full-sprint

full-sprint is a skill for Claude Code, Codex from rbah31/claude-code-workflow. It costs 79 tokens per session (1,475 once invoked), scanned A, original, Apache-2.0.

An automated workflow for running a complete software sprint from planning through building, review, fixes, and lessons learned. Each phase runs in a separate Claude command-line session, which keeps the reviewer from being biased by the builder's context.

In plain words
What is it for?
Use it when a sprint directive is ready and you want the full sprint executed end to end.
Why use it?
It removes the need to coordinate each sprint phase by hand while preserving a separate review step and running the project's safety checks and tests.

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/rbah31/claude-code-workflow/full-sprint
Any agent
npx skills add rbah31/claude-code-workflow --skill full-sprint
Clone the repo
git clone --depth 1 https://github.com/rbah31/claude-code-workflow

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 full-sprint

README.md
[![agentmods](https://agentmods.dev/badge/skills/rbah31/claude-code-workflow/full-sprint.svg)](https://agentmods.dev/skills/rbah31/claude-code-workflow/full-sprint)
Your own site
<a href="https://agentmods.dev/skills/rbah31/claude-code-workflow/full-sprint"><img src="https://agentmods.dev/badge/skills/rbah31/claude-code-workflow/full-sprint.svg" alt="Measured on agentmods" height="20"></a>
Per session 79 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,475 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 $0.00079 $0.01475
Opus 5 $0.00039 $0.00737
Sonnet 5 $0.00016 $0.00295
Haiku 4.5 $0.00008 $0.00147

Measured 4d ago against content hash 39b4240f2dda, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

full-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/full-sprint/SKILL.md · 137 lines

How it starts

The opening of the file, as written. The whole thing — 137 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Full Sprint Execution

You are orchestrating a complete sprint cycle. Each phase runs in an isolated claude -p session for context isolation — the review MUST NOT have the build context (it biases the review).

IMPORTANT: This skill automates the same phase-by-phase workflow as the manual sprint cycle. Quality comes from context isolation, not from running everything in one session. Each phase runs via claude -p --dangerously-skip-permissions so all hooks fire (Stop runs tests, PostToolUse scans secrets, PreToolUse blocks denylisted commands and destructive git ops).

Step 1 — Load context

Read briefs/sprint-directive.md for the sprint scope and type. Read .claude/CLAUDE.md to get the project name and context.

Step 2 — Determine sprint number

Find the highest sprint number in tasks/sprints/ and use N+1. Create the directory: tasks/sprints/sprint-XX/

Step 3 — Execute phases

For each phase, run a separate claude -p session via Bash:

claude -p --dangerously-skip-permissions \
  "You are working on [project name]. \
   Read .claude/CLAUDE.md for project conventions. \
   Read .claude/skills/[skill]/SKILL.md and follow its instructions exactly. \
   Input: [input file path]. \
   Save output to tasks/sprints/sprint-XX/[output file]. \
   Run tests before declaring done."

Why claude -p without --bare: full hook enforcement applies — the Stop hook runs tests, PostToolUse scans for secrets, PreToolUse blocks denylisted commands and destructive git operations. The CLAUDE.md, rules, and skills load automatically, so the agent gets the full project context without us having to inline everything in the prompt.

The previous v3.x recommendation to use --bare for "~10x SDK startup performance" was retired in v4.0 because the trade-offs (hooks skipped, API-only auth that breaks Claude Max OAuth, missing CLAUDE.md/rules auto-load) outweighed the startup gain. The --dangerously-skip-permissions flag alone gives the same non-interactive behavior with all guarantees preserved.

Read the full file on GitHub · 137 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 · 137 lines · 79 tokens per session scan A 39b4240f2dda

Subscribe to this mod's changes

full-sprint is a skill published in the GitHub repository rbah31/claude-code-workflow (5 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 79 tokens to every session and 1,475 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 2026-08-31.