ca-sprint
Autonomous sprint — one interactive spec gate, then plan-to-PR execution with every auto-decision SMARTS-scored and logged. Hard gates remain true stops.
Install
npx skills add https://github.com/arbiterForge/codeArbiter/tree/main/plugins/ca-pi/skills/ca-sprint
claude plugin marketplace add https://llmmart.ai/marketplace.json && claude plugin install arbiterforge-codearbiter@llmmart
git clone https://github.com/arbiterForge/codeArbiter.git
The skills CLI installs just this skill, for any of its supported agents. Claude Code installs the whole arbiterforge/codearbiter collection as a plugin from our marketplace. Git is the plain clone.
Skill manifest
/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.
For each independently actionable deliverable, select or create one work ID
through the installed hooks/work.py facade. Use an explicit ID or stable
source origin to resume; title and command invocation are not identity. A
single-outcome sprint may use one item. For several deliverables, set the same
optional cycle key on each item with work.py set-cycle, or pass --cycle-id
on creation. The cycle groups member work IDs; it does not copy their specs,
plans, task states or checks into a second ledger. work.py cycle-view <cycle-id> is the derived group overview. Keep real spec/plan attachments on
their selected member work item and report local progress, checks, PR delivery
and provider effects independently. See <plugin-root>/includes/helper-invocation.md for
literal helper invocation and retry boundaries.
Where the native project has explicitly configured transition mapping, use
the ordinary one-item lifecycle call for each member. It saves the mapped
tracker intent or a waiting reason with local progress. Do not translate
status labels or stage each target in a separate model-facing call. A later
explicit work.py sync-mapped <WORK-ID> handles only that item's mapped
targets and reports partial results; no sprint transition sends over the network.
Flow
Load and follow <plugin-root>/SPRINT.md:
- Specify and plan: build or resume the exact spec/plan representation. Ask about consequential missing choices, not about arbitrary approval hashes.
- 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.
- Report and deliver: show actual results, pending checks, and open choices. Use the existing authorized
commit-gateand 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
<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.
Files (codearbiter)
-
SKILL.md 3.2 KB
--- name: ca-sprint 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. For each independently actionable deliverable, select or create one work ID through the installed `hooks/work.py` facade. Use an explicit ID or stable source origin to resume; title and command invocation are not identity. A single-outcome sprint may use one item. For several deliverables, set the same optional cycle key on each item with `work.py set-cycle`, or pass `--cycle-id` on creation. The cycle groups member work IDs; it does not copy their specs, plans, task states or checks into a second ledger. `work.py cycle-view <cycle-id>` is the derived group overview. Keep real spec/plan attachments on their selected member work item and report local progress, checks, PR delivery and provider effects independently. See `<plugin-root>/includes/helper-invocation.md` for literal helper invocation and retry boundaries. Where the native project has explicitly configured transition mapping, use the ordinary one-item lifecycle call for each member. It saves the mapped tracker intent or a waiting reason with local progress. Do not translate status labels or stage each target in a separate model-facing call. A later explicit `work.py sync-mapped <WORK-ID>` handles only that item's mapped targets and reports partial results; no sprint transition sends over the network. ## Flow Load and follow `<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 `<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.
Comments (0)
Sign in to join the conversation.
Reviews (0)
No reviews yet.
No comments yet.