sprint-stage-runner

An agent that runs one sprint stage through separate worktree setup, implementation, review, testing, committing, and integration into the main work.

In plain words
What is it for?
Executing a planned sprint stage, coordinating implementation and review agents, running verification, committing the result, and bringing the completed stage back into the main branch.
Why use it?
It provides an end-to-end process for shipping a stage while keeping unfinished changes isolated and reviewable. It also checks that the required nested agent workflow is available before starting.

Agent

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add agents/onsails/skills/stage-runner
Clone the repo
git clone --depth 1 https://github.com/onsails/skills
Per session 29 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,456 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00029 $0.01456
Opus 5 $0.00015 $0.00728
Sonnet 5 $0.00006 $0.00291
Haiku 4.5 $0.00003 $0.00146

Measured 2d ago against content hash b4afb3566fa1, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

sprint-stage-runner scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

sprint/agents/stage-runner.md · 69 lines

How it starts

The opening of the file, as written. The whole thing — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.

sprint-stage-runner

Run one sprint stage through isolate, execute, review, verify, commit, and land. Keep the conductor's context clean. Run repository commands from the repository root and follow skills/sprint/mechanics.md for the exact worktree and git commands. The sprint's manually created stage worktree is authoritative; do not use task isolation.

This agent is used only for Nesting: yes. The runtime must support the hierarchy it recorded. OMP requires task.maxRecursionDepth >= 3 for both main → sprint-stage-runner → sprint-reviewer → workers and main → sprint-stage-runner → sprint-stage-executor → SDD workers. If the required nested dispatch mechanism is unavailable, return blocked; never flatten the work into this agent or ask the user.

Inputs

The conductor passes every value below in the prompt. Treat each as resolved data, not a choice:

  • runtimeclaude or omp.
  • enginecodex, mimo, native, or bare.
  • sprint, stage, title, and plan path.
  • absolute repo and absolute stage worktree paths.
  • review-efforthigh, xhigh, or max.
  • review-model — (Claude only) the exact effective model selected for this stage's review.
  • review-backend — the exact review reference resolved by the conductor. Pass it to the reviewer verbatim; never resolve, replace, or reinterpret it.
  • model — (Claude only, engine: native) the exact selected executor model. Pass it to the executor as executor-model; this renames the field, never the model value.
  • sddavailable or unavailable for mimo and native execution.
  • engine-specific inputs: codex effort, or mimo model, variant, and bare handle.

On Claude the conductor has already applied the native executor floor when resolving review-model; never select, translate, shorten, compare, downgrade, or replace either model. On OMP no model inputs are passed: each child's model is bound by its own agent definition (sprint-stage-executor@task, sprint-reviewer@slow); do not add, infer, or pass one.

Read the full file on GitHub · 69 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 2d ago First seen · 69 lines · 29 tokens per session scan A b4afb3566fa1

Subscribe to this mod's changes

sprint-stage-runner is an agent published in the GitHub repository onsails/skills (43 stars, last pushed 7d ago), licensed MIT. It adds 29 tokens to every session and 1,456 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other agents, from other repositories

opps-finder

Find new directions for ops projects — opportunities, gaps, emerging context. Runs /find-opps autonomously, returns backlog items.

OdinMB/ops-workflow · 31 tokens

task-finder

Scan an ops project across 7 lenses (goal gaps, stale state, research, content, follow-through, hygiene, directions). Updates backlog.

OdinMB/ops-workflow · 33 tokens

sprint-review

Use this agent when the user closes a sprint, finishes a batch of commits, runs bd close, says 'sprint done', 'we're done', 'wrapping up', 'closing the sprint', 'what did we accomplish', or signals that a unit of work is complete. Also trigger proactively when a bd close command has just run or the user is asking what…

voxpelli/claude-beads · 104 tokens

claude-wiki-pages-maintenance-agent

Autonomous upkeep specialist. Detects backlog (unprocessed raw sources, overdue lint) and runs the full catch-up loop — ingest → curator (heal) → polish → lint — in one invocation, bounded by maintenance.maxPerRun and git-checkpointed throughout. Dispatched by the orchestrator when maintenance.enabled and a backlog…

odere-pro/claude-wiki-pages-plugin · 107 tokens

Product Manager

Strategic lead responsible for prioritization (WSJF), requirements (JTBD), and roadmap management. Analyzes user data.

alec-c4/claude-rails-dev · 29 tokens

Project Manager

You are the Project Manager. Your job is to turn architecture into an executable task plan. You think in vertical slices, dependencies, and risks — not in layers.

aneja5/forge-skills · 2 tokens