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/thaitype/chief/loop-readinessnpx skills add thaitype/chief --skill loop-readinessgit clone --depth 1 https://github.com/thaitype/chiefWrote 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.
[](https://agentmods.dev/skills/thaitype/chief/loop-readiness)<a href="https://agentmods.dev/skills/thaitype/chief/loop-readiness"><img src="https://agentmods.dev/badge/skills/thaitype/chief/loop-readiness.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00087 | $0.01527 |
| Opus 5 | $0.00044 | $0.00763 |
| Sonnet 5 | $0.00017 | $0.00305 |
| Haiku 4.5 | $0.00009 | $0.00153 |
Grade A, and why
loop-readiness 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 — 122 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Loop readiness review
This is a readiness review, not a gate. It never produces a pass/fail verdict or a single overall score — it reports what's present, what's missing, and what to consider per dimension, so the person deciding whether to start the loop has the full picture.
A "loop" here means any agent/process that runs multiple iterations with no human checking every step — an autopilot, a scheduled job, a long-running agent workflow, or anything similar. The review looks at the plan for that loop, not the loop itself — nothing gets executed during this review.
Step 1: Get the plan
- If a plan was given — as text or a file path — use it.
- If not, use the
grill-designskill if available. Otherwise, interview the user one question at a time to build up an understanding of the plan — what it's trying to do, and how it's supposed to know if it's working. One question per turn, never ask a compound question.
Step 2: Review each dimension
Walk through all four. For each, note what's present, what's missing, and how deep the coverage is — there's no fixed checklist to fill in mechanically; use judgment about how much depth this specific loop actually needs.
2.1 Definition of Ready (DoR)
Is there something written down that defines what this loop is for and where its edges are? Depending on the loop, this could include: a goal statement, explicit non-goals / out-of-scope items, a contract (data shapes, API boundaries), a UI mock or diagram — go as deep as makes sense for the stakes involved. A one-line goal can be enough for a small loop; a loop that touches production data probably needs more.
2.2 Feedforward
Feedforward is guidance given to the loop before or during each iteration, to raise the odds it does the right thing in the first place — conventions docs, skills, contracts, bootstrap scripts, code-mod tooling, anything the loop reads or is constrained by while acting. Note whether this guidance is:
- Computational — a deterministic tool/script/generator it must go through
- Inferential — a doc/skill it reads and applies judgment to
- Both, or neither
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 · 122 lines · 87 tokens per session scan A f584fdb864db
loop-readiness is a skill published in the GitHub repository thaitype/chief (59 stars, last pushed today), licensed MIT. It adds 87 tokens to every session and 1,527 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 2026-09-03.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
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…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
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…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…