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/archive228/loopkit/init-script-contractnpx skills add Archive228/loopkit --skill init-script-contractgit clone --depth 1 https://github.com/Archive228/loopkitWhat 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 | $0.00035 | $0.01183 |
| Opus 5 | $0.00017 | $0.00592 |
| Sonnet 5 | $0.00007 | $0.00237 |
| Haiku 4.5 | $0.00003 | $0.00118 |
Grade A, and why
init-script-contract 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 — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Init Script Contract
Every coding session in a multi-session project starts by bringing the dev server up. If the entry point is named differently each time, or takes four minutes, or prompts for input, you burn tokens and wall-clock on every single session. The fix is a fixed set of script names at the project root with a hard contract. The initializer agent writes them once; every downstream session relies on them.
The names are load-bearing — [[shift-notes]] and [[broken-window-check]] both refer to them by name. Do not invent your own.
When to apply
- You are the initializer agent scaffolding a fresh project.
- You just discovered setup exceeds 120s and need to split cleanly.
- You are auditing an existing project whose sessions keep re-discovering how to launch the app.
The five scripts
| Script | Contract |
|---|---|
init.sh |
Clean clone → dev server up on localhost. Idempotent. Under 120s. Zero prompts. |
serve.sh |
Start the dev server only. Written when init.sh cannot fit under 120s. |
test.sh |
Run the full test suite. Exit non-zero on any failure. |
stop.sh |
Cleanly kill the dev server. Sessions run this before exiting. |
reset.sh |
Wipe local DB and ephemeral state. Leave code untouched. Used by [[broken-window-check]]. |
Procedure
- Pick the stack the spec implies. Do not scaffold Docker, CI, or lint configs the spec does not require.
- Write
init.shto run end-to-end from an empty clone. Pin every dependency (lockfile,==,Pipfile.lock). Answer every prompt non-interactively (-y,--yes,DEBIAN_FRONTEND=noninteractive). - Time it. Run
time ./init.shon a clean clone. If it exceeds 120s, split — move one-time setup intoinit.shand server launch intoserve.sh. Haveinit.shcallserve.shat the end so single-command startup still works. - Make it idempotent. Run
./init.shtwice back-to-back. If the second run errors or duplicates state, guard each step with existence checks (if [ ! -d node_modules ],createdb --if-not-exists, etc.). - Write
stop.shto kill by PID file or port, not by process name grep. Grep kills sibling agents on shared sandboxes. - Write
test.shwith a single end-to-end smoke test that provesinit.shproduced a serving app. No feature tests — those belong to future sessions. - Write
reset.shto drop and recreate the DB, clear caches, wipe/tmpartifacts. Never touch tracked files. - Verify from empty state.
git clean -fdx && ./init.sh && ./test.sh && ./stop.sh. Every script exits 0.
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 · 66 lines · 35 tokens per session scan A dfa332af1281
init-script-contract is a skill published in the GitHub repository Archive228/loopkit (753 stars, last pushed 1mo ago), licensed MIT. It adds 35 tokens to every session and 1,183 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…