loop

A control protocol for repeatedly asking a separate coding agent to work toward a specified repository goal. A repository is the project folder containing code and its change history.

In plain words
What is it for?
Running a delegated coding task in rounds, checking whether the repository reaches the requested state, and stopping only after completion is verified.
Why use it?
It keeps unfinished work moving through repeated attempts and requires a fresh verification pass before treating the goal as complete.

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/breezewish/codexpotter/loop
Any agent
npx skills add breezewish/CodexPotter --skill loop
Clone the repo
git clone --depth 1 https://github.com/breezewish/CodexPotter

Made for: Claude Code, Codex.

Per session 11 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,683 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 $0.00011 $0.02683
Opus 5 $0.00005 $0.01341
Sonnet 5 $0.00002 $0.00537
Haiku 4.5 $0.00001 $0.00268

Measured 2d ago against content hash 1af78502ebef, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

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.

skills/loop/SKILL.md · 271 lines

How it starts

The opening of the file, as written. The whole thing — 271 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CodexPotter Loop

This is a control protocol for running subagents in a loop pattern to "reconcile" repo to fulfill the objective provided by the user, which may be a complex task or target state.

Subagents own all task execution. You only coordinate the loop.

Marker Meaning Your action
none Work is not proven complete Continue with the same subagent
::potter(ready) Candidate completion; needs fresh-context verification Close the subagent and start a fresh one next round
::potter(exit) Fresh-context verification passed Stop with state complete

Control parameter:

  • rounds=N (default 10): maximum counted rounds

Your rules:

  • Do only the control actions this skill explicitly requires.
  • Do NOT implement, review, fix, test, or inspect repository.
  • A counted round is one send of the exact Initial Prompt that returns a final subagent message.
  • Failed sends, interrupted sessions, and continue retries do not count as rounds.
  • Reach Limit Prompt does not count as a round.
  • Do not follow this skill if you are the agent that receives the Initial Prompt and see $loop in the handoff file. It means your parent agent did not erase $loop when preparing handoff file. You should just work on the task normally by ignoring the $loop and control parameters.

1. Handoff

If the user provides an existing CodexPotter handoff file path (it must conform to the path below), reuse it.

Otherwise create a new handoff file:

.codexpotter/projects_v3/{yyyy}_{mm}_{dd}_{slug}.md

where:

  • {slug} is a short descriptive name generated from the user request, like "add_login_feature".

Use a path relative to the current repo/worktree root. Do not overwrite an existing file.

For a new file, write:

# Objective

## Original User Request

<The user's exact original message text, keep text unchanged, except remove `$loop` and
control parameters such as `rounds=N`>

## Important Context, Constraints, and User Preferences

<Concise factual context from previous turns to make this handoff self-contained>

## Critical Data, Examples, and References

<Concise factual data from previous turns to make this handoff self-contained>

# Done

Read the full file on GitHub · 271 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 · 271 lines · 11 tokens per session scan A 1af78502ebef

Subscribe to this mod's changes

loop is a skill published in the GitHub repository breezewish/CodexPotter (630 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 11 tokens to every session and 2,683 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.