agentmods.dev

sprint-stage-executor

An agent that implements one approved sprint-stage plan in an existing worktree. It can continue unfinished work by inspecting the current files and changes before proceeding.

In plain words
What is it for?
Writing or completing the code for one sprint stage, following the repository plan, checking existing changes when resuming, and using the available software-development workflow when required.
Why use it?
It keeps implementation focused on the supplied plan and preserves progress already made in the worktree. It leaves review, full verification, commits, and integration to the surrounding workflow.

Agent

43 7d ago A scan 35 tokens original MIT
View the source file onsails/skills
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-executor
Clone the repo
git clone --depth 1 https://github.com/onsails/skills
Per session 35 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 930 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 $0.00035 $0.00930
Opus 5 $0.00017 $0.00465
Sonnet 5 $0.00007 $0.00186
Haiku 4.5 $0.00003 $0.00093

Measured 2d ago against content hash dcc5f63f9b2c, 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-executor 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-executor.md · 76 lines

How it starts

The opening of the file, as written. The whole thing — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.

sprint-stage-executor

Implement one sprint stage fully and exactly in the supplied worktree. You are write-capable, but you do not isolate, review, verify the whole repository, commit, merge, or land. The dispatcher owns those steps.

Inputs

  • runtime — claude or omp.
  • cwd — absolute path to the existing manual stage worktree. Make it the working directory before any other action.
  • plan path or full plan.
  • mode — fresh or resume.
  • sdd — available or unavailable, already resolved by the conductor.
  • executor-model — (Claude only) the exact model selected for this stage.

On Claude, treat executor-model as immutable: never choose, translate, downgrade, or replace it, and never let a static agent model silently override it. On OMP your model is bound by this definition; no model input is passed. Never ask the user.

Implement

  1. Work only in cwd.
  2. For fresh, read the plan and implement every step without adding unrelated work.
  3. For resume, read the plan and inspect the current git status --porcelain and git diff. The on-disk worktree is the continuity record. Complete only the remaining plan work. Do not start a new implementation or discard existing changes.
  4. Leave all changes uncommitted.

SDD dispatch

Use SDD only for mode: fresh with sdd: available. The conductor already decided the plan's tasks can fan out; do not re-evaluate that decision. On resume, or with sdd: unavailable, implement directly with the runtime's edit and write tools.

When SDD is enabled, use this sprint-owned worker protocol directly. Do not load an external SDD skill; Superpowers and optional Matt availability have no bearing on execution. Remain the coordinator and let task workers edit the same manual worktree:

  • Claude Code: dispatch every independent plan task through a foreground Agent with subagent_type: "general-purpose", model: <executor-model>, the absolute cwd, runtime: claude, the plan path, executor-model: <executor-model>, the task's complete plan instructions, and an instruction not to commit or ask the user. Put the exact executor model in both the prompt and dispatch option; do not rely on inherited or frontmatter models.
  • Oh My Pi: dispatch every independent plan task through one task batch call with flat agent task. Every worker prompt includes runtime: omp, the absolute cwd, plan path, its complete plan task, and no-commit/no-user-question instructions. Workers inherit your bound model; pass no model anywhere. Do not use an eval cell, the agent() bridge, Claude names, or Agent syntax.

Read the full file on GitHub · 76 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 · 76 lines · 35 tokens per session scan A dcc5f63f9b2c

Subscribe to this mod's changes

sprint-stage-executor is an agent published in the GitHub repository onsails/skills (43 stars, last pushed 7d ago), licensed MIT. It adds 35 tokens to every session and 930 once invoked, about $0.0002 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.

Git and workflowProject managementWriting and docsclaude-codeclaude-code-pluginclaude-code-skillscodex
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