auto-continue-loop

A work-discipline guide for letting an agent continue through a task while stopping at defined approval gates. It uses priority cycles, test verification, parked blocked issues, owner decision briefs, and audit logs.

In plain words
What is it for?
Use it to organise repeated development cycles, run real tests, process critical-to-low priority issues, park blocked work, and resume from an audit log.
Why use it?
It structures long-running agent work so issues are handled by priority and blocked decisions are recorded instead of being silently skipped.

Skill for Claude CodeCodex

Part of the skill-olympus plugin — 13 skills, 2 commands, 41 agents 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/dannykkh/skill-olympus/auto-continue-loop
Any agent
npx skills add Dannykkh/skill-olympus --skill auto-continue-loop
Clone the repo
git clone --depth 1 https://github.com/Dannykkh/skill-olympus

Made for: Claude Code, Codex.

Or install skill-olympus, the plugin that ships this one along with the rest of its 13 skills, 2 commands, 41 agents.

Per session 328 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 13,489 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. Scan, not verified.
Origin unknown 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 $0.00328 $0.13489
Opus 5 $0.00164 $0.06744
Sonnet 5 $0.00066 $0.02698
Haiku 4.5 $0.00033 $0.01349

Measured 3d ago against content hash d73620f472b0, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade B, and why

auto-continue-loop scanned grade B with 1 finding 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 3d ago.

The scan reads SKILL.md. This mod also ships 6 executable files (scripts/cancel-loop.ps1, scripts/cancel-loop.sh, scripts/continue-loop.ps1, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

`sync-gemini-assets.js`가 훅을 복사하고, `~/.gemini/settings.json`의 **AfterAgent** 이벤트에 `loop-stop.ps1|sh`가 등록됩니다.
skills/auto-continue-loop/SKILL.md · 702 lines

The source is not reproduced here

No licence file

A repository with no LICENSE is all rights reserved by default, so the body is not copied here. The metadata, the measurements and the link are.

Read it on GitHub

Files

What ships with it

8 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.

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. 3d ago First seen · 702 lines · 328 tokens per session scan B d73620f472b0

Subscribe to this mod's changes

auto-continue-loop is a skill published in the GitHub repository Dannykkh/skill-olympus (5 stars, last pushed 9d ago), with no licence file. It adds 328 tokens to every session and 13,489 once invoked, about $0.0016 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.