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 OutlineDriven/odin-claude-plugin --skill llm-self-loopgit clone --depth 1 https://github.com/OutlineDriven/odin-claude-pluginWrote 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/outlinedriven/odin-claude-plugin/llm-self-loop)<a href="https://agentmods.dev/skills/outlinedriven/odin-claude-plugin/llm-self-loop"><img src="https://agentmods.dev/badge/skills/outlinedriven/odin-claude-plugin/llm-self-loop/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/outlinedriven/odin-claude-plugin/llm-self-loop"><img src="https://agentmods.dev/badge/skills/outlinedriven/odin-claude-plugin/llm-self-loop.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00056 | $0.01334 |
| Opus 5.5 | $0.00022 | $0.00534 |
| Sonnet 5.5 | $0.00011 | $0.00267 |
| Haiku 4.5 | $0.00006 | $0.00133 |
Grade A, and why
llm-self-loop 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 1mo 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 — 54 lines — stays where its author put it; the contents beside it link to each section on GitHub.
LLM self loop
Contract
| Field | Bound contract |
|---|---|
| Trigger | A human explicitly invokes this skill for a task whose iteration loop depends on a button click, dashboard check, terminal or web interaction, screenshot inspection, copy-paste, secret entry, or human verdict. |
| Authority | Inspect the named workflow and make only reversible changes to its named local harness artifacts. Do not change credentials, paid services, published or deployed state, remote data, or external systems. |
| Side effect | Replace inner-loop human gates with local CLI triggers, file outputs, structured logs, or contract assertions, limited to the workflow and local artifacts named by the human. |
| Done | The loop reaches its asserted completion condition without an inner-loop human action, or every step that cannot be automated is removed from the inner loop and represented as one outer-loop approval or a discrete human handoff. |
Inputs
Required: the workflow or local harness to restructure; the command, click, observation, or verdict that currently requires a human; and the loop's intended completion condition.
Supply any existing local commands, endpoints, logs, metrics queries, schemas, tests, and output paths that expose the gate. Credentials and secret values are neither required nor accepted. An output path and rollback method are optional; when omitted, choose paths inside the named local workflow and preserve the prior files so each change can be reverted.
Procedure
-
Bound the work to the named workflow and local harness files. Record the files that may change and how each will be restored before writing anything; do not widen the scope to redesign the surrounding system. Done when: the files that may change are recorded with their restore methods.
-
Trace one iteration and name the smallest inner-loop gate: the exact human action, the signal the human contributes, where that signal or result currently lives, and the observable condition that permits the next iteration. Validate commands, paths, schemas, and machine-readable responses where they enter the harness; do not infer unavailable interfaces or evidence. Done when: the smallest inner-loop gate is named with its action, signal, location, and continuation condition.
What ships with it
1 file 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.
- 1mo ago First seen · 54 lines · 56 tokens per session scan A 8969e4ea1b8a
llm-self-loop is a skill published in the GitHub repository OutlineDriven/odin-claude-plugin (39 stars, last pushed 27d ago), licensed Apache-2.0. It adds 56 tokens to every session and 1,334 once invoked, about $0.0002 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 2026-09-04.
Other skills, from other repositories
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…
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…
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…
next-cache-components-optimizer
Optimize the meaningful UI available immediately from a Next.js route on an initial load (hard navigation) or named client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route and entry point at a time; the shipped test then guards…