launch-worker

A command for manually starting headless workers, which are automated agents that work on GitHub issues without a user interface.

In plain words
What is it for?
Use it to launch one or more workers for GitHub issues, choose an agent or model, specify a repository, or preview the dispatch with a dry run.
Why use it?
It lets an operator start, retry, preview, or batch issue work when workers should run immediately instead of waiting for a scheduled cycle.

Command for Codex

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/marcusquinn/aidevops/launch-worker
Clone the repo
git clone --depth 1 https://github.com/marcusquinn/aidevops

Made for: Codex.

Per session 14 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 621 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 $0.00014 $0.00621
Opus 5 $0.00007 $0.00311
Sonnet 5 $0.00003 $0.00124
Haiku 4.5 $0.00001 $0.00062

Measured 2d ago against content hash 2b2ef7ba564f, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

launch-worker 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.

.agents/scripts/commands/launch-worker.md · 81 lines

How it starts

The opening of the file, as written. The whole thing — 81 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Args: $ARGUMENTS<issue|issue,issue> [owner/repo] [--model <id>] [--agent <name>] [--batch <list>] [--dry-run]

owner/repo is optional. When omitted, aidevops launch-worker resolves the current git repository from origin and dispatches against that repo.

What this does

Runs the first-class manual worker launcher:

aidevops launch-worker $ARGUMENTS

Use it when an operator needs to start workers intentionally instead of waiting for the next pulse cycle: smoke-testing a new issue, retrying after fixing a dispatch blocker, or launching a controlled batch with a specific model.

Syntax

# Preview one dispatch without launching, using the current git repo
aidevops launch-worker 22259 --dry-run

# Preview one dispatch without launching, using an explicit repo
aidevops launch-worker 22259 marcusquinn/aidevops --dry-run

# Launch one issue with default agent Build+ in the current repo
aidevops launch-worker 22259

# Launch multiple issues in the current repo with repeated issue arguments
aidevops launch-worker 22259 22260 22261

# Batch launch multiple issues in the current repo
aidevops launch-worker --batch 22259,22260 --dry-run

# Force a model and agent
aidevops launch-worker 22259 marcusquinn/aidevops \
  --model anthropic/claude-opus-4-7 --agent Build+

# Batch launch against an explicit repo
aidevops launch-worker --batch 22259,22260 marcusquinn/aidevops --dry-run

# Status for the current repo
aidevops launch-worker status 22259

Safety expectations

The launcher delegates to dispatch-single-issue-helper.sh dispatch, preserving the manual-dispatch ceremony: issue must be open, parent tasks are blocked, dedup is checked fail-closed, status moves to status:queued, origin:worker is applied, the runner is assigned, a worktree is created from origin/<default>, and the dispatch ledger is registered.

Output

Successful real launches print:

Read the full file on GitHub · 81 lines

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 · 81 lines · 14 tokens per session scan A 2b2ef7ba564f

Subscribe to this mod's changes

launch-worker is a command published in the GitHub repository marcusquinn/aidevops (391 stars, last pushed 2d ago), licensed MIT. It adds 14 tokens to every session and 621 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.