task-loop-feature

A command for repeating a development cycle: write code, fix problems, add tests, and run them until the task passes its acceptance requirements. TDD means developing with tests as a central check, but this description only confirms a repeated code-and-test loop.

In plain words
What is it for?
Tasks where the user asks the agent to keep coding, fixing, and testing until everything passes and the acceptance criteria are met.
Why use it?
It reduces the need to stop after one attempt when the code still fails tests or does not meet the agreed requirements.

Command for Claude Code

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 commands/acegalaxy-co/ace_commons-ccswitch-cli/task-loop-feature
Clone the repo
git clone --depth 1 https://github.com/acegalaxy-co/ace_commons-ccswitch-cli

Made for: Claude Code.

Per session 98 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 888 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. 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 $0.00098 $0.00888
Opus 5 $0.00049 $0.00444
Sonnet 5 $0.00020 $0.00178
Haiku 4.5 $0.00010 $0.00089

Measured yesterday against content hash 06f66013242b, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

task-loop-feature 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 yesterday.

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.

.claude/commands/task-loop-feature.md · 41 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

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. yesterday First seen · 41 lines · 98 tokens per session scan A 06f66013242b

Subscribe to this mod's changes

task-loop-feature is a command published in the GitHub repository acegalaxy-co/ace_commons-ccswitch-cli (2 stars, last pushed 16d ago), with no licence file. It adds 98 tokens to every session and 888 once invoked, about $0.0005 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.