sprint-wrap-up

An end-of-sprint checklist for closing completed development work and preparing the repository for the next sprint.

In plain words
What is it for?
It helps verify tasks are merged or documented, clean worktrees and branches, update shared state, and confirm required tests ran.
Why use it?
It reduces leftover work, branches, worktrees, stale agent records, and missing final checks.

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/loopdive/js2/sprint-wrap-up
Any agent
npx skills add loopdive/js2 --skill sprint-wrap-up
Clone the repo
git clone --depth 1 https://github.com/loopdive/js2

Made for: Claude Code, Codex.

Per session 32 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,897 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 $0.00032 $0.01897
Opus 5 $0.00016 $0.00949
Sonnet 5 $0.00006 $0.00379
Haiku 4.5 $0.00003 $0.00190

Measured 2d ago against content hash 0bb88d95799e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

sprint-wrap-up 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.

.claude/skills/sprint-wrap-up/SKILL.md · 196 lines

How it starts

The opening of the file, as written. The whole thing — 196 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Sprint Wrap-Up

Run this when all sprint tasks are done or the sprint is being closed.

Step 1: Verify all tasks are merged or closed

# Check TaskList for any in_progress or pending tasks

For each unmerged task: either have the dev self-merge via /test-and-merge, or document why it's deferred.

Step 2: Clean up worktrees

ls /workspace/.claude/worktrees/

For each worktree:

  • Check for uncommitted work: git -C <wt> diff --stat
  • Check for unmerged commits: git -C <wt> log --oneline main..HEAD
  • If all merged: git worktree remove --force <wt>
  • If unmerged: document in the issue file as Suspended Work

Then prune dead agent-status heartbeats and resync the shared checkout:

node /workspace/scripts/prune-agent-status.mjs          # clears stale ✕ records
bash /workspace/scripts/sync-workspace-main.sh          # FF /workspace to origin/main

(prune-agent-status also runs automatically on every SessionStart; this is the belt-and-suspenders end-of-sprint sweep.)

Step 3: Clean up branches

git branch | grep -v '^\*'

Delete branches that are fully merged. Keep branches with unmerged work.

Step 4: Verify test262 ran on the final state

Check that test262 has been run on the current main (either via CI sharded run on the last merged PR, or a local run). Do NOT run locally unless CI didn't cover it.

# Check latest CI test262 run on main
gh run list --workflow=test262-sharded.yml --branch=main --limit 1
# Or check local results
node -e "const r=JSON.parse(require('fs').readFileSync('benchmarks/results/test262-current.json','utf8')); console.log(r.summary.pass, '/', r.summary.total)"

Record results in sprint doc.

Step 5: Push sprint/N end tag

git tag sprint/N  # replace N with sprint number
git push origin sprint/N

Sprint-end tags ONLY sprint/N — it does not tag a version. Never git tag vX.Y.Z at sprint end. Version tags are cut exclusively via node scripts/release.mjs <x.y.z> (the deliberate, reviewed release flow); see docs/releasing.md and loopdive/js2wasm#389.

Read the full file on GitHub · 196 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 · 196 lines · 32 tokens per session scan A 0bb88d95799e

Subscribe to this mod's changes

sprint-wrap-up is a skill published in the GitHub repository loopdive/js2 (59 stars, last pushed 2d ago), licensed Apache-2.0. It adds 32 tokens to every session and 1,897 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.