Agent skill

Dispatching To Codex

by ccplugins in ccplugins/awesome-claude-code-plugins

A skill your agent uses when the user explicitly asks to hand a task to Codex — "use codex", "delegate this", "send it to codex", "交给codex", "派给codex", or the /delegate command.

Apache-2.0Auto-check passedProduct & Project Management

Install Dispatching To Codex

skills CLI
$ npx skills add ccplugins/awesome-claude-code-plugins --skill dispatching-to-codex -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install ccplugins/awesome-claude-code-plugins dispatching-to-codex --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/ccplugins/awesome-claude-code-plugins.git skills-src && mkdir -p .claude/skills && cp -r skills-src/plugins/praetor/skills/dispatching-to-codex .claude/skills/dispatching-to-codex && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
dispatching-to-codex
GitHub stars
967
Token cost
~1.1k tokens
SKILL.md length
582 words
Files
2
Skills in repo
68
Repo updated
First seen
Licence
Apache-2.0

At a glance

A skill your agent uses when the user explicitly asks to hand a task to Codex — "use codex", "delegate this", "send it to codex", "交给codex", "派给codex", or the /delegate command.

  • Works in 3 steps: NO DISPATCH WITHOUT FROZEN ACCEPTANCE… → NO ACCEPTANCE WITHOUT A FRESH-CONTEXT… → MAX 2 RETRIES, THEN LOUD TAKEOVER. Every…
  • The user explicitly asks to hand a task to Codex — use codex
  • SKILL.md covers Iron Laws (no exceptions), Is it worth dispatching? (say…, Lifecycle and Red Flags — excuses that mean…
  • Runs Shell scripts from its folder; calls codex and git

What it does

Dispatching To Codex is an agent skill from ccplugins/awesome-claude-code-plugins. Use when the user explicitly asks to hand a task to Codex — "use codex", "delegate this", "send it to codex", "交给codex", "派给codex", or the /delegate command. Runs the full dispatch lifecycle with frozen acceptance criteria and a binding independent judge. NEVER auto-dispatch — delegation happens only on the user's word. If a task looks Codex-shaped (bulk mechanical edits, wide read-and-report analysis, test scaffolding), you may offer the option in ONE line; if the user doesn't take it, drop it.

Its SKILL.md is about 1.1k tokens, which your agent loads only when the skill is triggered. The skill folder holds 1 other file (for example `preflight.sh`).

It sits in Product & Project Management, covering Test generation and User stories. The repository describes itself as: Awesome Claude Code plugins — a curated list of slash commands, subagents, MCP servers, and hooks for Claude Code. The licence is Apache-2.0.

When your agent uses it

  • The user explicitly asks to hand a task to Codex — use codex
  • Send it to codex
  • The /delegate command

Example prompts

  • “use codex”
  • “delegate this”
  • “send it to codex”
  • “/dispatching-to-codex”

Requirements

  • A Bash shell

Workflow steps

3 steps, taken from the first numbered list in SKILL.md.

  1. NO DISPATCH WITHOUT FROZEN ACCEPTANCE CRITERIA COMMITTED TO GIT. If you cannot write a concrete pass/fail check, the task is not ready to…
  2. NO ACCEPTANCE WITHOUT A FRESH-CONTEXT JUDGE VERDICT. A FAIL cannot be overridden — not by you, not by "the diff looks fine".
  3. MAX 2 RETRIES, THEN LOUD TAKEOVER. Every failure path ends with you doing the work and telling the user delegation failed. Silent success…

What it can do on your machine

Read from SKILL.md and the folder at commit 5bd4f16. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Ships script files (Shell), which the agent can run.

    Shell commands in SKILL.md call:

    • codex
    • git

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md. Its commands use git, which can reach the network depending on how they are called.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Dispatching To Codex loads about 1.1k tokens when it runs. Until then it costs about 130 tokens; SKILL.md has 582 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~130
When it runs · the whole SKILL.md, loaded when a task matches
~1.1k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from ccplugins/awesome-claude-code-plugins at commit 5bd4f16, republished under its Apache-2.0 licence (© ccplugins). 582 words, ~1,141 tokens.

