autoloop

autoloop is a skill for Claude Code from jun0-ds/sonmat. It costs 44 tokens per session (5,476 once invoked), scanned A, original, BSD-3-Clause.

A repeatable work cycle that plans a task, defines the expected result, carries it out, checks the result, records useful findings, and repeats when needed.

In plain words
What is it for?
It helps manage multi-step work, inspect prior session notes, verify changes, decide whether to continue or escalate, and save relevant context.
Why use it?
It gives complex coding tasks a consistent process and identifies when more planning, checking, or user input is needed.

Skill for Claude Code

Written for Claude Code: user-invocable in frontmatter. Also seen: mentions CLAUDE.md; mentions subagents; mentions Claude Code.

Part of the sonmat plugin — 6 skills, 3 agents, 1 hook shipped together

Good fit It helps manage multi-step work, inspect prior session notes, verify changes, decide whether to continue or escalate, and save relevant context.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/jun0-ds/sonmat/autoloop
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.

Any agent
npx skills add jun0-ds/sonmat --skill autoloop
Clone the repo
git clone --depth 1 https://github.com/jun0-ds/sonmat

Made for: Claude Code.

Or install sonmat, the plugin that ships this one along with the rest of its 6 skills, 3 agents, 1 hook.

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 autoloop

README.md
[![agentmods](https://agentmods.dev/badge/skills/jun0-ds/sonmat/autoloop/github.svg)](https://agentmods.dev/skills/jun0-ds/sonmat/autoloop)
Your own site
<a href="https://agentmods.dev/skills/jun0-ds/sonmat/autoloop"><img src="https://agentmods.dev/badge/skills/jun0-ds/sonmat/autoloop/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.

agentmods 80×15 button for autoloop

Your own site · 80×15
<a href="https://agentmods.dev/skills/jun0-ds/sonmat/autoloop"><img src="https://agentmods.dev/badge/skills/jun0-ds/sonmat/autoloop.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 44 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 5,476 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 $0.00044 $0.05476
Opus 5.5 $0.00018 $0.02190
Sonnet 5.5 $0.00009 $0.01095
Haiku 4.5 $0.00004 $0.00548

Measured today against content hash d55da8c43efe, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

autoloop 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 today.

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.

skills/autoloop/SKILL.md · 383 lines

How it starts

The opening of the file, as written. The whole thing — 383 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Autoloop — Autonomous Loop Protocol

0. Entry Routing

On receiving a task, judge complexity:

Signal L0 (direct) Full loop
Files to modify 1 Multiple
Iteration needed One-shot Expected

L0: Skip planning questions and definition. Apply core.md + hints.md → execute → verify → done. Escalate to full loop if a trigger fires.

Full loop: Proceed to section 1.

Bridge-note check: Before starting any task, check if the sonmat bridge note exists (bridge-note.md in $SONMAT_PROJECTS_BASE/<slug>, default ~/.sonmat/projects/<slug>/ where <slug> is the cwd path with /→-; legacy .claude/sonmat/ as fallback). If relevant context is found, incorporate it silently. Mention to user only if directly relevant to the new task.

1. Planning Questions

When no loop definition exists, build one through conversation. Ask 2-3 at a time, not all at once.

Required Questions

# Question Collects
1 What is the end goal? loop.name + objective
2 Which files/scope to modify? loop.modify
3 How to run after modification? loop.run
4 How to evaluate results? loop.evaluate
5 Keep/discard/refine criteria? loop.judge
6 Constraints? (off-limits files, time, preservation zones) loop.constraints
7 When to stop? loop.exit

Skip rules

  • Already answered in task description → fill without asking.
  • Clearly inferable from context → fill without asking.
  • At minimum, secure modify, run, evaluate.

Confirmation

Show the loop definition YAML and get user approval before starting. For L0 tasks: one-line summary suffices — "Proceeding like this: [summary]. Object if not." Silence after the L0 notice permits ordinary execution under the raw request but does not create an approved-baseline envelope; that envelope requires an explicit user approval turn.

Approval freezes the displayed definition as the execution baseline; preserve the exact display together with the raw approval turn. It does not amend a standing contract omitted from the definition. New evidence may change implementation details within that baseline. If it would instead change the approved objective, loop.modify, loop.constraints, or loop.judge — or restore behavior the baseline explicitly removed — show the current baseline and proposed revision and get reapproval before executing the revision. A safety or privacy conflict pauses execution but does not select a fallback on the user's behalf.

Read the full file on GitHub · 383 lines

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. today Changed · +4 tokens per session d55da8c43efe
  2. 1mo ago Changed · +1 lines 9b54603893f0
  3. 1mo ago Changed 8b2ab15349b2
  4. 1mo ago Changed 95a54f8b3e5e
  5. 2mo ago Changed · +7 lines 4b575017fb51
  6. 2mo ago First seen · 375 lines · 40 tokens per session scan A fc20a77d2743

Subscribe to this mod's changes

autoloop is a skill published in the GitHub repository jun0-ds/sonmat (5 stars, last pushed yesterday), licensed BSD-3-Clause. It adds 44 tokens to every session and 5,476 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 2026-08-31.

Related

autoloop compared with skills from other repositories

autoloop next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
autoloopjun0-ds/sonmatSkill5yesterdayBSD-3-ClauseA44Claude Code
huedominikmartn/hueSkill900yesterdayMITA84Claude Code, Codex
example-feature-generatorqf-studio/navigatorSkill3562d agoMITA33Claude Code
authentication-patternstravisjneuman/.claudeSkill108yesterdayMITA28Claude Code
electron-desktoptravisjneuman/.claudeSkill108yesterdayMITA38Claude Code
content-repurposertravisjneuman/.claudeSkill108yesterdayMITA43Claude Code
impact-report-writertravisjneuman/.claudeSkill108yesterdayMITA43Claude Code