
# /ca:sprint — autonomous sprint
The user's requested sprint establishes its working scope. Use `brainstorming` to clarify genuinely missing outcomes, `writing-plans` to maintain a practical plan, and `subagent-driven-development` to execute through real task dependencies without per-batch permission questions. Record meaningful choices and honest evidence; do not invent approvals, clear user stops, or infer tests passed from progress labels.
## Flow
Load and follow `${CLAUDE_PLUGIN_ROOT}/SPRINT.md`:
1. **Specify and plan:** build or resume the exact spec/plan representation. Ask about consequential missing choices, not about arbitrary approval hashes.2. **Execute:** work through task-scoped prerequisites and coherent batches, implement or delegate where useful, and check changed behavior. Retry affected failures without restarting a reviewer fleet.3. **Report and deliver:** show actual results, pending checks, and open choices. Use the existing authorized `commit-gate` and PR handoff; opening a PR does not authorize merging or publishing.
Real host/tool permissions, explicit security policy, irreversible operation limits and user stops remain intact. Artifact `DONE` means implementation reported complete, not independently verified acceptance.
## Arguments
- **Goal:** intended sprint outcome and scope.- **`--farm`:** separately requested legacy Markdown preview backend; obey its provider, budget and circuit-breaker boundaries. HTML farm is disabled, and failure does not authorize a silent backend switch.
## Routes to
`${CLAUDE_PLUGIN_ROOT}/SPRINT.md` routes through `brainstorming`, `writing-plans`, `subagent-driven-development`, `commit-gate`, and `finishing-a-development-branch`.
For a single bounded feature, use `/ca:feature`. No repetitive initial spec approval interview is implied by either entry.