dev-sprint

dev-sprint is a skill for Claude Code, Codex from reboulip/rblclass. It costs 89 tokens per session (1,735 once invoked), scanned A, original, Apache-2.0.

A sprint runner for the RBLclass add-in. It reads the project's roadmap and completes every unchecked task in the current version section.

In plain words
What is it for?
Use it to carry out a full development sprint from ROADMAP.md, including preparing implementation plans, making code changes, verifying them, and updating the roadmap.
Why use it?
It removes the need to coordinate each roadmap task manually. Each task is prepared, implemented, checked, and recorded as complete in order.

Skill for Claude CodeCodex

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/reboulip/rblclass/dev-sprint
Any agent
npx skills add reboulip/rblclass --skill dev-sprint
Clone the repo
git clone --depth 1 https://github.com/reboulip/rblclass

Made for: Claude Code, Codex.

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 dev-sprint

README.md
[![agentmods](https://agentmods.dev/badge/skills/reboulip/rblclass/dev-sprint.svg)](https://agentmods.dev/skills/reboulip/rblclass/dev-sprint)
Your own site
<a href="https://agentmods.dev/skills/reboulip/rblclass/dev-sprint"><img src="https://agentmods.dev/badge/skills/reboulip/rblclass/dev-sprint.svg" alt="Measured on agentmods" height="20"></a>
Per session 89 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,735 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 $0.00089 $0.01735
Opus 5 $0.00044 $0.00868
Sonnet 5 $0.00018 $0.00347
Haiku 4.5 $0.00009 $0.00173

Measured 4d ago against content hash 43c26bef1790, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

dev-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.

.claude/skills/dev-sprint/SKILL.md · 191 lines

How it starts

The opening of the file, as written. The whole thing — 191 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/dev-sprint — run the current sprint

What this does

Finds the active sprint in ROADMAP.md and drives every unchecked item to completion. Each item goes through:

  1. Preparation (feature-prep subagent, Sonnet 4.6) — reads the codebase and produces an Implementation Brief.
  2. Implementation (/feature-impl skill) — implements, verifies, and commits the item (including the ROADMAP.md checkbox update).

Preparation for item N+1 is dispatched in the same message as /feature-impl for item N, so both run in parallel. The brief lands while implementation is in progress and is read right after N's commit, before N+1 starts.


Rules

Always perform the dev sprint in develop branch, and make sure develop is up to date with main before starting.


Step 0 — Version stamp

0a — Locate the active sprint and read current version

Read ROADMAP.md. The active sprint is the highest-versioned ## vX.X.X.X section that contains at least one unchecked item (- [ ]). Extract the sprint version label (e.g. v2.4.0.0).

Read the current AssemblyVersion from src/RBLclass.AddIn/Properties/AssemblyInfo.cs.

0b — Classify the sprint and present a version proposal

Scan the sprint's full item list. Classify the overall change as:

  • Hotfix — bug fixes only, no new user-facing capability.
  • Minor — new features or enhancements; no breaking changes.
  • Major — breaking changes, architectural overhaul, or a full-product version boundary.

Present a brief summary (5–10 words per item) and the classification rationale, then ask the user to confirm or override the target version via AskUserQuestion:

Sprint: <roadmap version>
Current AssemblyVersion: <x.y.z.w>
Classification: <Hotfix | Minor | Major> — <one-line rationale>

Planned changes:
  • <Label>: <brief description>
  …

Proposed version: <roadmap version>

Options: "Confirm " / the user may select "Other" to provide a different version string.

Read the full file on GitHub · 191 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. 4d ago First seen · 191 lines · 89 tokens per session scan A 43c26bef1790

Subscribe to this mod's changes

dev-sprint is a skill published in the GitHub repository reboulip/rblclass (11 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 89 tokens to every session and 1,735 once invoked, about $0.0004 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 skills, from other repositories

workthreads

SpecStory Workthreads - a weekly work-thread rollup across a team's repos from SpecStory coding histories (any agent - Claude Code, Codex, Cursor, Gemini, and more). It groups the window's sessions into threads of work per project and labels each new / open / recently closed, so a lead sees what shipped, what is still…

specstoryai/getspecstory · 126 tokens

story-readiness

Validate that a story file is implementation-ready. Checks for embedded GDD requirements, ADR references, engine notes, clear acceptance criteria, and no open design questions. Produces READY / NEEDS WORK / BLOCKED verdict with specific gaps. Use when user says 'is this story ready', 'can I start on this story', 'is…

Donchitos/Claude-Code-Game-Studios · 77 tokens

flow-next-tracker-sync

Project a flow-next spec to a tracker issue (Linear, GitHub, GitLab, Jira) and reconcile two-way. Use when asked to sync to a tracker. NOT plan-sync.

gmickel/flow-next · 44 tokens

loop

Full execution protocol for MODE: LOOP — the compound-engineering loop: brainstorm → plan → build → review → improve, iterating under defense-in-depth stop conditions with generator/critic separation, durable resumable state, and mandatory compounding learning capture. Loaded on demand by the architect when the loop…

ZaxbyHub/opencode-swarm · 72 tokens

subagent-delegation

Canonical protocol for delegating GSD work to native Antigravity subagents — when to delegate, how to invoke, workspace isolation modes, and the inline fallback for older IDE versions.

toonight/get-shit-done-for-antigravity · 42 tokens

projects

List all managed projects with status, branch, open PRs, and open issue counts — portfolio-level view.

me2resh/apexyard · 24 tokens