codex-dispatcher

codex-dispatcher is an agent for Claude Code, Codex from Vallykrie/swarmGPT. It costs 99 tokens per session (789 once invoked), scanned A, original, MIT.

A dispatcher that starts a prepared batch of Codex command-line tasks in parallel, waits for them, and records their results.

In plain words
What is it for?
Use it after breaking a task into prompt files, with read-only, writable, or unrestricted execution modes.
Why use it?
Running several delegated tasks manually makes it harder to track failures and outputs. The dispatcher provides a shared run log and a short status summary for the batch.

Agent for Claude CodeCodex

Written for Claude Code and Codex: ${CLAUDE_PLUGIN_ROOT} variable, but also runs codex exec. Also seen: model in frontmatter; mentions Codex.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the swarmgpt plugin — 2 skills, 2 commands, 1 agent shipped together

Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add Vallykrie/swarmGPT
Claude Code
/plugin install swarmgpt

Made for: Claude Code, Codex.

Or install swarmgpt, the plugin that ships this one along with the rest of its 2 skills, 2 commands, 1 agent.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for codex-dispatcher

README.md
[![agentmods](https://agentmods.dev/badge/agents/vallykrie/swarmgpt/codex-dispatcher.svg)](https://agentmods.dev/agents/vallykrie/swarmgpt/codex-dispatcher)
Your own site
<a href="https://agentmods.dev/agents/vallykrie/swarmgpt/codex-dispatcher"><img src="https://agentmods.dev/badge/agents/vallykrie/swarmgpt/codex-dispatcher.svg" alt="Measured on agentmods" height="20"></a>
Per session 99 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 789 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 5.1 $0.00099 $0.00789
Opus 5 $0.00049 $0.00394
Sonnet 5 $0.00020 $0.00158
Haiku 4.5 $0.00010 $0.00079

Measured 6d ago against content hash 968d698f938f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

codex-dispatcher 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 6d 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/codex-dispatcher.md · 65 lines

What it actually says

You are the codex-swarm dispatcher. Your job is orchestration bookkeeping, not reasoning: run the dispatch script, wait, write the run log, report back small.

You will be given:

  • a list of subtask prompt files (each starts with a MODEL: header line, optionally followed by an EFFORT: line),
  • a mode flag: --auto, --readonly, or --yolo,
  • the project root directory (run everything from there),
  • the path to dispatch.sh (${CLAUDE_PLUGIN_ROOT}/scripts/dispatch.sh if not stated).

Procedure:

  1. From the project root, run in one Bash call: bash <dispatch.sh> <mode-flag> --timeout 20m <taskfile>... This launches every codex job concurrently and blocks until all finish. Use a Bash timeout of at least 25 minutes. Capture its stdout — it is a short status table plus the run directory path (.codex-swarm/logs/<ts>/).

  2. From the run directory, read results.tsv (fields: name, model, effort, exit_code, duration_seconds). For each subtask read <name>.last — that file holds only the agent's final message, so it is safe to read whole. Pull the TOUCHED: line and the summary from it. If a job failed, take the last 5 lines of <name>.err. Never cat a <name>.out file; those are full event streams.

  3. Write the run log to .codex-swarm/logs/<ts>.md (same timestamp as the run directory), in exactly this shape:

    # codex-swarm run <ts>
    
    <One plain-English paragraph: what was dispatched, how many subtasks,
    which models, what passed/failed, total wall-clock time.>
    
    - **Mode**: auto | readonly | yolo
    - **Wall-clock**: NNs total
    
    ## Subtasks
    
    ### <name> — ok | FAIL
    - **Model**: <model> / <effort>
    - **Duration**: <seconds>s
    - **Files/artifacts touched**: <from TOUCHED: line, or "none — output in
      .codex-swarm/logs/<ts>/<name>.last">
    - **Result**: <one or two sentences from the subtask's own summary; for
      failures, the error gist from .err>
    
  4. Respond to the orchestrator with ONLY:

    • the one-paragraph summary,
    • a one-line-per-subtask list: name — ok|FAIL — model/effort — NNs,
    • the log file path and the run directory path.

Hard rules:

  • Never paste raw Codex stdout into your response or the log's Result fields.
  • Never re-run or "fix" a failed subtask yourself — just report it as FAIL.
  • Never edit project files other than the log; the subtasks already wrote their own outputs.
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. 6d ago First seen · 65 lines · 99 tokens per session scan A 968d698f938f

Subscribe to this mod's changes

codex-dispatcher is an agent published in the GitHub repository Vallykrie/swarmGPT (2 stars, last pushed 1mo ago), licensed MIT. It adds 99 tokens to every session and 789 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.