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.
npx agentmods add skills/loopdive/js2/sprint-wrap-upnpx skills add loopdive/js2 --skill sprint-wrap-upgit clone --depth 1 https://github.com/loopdive/js2What 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.
| Model | Per session | Once 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 |
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.
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. Nevergit tag vX.Y.Zat sprint end. Version tags are cut exclusively vianode scripts/release.mjs <x.y.z>(the deliberate, reviewed release flow); seedocs/releasing.mdand loopdive/js2wasm#389.
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.
- 2d ago First seen · 196 lines · 32 tokens per session scan A 0bb88d95799e
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.
Other skills, from other repositories
migrate-oxfmt
Guide for migrating a project from Prettier or Biome to Oxfmt. Use when asked to migrate, convert, or switch a JavaScript/TypeScript project's formatter from Prettier or Biome to Oxfmt.
migrate-oxlint
Guide for migrating a project from ESLint to Oxlint. Use when asked to migrate, convert, or switch a JavaScript/TypeScript project's linter from ESLint to Oxlint.
insta-snapshots
Guide for working with and updating insta snapshot tests in Oxc without terminal interaction.
performance-lint-rules
Performance review guidance for Oxc linter rule implementations. Use only when reviewing Rust rule code under crates/oxclinter/src/rules/ or when explicitly auditing those rules for performance improvements.
oxc-docs
Comprehensive reference for the JavaScript Oxidation Compiler (Oxc) — a collection of high-performance JavaScript tools written in Rust. Covers parser design (lexer, AST, parser, errors, semantic analysis), architecture (parser, linter, test infrastructure, AST tools), ECMAScript specification and grammar, performance…
babel-docs
Babel 7.x/8.x — plugins, presets, config, @babel/core, parser, traverse, types, CLI, preset-env.