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 skills add SunflowersLwtech/sunkit --skill loopify-requirementsgit clone --depth 1 https://github.com/SunflowersLwtech/sunkitWrote 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/sunflowerslwtech/sunkit/loopify-requirements)<a href="https://agentmods.dev/skills/sunflowerslwtech/sunkit/loopify-requirements"><img src="https://agentmods.dev/badge/skills/sunflowerslwtech/sunkit/loopify-requirements/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/sunflowerslwtech/sunkit/loopify-requirements"><img src="https://agentmods.dev/badge/skills/sunflowerslwtech/sunkit/loopify-requirements.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00104 | $0.00953 |
| Opus 5.5 | $0.00042 | $0.00381 |
| Sonnet 5.5 | $0.00021 | $0.00191 |
| Haiku 4.5 | $0.00010 | $0.00095 |
Grade A, and why
loopify-requirements 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 2mo 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 — 106 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Loopify Requirements
Turn a request into a loop contract: a bounded process that can wake up, inspect state, act, verify, report, and stop. Optimize for reliability before autonomy.
Core Rule
A requirement is not loop-ready until it answers:
- Goal: what outcome should repeatedly become true?
- Trigger: what starts or wakes the loop?
- State: what evidence does each iteration inspect?
- Scope: what may the agent read, change, or call?
- Verification: how does the loop know the work is correct?
- Escalation: when must it ask a human?
- Stop: when should it end, pause, or refuse to continue?
- Audit: what should be logged for later review?
If any answer is missing, produce a Not Loop-Ready section and fill the smallest safe next step.
Workflow
-
Classify the request
one_shot: solve once; loopification should produce a checklist or reusable prompt.scheduled: run on a cadence such as hourly, daily, weekly.event_driven: run on PR, alert, webhook, email, file change, or user message.monitor: watch for a condition and report or act.long_horizon: split work into iterations with state carryover.
-
Pick the autonomy level
L0: human-run checklist.L1: reusable prompt for manual runs.L2: supervised loop that proposes actions.L3: scheduled loop with read-only or low-risk writes.L4: event/API/GitHub-triggered routine with bounded writes.L5: autonomous write/merge/publish. Use only when verification, rollback, and escalation are explicit.
Default to the lowest level that solves the user’s problem.
-
Write the Loop Contract Use the user’s words, but convert vague wishes into observable state, allowed actions, and success checks. Separate facts, assumptions, open questions, and unsafe automation.
-
Rewrite the prompt Produce instructions an agent can run repeatedly. Include:
- role and goal,
- inputs to inspect,
- allowed tools and forbidden actions,
- step-by-step iteration,
- verification command or review check,
- report format,
- escalation and stop rules.
What ships with it
4 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 2mo ago First seen · 106 lines · 104 tokens per session scan A 31b053eb7e16
loopify-requirements is a skill published in the GitHub repository SunflowersLwtech/sunkit (13 stars, last pushed yesterday), licensed Apache-2.0. It adds 104 tokens to every session and 953 once invoked, about $0.0004 per session on Opus 5.5. 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
prompt-master
Generates optimized prompts for AI tools. Activates only when the user explicitly asks to write, fix, improve, or adapt a prompt for a specific AI tool (LLM, Cursor, Midjourney, image AI, video AI, coding agents, etc.). Does not activate for general conversation, coding tasks, document writing, or other…
blockrun
Pay-per-call access to AI models, real-time data, media generation and multi-chain RPC over x402 micropayments (USDC on Base, Solana or Arc), or a BlockRun account API key. No subscriptions. Start here when you have the BlockRun MCP installed and need to know WHICH tool answers a question, how the wallet works, or how…
flux2-lora-training
Plan or review LoRA and edit-training work specifically for FLUX.2 Klein or Qwen-Image-Edit, including paired datasets, trainer-version contracts, and held-out fidelity checks. Do not use for generic Stable Diffusion/DiT training, prompt authoring, or model serving; route those tasks to their specialized skill.
deepseek-provider-contract
Validate a proposed DeepSeek API integration before any key or project context is sent: check thinking-mode tool-call history, strict-schema assumptions, bounded output, and provider data boundaries. Use when integrating DeepSeek, adding DeepSeek tool calls or streaming, debugging DeepSeek 400 after a tool call, or…
llm-finops-router
Expert guide for AI FinOps, dynamic model routing (LiteLLM, Portkey, RouteLLM), cost optimization, budget enforcement, semantic caching, and latency-based fallback architectures / Panduan ahli untuk AI FinOps, routing model dinamis, optimasi biaya, penegakan anggaran, semantic caching, dan arsitektur fallback berbasis…
voice-ai-realtime-agent
Expert guide for Ultra-Low Latency Conversational Voice AI (<300ms), WebRTC bidirectional streaming, OpenAI Realtime API, Gemini Multimodal Live Audio, LiveKit Agents, and Semantic VAD / Panduan ahli AI suara percakapan real-time berlatensi ultra-rendah.