looper

A recurring work loop that follows a plan file until every listed task is complete.

In plain words
What is it for?
It reads the plan, completes remaining tasks, reports brief progress during the loop, and returns a configured completion word when finished.
Why use it?
It maintains progress across repeated runs and avoids stopping for confirmation unless something genuinely blocks the work.

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/pcopu/coco/looper
Any agent
npx skills add pcopu/coco --skill looper
Clone the repo
git clone --depth 1 https://github.com/pcopu/coco

Made for: Claude Code, Codex.

Per session 18 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 189 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 $0.00189
Opus 5 $0.00009 $0.00095
Sonnet 5 $0.00004 $0.00038
Haiku 4.5 $0.00002 $0.00019

Measured 2d ago against content hash d2e1ddf5f201, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

looper 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.

apps/looper/SKILL.md · 28 lines

What it actually says

Looper App

Use this app when a recurring plan loop is active for the topic.

Core behavior

  • Treat the referenced plan markdown file as the source of truth.
  • Continue executing tasks from that plan until all items are complete.
  • Keep progress focused and avoid asking for confirmation unless blocked.
  • When all work is complete, reply with exactly the configured completion keyword as a single word.

Response style during loop

  • For in-progress loop ticks, briefly summarize what was finished and what is next.
  • Keep momentum and proceed to the next plan steps immediately.
  • If blocked, state the blocker and the minimal unblock action.

Completion

  • Only emit the completion keyword when the plan is fully complete.
  • Do not include extra words, punctuation, or formatting around the keyword.
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 · 28 lines · 18 tokens per session scan A d2e1ddf5f201

Subscribe to this mod's changes

looper is a skill published in the GitHub repository pcopu/coco (4 stars, last pushed 8d ago), licensed MIT. It adds 18 tokens to every session and 189 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 2026-08-31.