loop

A command that runs one work-discovery cycle across enrolled repositories, or keeps running in watch mode. A repository is a project tracked by version control.

In plain words
What is it for?
Use it to discover repository work, run it in a sandbox, create pending inbox proposals, simulate routing with dry-run, or continuously monitor with watch mode.
Why use it?
It gathers and routes possible work without applying changes automatically, so you can review proposed work first.

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/ashlrai/ashlr-plugin/loop
Clone the repo
git clone --depth 1 https://github.com/ashlrai/ashlr-plugin
Per session 21 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 298 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 $0.00021 $0.00298
Opus 5 $0.00010 $0.00149
Sonnet 5 $0.00004 $0.00060
Haiku 4.5 $0.00002 $0.00030

Measured yesterday against content hash dd18e7b025aa, 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 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/loop.md · 41 lines

What it actually says

Runs the ashlr fleet conductor over every enrolled repo: discovers work, routes each item across the polyglot backend roster by trust tier, runs it sandboxed, and files PENDING inbox proposals. Default is one tick (safe — will not hang the terminal). Nothing is applied until you review via ashlr inbox.

The conductor is goal-aware: active goals are prioritised over the general backlog. The kill-switch (~/.ashlr/KILL) and daily budget are respected; auto-merge and intelligence posture are read from your config at runtime.

Usage

/loop [--watch] [--dry-run]

Flags:

  • --watch — run the continuous loop (Ctrl-C to stop). Default: one tick.
  • --dry-run — simulate work discovery and routing without spawning any engine runs.

Steps

Run the following Bash command and relay its output verbatim:

ashlr loop $ARGUMENTS

After the command completes, relay the final summary line from the output and add exactly one reminder line:

Any proposals filed await review in ashlr inbox — nothing was applied.

No preamble, no trailing summary beyond the above reminder.

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 · 21 tokens per session scan A dd18e7b025aa

Subscribe to this mod's changes

loop is a command published in the GitHub repository ashlrai/ashlr-plugin (3 stars, last pushed yesterday), licensed MIT. It adds 21 tokens to every session and 298 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.