Download SKILL.mdSave it as .claude/skills/dispatching-to-codex/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.
name
dispatching-to-codex
description
Use when the user explicitly asks to hand a task to Codex — "use codex", "delegate this", "send it to codex", "交给codex", "派给codex", or the /delegate command. Runs the full dispatch lifecycle with frozen acceptance criteria and a binding independent judge. NEVER auto-dispatch — delegation happens only on the user's word. If a task looks Codex-shaped (bulk mechanical edits, wide read-and-report analysis, test scaffolding), you may offer the option in ONE line; if the user doesn't take it, drop it.

Dispatching to Codex

Claude is the brain; Codex is the hands. You plan, freeze the bar, and judge. Codex executes on its own quota, in its own process, so your context stays small and your tokens go to judgment — not grunt work.

Iron Laws (no exceptions)

  1. NO DISPATCH WITHOUT FROZEN ACCEPTANCE CRITERIA COMMITTED TO GIT. If you cannot write a concrete pass/fail check, the task is not ready to delegate — do it yourself.
  2. NO ACCEPTANCE WITHOUT A FRESH-CONTEXT JUDGE VERDICT. A FAIL cannot be overridden — not by you, not by "the diff looks fine".
  3. MAX 2 RETRIES, THEN LOUD TAKEOVER. Every failure path ends with you doing the work and telling the user delegation failed. Silent success is forbidden.

Is it worth dispatching? (say so BEFORE starting)

Dispatch overhead is real: branch + freeze + judge ≈ minutes of wall-clock and some of both quotas. If you could finish the task faster than the overhead, tell the user plainly: "This is faster for me to do directly — still want Codex on it?" Then respect their answer.

Good dispatches: bulk/repetitive edits, migrations, mechanical test-writing against a clear spec, wide "read everything, report back" analysis, output-heavy runs. Bad dispatches: design work, subtle debugging, anything ambiguous, tiny tasks.

Lifecycle

  1. Preflight. Run ${CLAUDE_SKILL_DIR}/preflight.sh. Not ready → one-line explanation (e.g. "run codex login once and I can dispatch"), then do the work yourself. Never nag twice in a session.

Analysis-only shortcut: if the dispatch edits NO files (wide read-and-report, investigation), skip ISOLATE/FREEZE/JUDGE — run codex exec --sandbox read-only and review the report yourself. The gate exists for merges, not for reading. Everything below is the write path.

  1. Isolate. git switch -c codex/<slug> — throwaway branch; main is never touched.
  2. Freeze. Write .codex/ACCEPTANCE.md: one-line GOAL + the exact commands that must pass (exit codes, not vibes). Commit it BEFORE Codex exists. See skills/writing-codex-briefs for the format.
  3. Brief + dispatch. Self-contained brief (Codex sees zero chat history). Stock config: codex exec -m gpt-5.5 -c model_reasoning_effort="xhigh" --sandbox workspace-write "<brief>" 2>/dev/null Model/effort overrides, in priority order: PRAETOR_MODEL / PRAETOR_EFFORT env vars (use verbatim if set) → preflight reported config=custom (active relay provider: DROP the -m/-c flags, keep --sandbox, respect their config) → stock default above. Never danger-full-access. Always a hard timeout. Big output → -o <file>, never into your context.
  4. Judge. Spawn a FRESH subagent with agents/codex-judge.md + repo path + branch name. Codex's work is UNCOMMITTED — the judge reviews the working tree (git diff HEAD), runs every frozen check, checks the bar wasn't moved. Returns PASS or FAIL + evidence.
  5. Resolve. PASS → you commit (Codex never commits), report in plain language, append the ledger. FAIL → re-brief with codex exec resume --last "<fix>" (≤2 retries) or take over loudly.
  6. Cleanup. Merge or delete the branch. Append one line to .codex/ledger.jsonl: {task, model, verdict_history, wall_seconds, dispatched_at}.
Show full SKILL.md (121 more words)Show less

Kill switch: a STOP file in the repo root halts all dispatching — check before every dispatch.

