llm-self-loop

llm-self-loop is a skill for Claude Code, Codex from OutlineDriven/odin-claude-plugin. It costs 56 tokens per session (1,334 once invoked), scanned A, original, Apache-2.0.

A method for replacing human actions inside an iteration loop with local commands, files, logs, or explicit checks. An iteration loop is the repeated cycle of making a change, checking it, and trying again.

In plain words
What is it for?
It is for restructuring local workflows so they can reach a defined completion condition with fewer human interventions.
Why use it?
It removes repeated button clicks, dashboard checks, screenshot reviews, copy-paste steps, and other manual gates from the inner loop. Work that cannot be automated becomes a separate approval or handoff.

Skill for Claude CodeCodex

Written for Claude Code and Codex: shipped in a Claude Code plugin, but also agents/openai.yaml present.

Part of the odin-agent plugin — 47 skills shipped together

Install

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.

agentmods
npx agentmods add skills/outlinedriven/odin-claude-plugin/llm-self-loop
Any agent
npx skills add OutlineDriven/odin-claude-plugin --skill llm-self-loop
Clone the repo
git clone --depth 1 https://github.com/OutlineDriven/odin-claude-plugin

Made for: Claude Code, Codex.

Or install odin-agent, the plugin that ships this one along with the rest of its 47 skills.

Wrote 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.

agentmods badge for llm-self-loop

README.md
[![agentmods](https://agentmods.dev/badge/skills/outlinedriven/odin-claude-plugin/llm-self-loop.svg)](https://agentmods.dev/skills/outlinedriven/odin-claude-plugin/llm-self-loop)
Your own site
<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="Measured on agentmods" height="20"></a>
Per session 56 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,334 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00056 $0.01334
Opus 5 $0.00028 $0.00667
Sonnet 5 $0.00011 $0.00267
Haiku 4.5 $0.00006 $0.00133

Measured 2d ago against content hash 8969e4ea1b8a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

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 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.

plugins/odin-agent/skills/llm-self-loop/SKILL.md · 54 lines

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

  1. 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.

  2. 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.

Read the full file on GitHub · 54 lines

Files

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.

Changes

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.

  1. 2d ago First seen · 54 lines · 56 tokens per session scan A 8969e4ea1b8a

Subscribe to this mod's changes

llm-self-loop is a skill published in the GitHub repository OutlineDriven/odin-claude-plugin (35 stars, last pushed yesterday), licensed Apache-2.0. It adds 56 tokens to every session and 1,334 once invoked, about $0.0003 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 2026-09-04.