agent-loop-ext

agent-loop-ext is a skill for Claude Code, Codex from jmagly/aiwg. It costs 18 tokens per session (2,542 once invoked), scanned A, original, MIT.

An external process that runs long, repeated coding-agent tasks and saves their progress to disk. The loop can continue after the original AI session stops.

In plain words
What is it for?
Use it for work lasting longer than one session, crash recovery, CI/CD integration, or several agent loops running at once.
Why use it?
It prevents lost progress when a session crashes or ends before the work is complete. It also supports tasks connected to automated build and deployment pipelines.

Skill for Claude CodeCodex

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/jmagly/aiwg/agent-loop-ext
Any agent
npx skills add jmagly/aiwg --skill agent-loop-ext
Clone the repo
git clone --depth 1 https://github.com/jmagly/aiwg

Made for: Claude Code, Codex.

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 agent-loop-ext

README.md
[![agentmods](https://agentmods.dev/badge/skills/jmagly/aiwg/agent-loop-ext.svg)](https://agentmods.dev/skills/jmagly/aiwg/agent-loop-ext)
Your own site
<a href="https://agentmods.dev/skills/jmagly/aiwg/agent-loop-ext"><img src="https://agentmods.dev/badge/skills/jmagly/aiwg/agent-loop-ext.svg" alt="Measured on agentmods" height="20"></a>
Per session 18 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,542 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 $0.00018 $0.02542
Opus 5 $0.00009 $0.01271
Sonnet 5 $0.00004 $0.00508
Haiku 4.5 $0.00002 $0.00254

Measured 4d ago against content hash e977e984fa43, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

agent-loop-ext 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 4d 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.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

agentic/code/addons/agent-loop/skills/agent-loop-ext/SKILL.md · 259 lines

How it starts

The opening of the file, as written. The whole thing — 259 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Skill access pattern (post-kernel-pivot, 2026.5+)

Skill names referenced in this document are AIWG skills, not slash commands. Most are not kernel-listed and cannot be invoked as /skill-name by the platform. Reach them via:

aiwg discover "<capability>"
aiwg show skill <name>

Only kernel-listed skills (aiwg-doctor, aiwg-refresh, aiwg-status, aiwg-help, use, steward) are directly invokable as slash commands. See skill-discovery rule.

Al External

You are the Al External Orchestrator — launching and managing crash-resilient iterative loops that run outside the AI session for long-running tasks.

Core Difference from ralph

ralph runs the loop inside the current AI session. agent-loop-ext (formerly ralph-external) launches the loop as an external process via tools/ralph-external/run.sh, persisting all state to .aiwg/ralph-external/. If the session dies mid-loop, the loop survives and can be reattached or resumed.

Use agent-loop-ext when:

  • The task will take longer than a single session
  • You need CI/CD pipeline integration
  • You want crash recovery guarantees
  • You need to run multiple loops in parallel

Natural Language Triggers

Users may say:

  • "agent-loop-ext"
  • "external agent loop"
  • "out-of-session loop"
  • "persistent agent loop"
  • "ralph external"
  • "external ralph"
  • "crash-resilient loop"
  • "persistent ralph"
  • "long-running ralph task"
  • "ralph with crash recovery"
  • "start background ralph"

Parameters

Objective (required)

The task the loop should accomplish. Passed as the first positional argument.

--completion (optional — inferred when omitted)

Success criteria as a verifiable command. The loop exits when this command returns exit code 0.

Good examples:

  • --completion "npm test passes with 0 failures"
  • --completion "npx tsc --noEmit exits with code 0"
  • --completion "coverage report shows >80%"

Read the full file on GitHub · 259 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. 4d ago First seen · 259 lines · 18 tokens per session scan A e977e984fa43

Subscribe to this mod's changes

agent-loop-ext is a skill published in the GitHub repository jmagly/aiwg (208 stars, last pushed today), licensed MIT. It adds 18 tokens to every session and 2,542 once invoked, about $0.0001 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 2026-08-30.