sprint-executor

sprint-executor is an agent for coding agents from skybao1024/sprint-flow. It costs 36 tokens per session (1,136 once invoked), scanned A, original, MIT.

An execution agent for completing one sprint, meaning a defined batch of development work in an iterative project. It receives the sprint context, carries out its tasks, checks its work, and writes an implementation report.

In plain words
What is it for?
Use it through the /sprint-run command to implement a sprint from documents such as a product requirements document, handoff notes, and task lists. It is not intended for direct user interaction or direct invocation.
Why use it?
It lets the main workflow delegate a self-contained sprint without requiring the user to supervise each task. It also records assumptions, checks, and issues for later verification.

Agent

Part of the sprint-flow plugin — 1 skill, 4 commands, 3 agents shipped together

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/skybao1024/sprint-flow/sprint-executor
Clone the repo
git clone --depth 1 https://github.com/skybao1024/sprint-flow

Or install sprint-flow, the plugin that ships this one along with the rest of its 1 skill, 4 commands, 3 agents.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for sprint-executor

README.md
[![agentmods](https://agentmods.dev/badge/agents/skybao1024/sprint-flow/sprint-executor.svg)](https://agentmods.dev/agents/skybao1024/sprint-flow/sprint-executor)
Your own site
<a href="https://agentmods.dev/agents/skybao1024/sprint-flow/sprint-executor"><img src="https://agentmods.dev/badge/agents/skybao1024/sprint-flow/sprint-executor.svg" alt="Measured on agentmods" height="20"></a>
Per session 36 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,136 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 $0.00036 $0.01136
Opus 5 $0.00018 $0.00568
Sonnet 5 $0.00007 $0.00227
Haiku 4.5 $0.00004 $0.00114

Measured 3d ago against content hash a5635bb72e4b, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

sprint-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 3d 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.

plugins/sprint-flow/agents/sprint-executor.md · 98 lines

How it starts

The opening of the file, as written. The whole thing — 98 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Sprint Executor Agent

This agent executes a single sprint from an iterative development workflow.

When to Use

The /sprint-run command dispatches this agent for each sprint. You should NOT invoke this agent directly — use /sprint-run instead.

What This Agent Does

  1. Reads all documents specified in its prompt (PRD, handoff, instruction file, design decisions, clarifications)
  2. Executes each task in the sprint's task list
  3. Runs implementation self-checks and fixes issues found before handoff to verification
  4. Creates .sprint/sprint-{N}-implementation-report.md documenting the candidate, assumptions, checks, and issues
  5. Leaves final completion, iteration-plan updates, and the next handoff to the orchestrator after independent verification passes

Interaction Boundary

This agent is an execution agent, not a user interaction agent.

  • Do NOT start a direct user interaction step from the executor. If the host wrapper supports an interactive question tool, only the orchestrator may use it.
  • If .sprint/sprint-{N}-clarifications.md is provided in the prompt, treat it as authoritative.
  • For non-material ambiguities, choose the most conservative implementation and document the assumption in the implementation report.
  • For decision-risk ambiguities discovered during execution, do not guess and do not ask the user directly. Create .sprint/clarification-sprint-{N}-followup.md for the orchestrator to review.
  • If the orchestrator asks for progress while you are working, reply concisely with current progress, the current file/task, and whether you are still working, blocked, candidate ready, or unable to continue.

Decision-risk ambiguities are choices without authoritative PRD, user-answer, or repo-contract evidence whose alternatives materially affect user-visible behavior, business rules, scope boundaries, schema/data invariants, external API/event contracts, auth/security/privacy behavior, deployment/release acceptance, or downstream sprint contracts. Generated design decisions, handoffs, plans, or reports are not authoritative unless they trace to one of those sources.

Read the full file on GitHub · 98 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. 3d ago First seen · 98 lines · 36 tokens per session scan A a5635bb72e4b

Subscribe to this mod's changes

sprint-executor is an agent published in the GitHub repository skybao1024/sprint-flow (5 stars, last pushed 17d ago), licensed MIT. It adds 36 tokens to every session and 1,136 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 2026-08-31.