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.
npx agentmods add skills/amelnagdy/delegate-skills/commandcode-delegatenpx skills add amElnagdy/delegate-skills --skill commandcode-delegategit clone --depth 1 https://github.com/amElnagdy/delegate-skillsWhat 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.
| Model | Per session | Once 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 |
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.
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.
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
cmdCLI is not installed or not authenticated (runcmd 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 --versiondoes 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 (
-pwith 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.
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.
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.
- 2d ago First seen · 170 lines · 123 tokens per session scan A 011e7072ca77
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.
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.
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…
update-package-readme
Update one SuPi package README and its direct user-facing Markdown references from installed Pi docs and verified package evidence.
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.
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…
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.