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/structured-outputnpx skills add Archive228/loopkit --skill structured-outputgit 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 | $0.00040 | $0.00787 |
| Opus 5 | $0.00020 | $0.00394 |
| Sonnet 5 | $0.00008 | $0.00157 |
| Haiku 4.5 | $0.00004 | $0.00079 |
Grade A, and why
structured-output 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 — 55 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Structured Output
Prompted JSON — "reply as JSON" in the system prompt — fails on ~2-8% of calls in the wild: stray prose before the object, trailing commas, unescaped quotes, code fences. That failure rate is fine for a demo and fatal for a loop that runs a thousand times.
The hierarchy — use the strongest that fits
-
Tool use with schema (best) — declare a tool with a JSON Schema for its input. Force the model to call that tool. The API validates the arguments against the schema before you see them. Malformed JSON never leaves the model. Use this whenever the downstream is a real parser.
-
JSON mode /
response_format(good) — where supported. Guarantees a valid JSON object at the top level; does not guarantee schema conformance. Cheap upgrade over prompted-JSON. -
Prompted JSON with strict rules (fallback) — for models/tiers without tool use. Say "output ONLY the JSON object, no code fences, no prose", give an example, and validate on receive. Assume ~5% failure and handle it.
The validate-and-retry pattern
call → parse → if fail: retry once with the parse error appended → parse → if fail: hard fail
- One retry, not a loop. If the model can't produce it in two tries, the schema is too complex or the prompt is wrong. Log and stop.
- Feed the parse error back verbatim on retry — the model will fix specific issues ("expected string at line 3") that it can't guess from a generic "please try again".
- Never silently coerce. If a required field is missing, fail loudly. Auto-defaults hide prompt bugs.
Schema design — keep it flat
- Flat objects beat nested. Every level of nesting is another chance to hallucinate.
- Enums over free strings.
"severity": "high|medium|low"not"severity": "...". - Optional fields default to null explicitly in the schema. Don't ask the model to "omit if unknown".
- No
additionalProperties: truewithout a reason. If the model can add fields, it will, and they'll be inconsistent.
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 · 55 lines · 40 tokens per session scan A 76efd03f57ad
structured-output is a skill published in the GitHub repository Archive228/loopkit (753 stars, last pushed 1mo ago), licensed MIT. It adds 40 tokens to every session and 787 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…