Red Flags — excuses that mean STOP

ExcuseReality
"The diff looks obviously fine, skip the judge"Obvious diffs are where silent regressions hide. Law 2.
"No time to write acceptance criteria"Then there's no way to know Codex succeeded. Law 1.
"One more retry will fix it"Retry 3+ burns both quotas for a coin flip. Law 3.
"Codex said tests pass"Codex reporting ≠ judge verifying. Only exit codes count.
"It's just a small task, skip the branch"Small tasks on main are how main breaks. Isolate or don't dispatch.
"User probably wants this delegated"Probably ≠ said so. Offer in one line, then drop it.

© ccplugins, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 1 other file in plugins/praetor/skills/dispatching-to-codex of ccplugins/awesome-claude-code-plugins.

  • SKILL.md
  • preflight.sh

Open the folder on GitHubat commit 5bd4f16

Compare with similar skills

Dispatching To Codex next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Dispatching To Codex compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Dispatching To Codex this skillccplugins/awesome-claude-code-plugins967—~1.1kAutomated safety check: PassApache-2.0
Review Rfcnurettincoban/ai-prd-workflow298—~1.4kAutomated safety check: PassMIT
QA Handoff Packagemohitagw15856/pm-claude-skills1.4k—~1.1kAutomated safety check: PassMIT
Test Scenariosphuryn/pm-skills27k—~866Automated safety check: PassMIT
Test Authorjpicklyk/task-orchestrator207—~8.2kAutomated safety check: PassMIT
Test Case Writermohitagw15856/pm-claude-skills1.4k—~970Automated safety check: PassMIT

Similar skills

  • Review Rfc

    nurettincoban/ai-prd-workflow

    Review an implemented RFC in a fresh context against its acceptance criteria, RULES.md and the test plan, and save the review to reviews/.

    298 GitHub stars~1.4k tokensUpdated 6 days ago
    Product & Project ManagementAuto-check passed
  • QA Handoff Package

    mohitagw15856/pm-claude-skills

    Turn a story and its change into a clean 'ready for QA' package — test scenarios, edge cases, the data and environment setup, and what's explicitly out of scope.

    1.4k GitHub stars~1.1k tokensUpdated yesterday
    Product & Project ManagementAuto-check passed
  • Test Scenarios

    phuryn/pm-skills

    Create comprehensive test scenarios from user stories with test objectives, starting conditions, user roles, step-by-step actions, and expected outcomes.

    27k GitHub stars~866 tokensUpdated 22 days ago
    Testing & QAAuto-check passed
  • Test Author

    jpicklyk/task-orchestrator

    Test authoring framework for items carrying the needs-test-author trait.

    207 GitHub stars~8.2k tokensUpdated yesterday
    Testing & QAAuto-check passed
  • Test Case Writer

    mohitagw15856/pm-claude-skills

    Turn a requirement or user story into clear, executable test cases.

    1.4k GitHub stars~970 tokensUpdated yesterday
    Testing & QAAuto-check passed
  • Argent QA Flows

    bbplayer-app/BBPlayer

    Create repeatable QA regression E2E tests as Argent flows from test cases, tickets, or acceptance criteria.

    1.1k GitHub stars~3.2k tokensUpdated yesterday
    Testing & QAAuto-check passed

More from ccplugins/awesome-claude-code-plugins

All 68 skills in this repo
  • AI Meeting

    ccplugins/awesome-claude-code-plugins

    Run structured AI meetings for plans, product ideas, technical designs, business decisions, feature proposals, and strategy choices.

    967 GitHub stars~2.4k tokensUpdated 1 mo ago
    Auto-check: notes
  • Fastapi App

    ccplugins/awesome-claude-code-plugins

    Bootstrap a new FastAPI backend with async SQLAlchemy 2.0, asyncpg, Alembic, Pydantic v2, and no deprecated APIs.

    967 GitHub stars~1.1k tokensUpdated 1 mo ago
    Auto-check: notes
  • Flutter App

    ccplugins/awesome-claude-code-plugins

    Bootstrap a new Flutter mobile app with clean architecture, Riverpod, FVM-pinned SDK, current packages, and no deprecated APIs.

