sprint

sprint is a skill for Claude Code, Codex from bouob/agent-harness. It costs 114 tokens per session (9,759 once invoked), scanned A, original, MIT.

An autonomous coding workflow with separate planning, implementation, and evaluation stages. It pauses for approval of the plan before implementation unless automatic mode is requested.

In plain words
What is it for?
Use it to decompose a specification, review or revise the resulting plan, implement tasks in parallel when possible, and evaluate the result.
Why use it?
It catches an unclear direction or a poor breakdown of the work before automated workers start changing code.

Skill for Claude CodeCodex

Installs and runs on its own, but its text points at files inside its plugin — anything it tells you to read at a ${CLAUDE_PLUGIN_ROOT} path is only there once the plugin is installed. Installing the plugin gets both.

Part of the agent-harness plugin — 5 skills, 1 command, 1 hook 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 skills/bouob/agent-harness/sprint
Any agent
npx skills add bouob/agent-harness --skill sprint
Clone the repo
git clone --depth 1 https://github.com/bouob/agent-harness

Made for: Claude Code, Codex.

Or install agent-harness, the plugin that ships this one along with the rest of its 5 skills, 1 command, 1 hook.

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

README.md
[![agentmods](https://agentmods.dev/badge/skills/bouob/agent-harness/sprint.svg)](https://agentmods.dev/skills/bouob/agent-harness/sprint)
Your own site
<a href="https://agentmods.dev/skills/bouob/agent-harness/sprint"><img src="https://agentmods.dev/badge/skills/bouob/agent-harness/sprint.svg" alt="Measured on agentmods" height="20"></a>
Per session 114 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 9,759 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 $0.00114 $0.09759
Opus 5 $0.00057 $0.04880
Sonnet 5 $0.00023 $0.01952
Haiku 4.5 $0.00011 $0.00976

Measured 4d ago against content hash e985ee105603, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

sprint 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 4d 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.

skills/sprint/SKILL.md · 742 lines

How it starts

The opening of the file, as written. The whole thing — 742 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/sprint — Autonomous Multi-Agent Sprint

Two gates, two failure classes

A wrong direction caught after Generators run costs a full iteration to rescue; caught before, it costs one plan re-read. /sprint therefore has two gates in front of implementation:

  1. Plan mode (optional, before /sprint) — catches a wrong or ambiguous spec. For vague verbs, missing acceptance criteria, or multiple possible interpretations, enter plan mode first so the Planner starts from a sharpened spec.
  2. Plan checkpoint (Phase 3, built-in) — catches a wrong decomposition. The Planner's plan comes back to the main session for your approval before any Generator launches. You can approve, edit the plan file, replan with feedback, or abort. Prefix the spec with auto to skip this gate and run fully autonomously.

References (read on demand)

  • ${CLAUDE_PLUGIN_ROOT}/skills/sprint/references/config-schema.md — routing config, schema v4 (auto-lifts v1 / v2 / v3)
  • ${CLAUDE_PLUGIN_ROOT}/skills/sprint/references/sprint-contract.schema.md — artifact schema for sprint-meta / plan / progress / eval files
  • ${CLAUDE_PLUGIN_ROOT}/skills/sprint/references/planner.md — Planner role prompt
  • ${CLAUDE_PLUGIN_ROOT}/skills/sprint/references/generator.md — Generator role prompt
  • ${CLAUDE_PLUGIN_ROOT}/skills/sprint/references/evaluator.md — Evaluator role prompt
  • ${CLAUDE_PLUGIN_ROOT}/skills/sprint/references/handoff-schema.md — inter-phase handoff schema
  • ${CLAUDE_PLUGIN_ROOT}/skills/sprint/references/agent-fallback.md — legacy Agent-tool orchestration (used when dynamic workflows are unavailable)

Input

$ARGUMENTS

If arguments are empty: ask the user for a spec before proceeding.

auto flag: if $ARGUMENTS starts with the word auto followed by a space, set {checkpoint_mode} = skip and strip the flag — everything after it is the spec. Otherwise {checkpoint_mode} = review. All later references to "the spec" mean the flag-stripped text; it is what goes into sprint-meta.json and every agent prompt.

Read the full file on GitHub · 742 lines

Files

What ships with it

7 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 4d ago First seen · 742 lines · 114 tokens per session scan A e985ee105603

Subscribe to this mod's changes

sprint is a skill published in the GitHub repository bouob/agent-harness (5 stars, last pushed 1mo ago), licensed MIT. It adds 114 tokens to every session and 9,759 once invoked, about $0.0006 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.

Related

Other skills, from other repositories

ci-review

CI-optimized code review: multi-agent parallel review with confidence scoring and atomic GitHub PR review posting. Runs specialized review agents, scores findings, and submits a GitHub PR review via post-review.sh. Always executes post-review.sh to submit a review on every run (including zero-findings runs). Triggers…

rube-de/cc-skills · 127 tokens

pr-check

PR review compliance: fetch review comments from an open PR, categorize as resolved/unresolved/dismissed, critically evaluate fixable items, implement approved fixes, and reply inline. Pass --unattended to halt on human-judgment items (emitted as Pending-Human) instead of prompting via AskUserQuestion.

rube-de/cc-skills · 67 tokens

council

Consult external AI council (Gemini 3.8 Flash, Codex, GLM-5.3, Kimi) for thorough reviews and consensus-driven decisions. Use ONLY when explicitly invoked with "/council" or when user says "consult the council", "invoke council", or "council review". Do NOT auto-trigger on generic phrases like "thorough review".

rube-de/cc-skills · 82 tokens

babysit

PR babysitter: monitors CI status, auto-rebases when behind, auto-fixes CI where possible, delegates review comment handling to dlc:pr-check, and re-requests review after fixes. Designed for /loop usage with Remote Control.

rube-de/cc-skills · 53 tokens

brainstorm

You MUST use this skill before /pm when work is ambiguous, scope is unclear, or multiple approaches exist. Explores problem space, proposes 2-3 approaches with trade-offs, and produces an approved spec document that feeds into both issue creation (/pm) and implementation planning (/cdt). Triggers: brainstorm, explore…

rube-de/cc-skills · 96 tokens

pm

Project manager for GitHub issues: brainstorm design approaches, create structured issues optimized for LLM agent teams, triage and recommend what to work on next, audit and clean up stale issues, or deep-validate a single issue against the codebase. Triggers: create issue, plan work, new task, project manager, write…

rube-de/cc-skills · 98 tokens