Claude Skill

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.

LLM Mart · 0 points · 17 views 0 listing impressions 0 install-command copies
Download arbiterForge-codeArbiter-plugins_ca-codex_skills_ca-sprint-9b8989c.zip · 1 KB

Install

skills CLI npx skills add https://github.com/arbiterForge/codeArbiter/tree/main/plugins/ca-codex/skills/ca-sprint
Claude Code claude plugin marketplace add https://llmmart.ai/marketplace.json && claude plugin install arbiterforge-codearbiter@llmmart
Git 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 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 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

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 3.3 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 [includes/helper-invocation.md](../../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 [SPRINT.md](../../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
    
    [SPRINT.md](../../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.

No comments yet.

Reviews (0)

No reviews yet.