    967 GitHub stars~1.1k tokensUpdated 1 mo ago
    Auto-check: notes
  • Nextjs App

    ccplugins/awesome-claude-code-plugins

    Bootstrap a new Next.js (App Router, TypeScript) web app with current packages and no deprecated APIs.

    967 GitHub stars~1.1k tokensUpdated 1 mo ago
    Auto-check: notes
  • Dev Report

    ccplugins/awesome-claude-code-plugins

    Write up a coding session for a non-technical stakeholder — the context, what was built, and the engineering reasoning behind it — the way a senior engineer briefs a product manager who does not…

    967 GitHub stars~3.1k tokensUpdated 1 mo ago
    Auto-check passed
  • Difesa Attacchi

    ccplugins/awesome-claude-code-plugins

    Aggiunge a un sito/app un agente di difesa che rileva e blocca richieste malevole (SQL injection, XSS, path traversal, brute force, bot) con rate limiting, blocklist IP e modalità lockdown che…

    967 GitHub stars~781 tokensUpdated 1 mo ago
    Auto-check passed

Questions about Dispatching To Codex

What does Dispatching To Codex do?

A skill your agent uses when the user explicitly asks to hand a task to Codex — "use codex", "delegate this", "send it to codex", "交给codex", "派给codex", or the /delegate command. Dispatching To Codex is an agent skill from ccplugins/awesome-claude-code-plugins. Use when the user explicitly asks to hand a task to Codex — "use codex", "delegate this", "send it to codex", "交给codex", "派给codex", or the /delegate command.

When should I use Dispatching To Codex?

Dispatching To Codex fits situations like: the user explicitly asks to hand a task to Codex — use codex; send it to codex; the /delegate command.

How do I install Dispatching To Codex in Claude Code?

Run `npx skills add ccplugins/awesome-claude-code-plugins --skill dispatching-to-codex -a claude-code`. Or copy the skill folder (plugins/praetor/skills/dispatching-to-codex in ccplugins/awesome-claude-code-plugins) into .claude/skills/dispatching-to-codex in your project. Claude Code loads it when a task matches its description.

How do I install Dispatching To Codex in Codex?

Run `npx skills add ccplugins/awesome-claude-code-plugins --skill dispatching-to-codex -a codex`. Or copy the skill folder (plugins/praetor/skills/dispatching-to-codex in ccplugins/awesome-claude-code-plugins) into .agents/skills/dispatching-to-codex in your project. Codex loads it when a task matches its description.

Can I use Dispatching To Codex in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add ccplugins/awesome-claude-code-plugins --skill dispatching-to-codex -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/dispatching-to-codex, .gemini/skills/dispatching-to-codex, .github/skills/dispatching-to-codex and .opencode/skills/dispatching-to-codex in your project.

What does Dispatching To Codex need to run?

Going by SKILL.md and its folder, Dispatching To Codex needs a shell for the scripts in its folder and the command-line tools its instructions call (codex and git). Our summary lists: A Bash shell.

Does Dispatching To Codex access the network?

SKILL.md contains no URLs. Its commands use git, which can reach the network depending on how they are called. This is read from the text; nothing was executed.

Is Dispatching To Codex safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Dispatching To Codex use?

Dispatching To Codex is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Dispatching To Codex use?

About 1.1k tokens (SKILL.md is roughly 4.6k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Dispatching To Codex?

Skills that share tags, products or a category with Dispatching To Codex: Review Rfc (nurettincoban/ai-prd-workflow, 298 stars), QA Handoff Package (mohitagw15856/pm-claude-skills, 1.4k stars), Test Scenarios (phuryn/pm-skills, 27k stars) and Test Author (jpicklyk/task-orchestrator, 207 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Dispatching To Codex?

ccplugins (a GitHub organization) maintains it in ccplugins/awesome-claude-code-plugins, which has 967 GitHub stars. The repository holds 68 skills in this directory. The repository was last updated on August 12, 2026.

Source: ccplugins/awesome-claude-code-plugins on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.