run-loop

A command that repeatedly works through the tasks in an implementation plan. For each task it follows the project workflow, including branching, building, opening a draft pull request, verification, and checkpoints, and it stops when the target, a safety limit, or the budget is reached.

In plain words
What is it for?
Running a multi-task implementation plan unattended until the work is complete or a defined stop condition occurs.
Why use it?
It reduces the need to manually start each planned task and keeps progress tied to the project’s documented workflow. It never merges pull requests.

Command

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/affectionatec/agentic-engineering/run-loop
Clone the repo
git clone --depth 1 https://github.com/affectionatec/agentic-engineering
Per session 50 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 173 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 $0.00050 $0.00173
Opus 5 $0.00025 $0.00086
Sonnet 5 $0.00010 $0.00035
Haiku 4.5 $0.00005 $0.00017

Measured yesterday against content hash e72e50db8cd4, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

run-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 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.

commands/run-loop.md · 9 lines

What it actually says

Invoke the agentic-engineering:run-loop skill with this target: $ARGUMENTS

The skill carries the full loop protocol — target parsing, preconditions, the per-task loop body, stop conditions, wind-down, and hard rules. Follow it exactly. (This command is a thin alias so /run-loop works in Claude Code; the skill is the single source of truth and also serves harnesses that load skills but not plugin commands.)

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 · 9 lines · 0 tokens per session scan A e72e50db8cd4

Subscribe to this mod's changes

run-loop is a command published in the GitHub repository affectionatec/agentic-engineering (4 stars, last pushed 2mo ago), licensed MIT. It adds 50 tokens to every session and 173 once invoked, about $0.0003 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.