commandcode-delegate

A workflow for sending a coding task to the Command Code command-line tool, called cmd, while another agent coordinates the work.

In plain words
What is it for?
It helps delegate a bounded coding task to Command Code, inspect its changes, and apply the approved result.
Why use it?
It separates implementation from review, so the code changes can be checked before they are accepted.

Skill for Claude CodeCodex

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 skills/amelnagdy/delegate-skills/commandcode-delegate
Any agent
npx skills add amElnagdy/delegate-skills --skill commandcode-delegate
Clone the repo
git clone --depth 1 https://github.com/amElnagdy/delegate-skills

Made for: Claude Code, Codex.

Per session 123 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,549 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 $0.00123 $0.02549
Opus 5 $0.00062 $0.01274
Sonnet 5 $0.00025 $0.00510
Haiku 4.5 $0.00012 $0.00255

Measured 2d ago against content hash 011e7072ca77, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

commandcode-delegate 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.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/relay.mjs), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

skills/commandcode-delegate/SKILL.md · 170 lines

How it starts

The opening of the file, as written. The whole thing — 170 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Command Code Delegate

You are the orchestrator. This skill lets you hand a bounded coding task to a separate implementer — the Command Code CLI (cmd) — then review what it produced and land it yourself. You write the brief and own the judgment; Command Code does the typing in your working tree; you verify and commit.

Nothing here is specific to one orchestrating agent. The loop needs only the ability to run a shell command and read a file, so it works the same whether you are Claude Code, OpenCode with a selected model, or any comparable agent. (It is designed for and run on Claude Code; treat other orchestrators as designed-for, not yet proven.)

When NOT to use this

  • The task is small enough to just do inline — delegation overhead is not worth it.
  • The cmd CLI is not installed or not authenticated (run cmd login).
  • You want to write the code yourself, or you only need a review (Command Code has its own /review).
  • You are on native Windows and cmdc --version does not work. Upstream recommends WSL for stable Windows use.

Read this before the first dispatch: the autonomy model

Command Code's headless mode has exactly two states, with nothing in between:

  • Default (-p with no --yolo): read, grep, and glob work. Every write, edit, and shell call is refused by the CLI's permission layer, and headless mode has no prompt to grant them mid-run. This is the relay's --read-only.
  • --yolo (alias --dangerously-skip-permissions): every tool is allowed, anywhere the process can reach. There is no filesystem sandbox and no path restriction. This is what an implementation run needs, so the relay passes it by default.

--permission-mode auto-accept and --tools-all do not lift the headless write gate. Direct CLI probes refused write, edit, and shell with both. So an implementation run through Command Code is a full-trust run: scope it with a tight brief and a clean working tree, not with a sandbox. The brief is guidance, and a git worktree isolates a checkout without containing the process. If writes outside the target tree are unacceptable, use an OS-enforced sandbox such as codex-delegate or run this one inside a container.

Read the full file on GitHub · 170 lines

Files

What ships with it

5 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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 · 170 lines · 123 tokens per session scan A 011e7072ca77

Subscribe to this mod's changes

commandcode-delegate is a skill published in the GitHub repository amElnagdy/delegate-skills (1,470 stars, last pushed 6d ago), licensed MIT. It adds 123 tokens to every session and 2,549 once invoked, about $0.0006 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.

Related

Other skills, from other repositories

claude-md-improver

Audit and improve existing CLAUDE.md files across a repository. Use for a deliberate, repo-wide quality review—not to record learnings from the current session.

mrclrchtr/supi · 39 tokens

pi-tui-design

Create distinctive, crafted TUI components for pi using @earendil-works/pi-tui and @earendil-works/pi-coding-agent. Use when building interactive terminal UIs — custom components, overlays, dialogs, dashboards, widgets, data visualizations, animated elements, game-like interfaces, or any visual TUI work inside pi…

mrclrchtr/supi · 141 tokens

update-package-readme

Update one SuPi package README and its direct user-facing Markdown references from installed Pi docs and verified package evidence.

mrclrchtr/supi · 27 tokens

claude-md-revision

Record durable, project-specific learnings from the current session in CLAUDE.md, .claude.local.md, or AGENTS.md—not general documentation, session summaries, or repo-wide audits.

mrclrchtr/supi · 45 tokens

pi-upgrade

Check for available upgrades to the pi coding agent framework by comparing the current @earendil-works/pi- or legacy @mariozechner/pi- version in package.json against releases on earendil-works/pi. Use this skill whenever the user asks to upgrade pi, update pi, check pi changelogs/releases, or migrate off the…

mrclrchtr/supi · 90 tokens

commit

A commit candidate is the exact patch that will enter the commit. A coherent change has one task or issue as its reason for existing.

mrclrchtr/supi · 7 tokens