delegate

delegate is a command for Claude Code from SteveGJones/ai-first-sdlc-practices. It costs 29 tokens per session (624 once invoked), scanned A, original, MIT.

A command that sends a defined sub-problem to another installed AI coding-agent command-line tool and returns a compact result.

In plain words
What is it for?
It helps delegate prompts with a chosen backend, model, effort level, working directory, timeout, and permission posture.
Why use it?
It lets you use a different agent for a specialised task without manually switching tools or copying the request.

Command for Claude Code

Written for Claude Code: argument-hint in frontmatter. Also seen: 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 sdlc-model-council plugin — 1 skill, 7 commands, 2 agents shipped together

Good fit It helps delegate prompts with a chosen backend, model, effort level, working directory, timeout, and permission posture.

Compare 6 commands from other repositories ↓
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 SteveGJones/ai-first-sdlc-practices
Claude Code
/plugin install sdlc-model-council

Made for: Claude Code.

Or install sdlc-model-council, the plugin that ships this one along with the rest of its 1 skill, 7 commands, 2 agents.

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 delegate

README.md
[![agentmods](https://agentmods.dev/badge/commands/stevegjones/ai-first-sdlc-practices/delegate/github.svg)](https://agentmods.dev/commands/stevegjones/ai-first-sdlc-practices/delegate)
Your own site
<a href="https://agentmods.dev/commands/stevegjones/ai-first-sdlc-practices/delegate"><img src="https://agentmods.dev/badge/commands/stevegjones/ai-first-sdlc-practices/delegate/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for delegate

Your own site · 80×15
<a href="https://agentmods.dev/commands/stevegjones/ai-first-sdlc-practices/delegate"><img src="https://agentmods.dev/badge/commands/stevegjones/ai-first-sdlc-practices/delegate.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 29 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 624 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 $0.00029 $0.00624
Opus 5 $0.00015 $0.00312
Sonnet 5 $0.00006 $0.00125
Haiku 4.5 $0.00003 $0.00062

Measured 10d ago against content hash a61e1f8118e4, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-13, from the pricing page.

Security

Grade A, and why

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 10d 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.

plugins/sdlc-model-council/commands/delegate.md · 48 lines

What it actually says

Delegate the following request to a peer agentic CLI backend through this plugin's delegation-runner agent.

Arguments: $ARGUMENTS

Parse $ARGUMENTS as: the first whitespace-delimited token is the backend (codex, agy, or any other id extdel.sh list-backends shows as registered); the rest, up to any trailing key=value tokens, is the prompt; trailing posture=, model=, effort=, handle=, cwd=, timeout_s= tokens are optional fields to pass through. If no backend is given, do not guess — ask, or run ${CLAUDE_PLUGIN_ROOT}/scripts/extdel.sh list-backends and offer the installed options.

Do this:

  1. Consult the routing table first. Load the council-policy skill (in particular its §3.3 routing table) before dispatching anything. Some request shapes — reviewing this session's own diff, an adversarial review gate, rescuing a stuck codex task, continuing a persistent codex thread — should be handed off to the matching /codex:* sibling-plugin command in this main thread instead of dispatched through this plugin, if that sibling plugin is installed (check your own available-skills listing for /codex:* commands first; only fall back to a list-backends probe if you can't tell). If the routing table says hand off, do that instead of continuing below, and say so plainly.
  2. Otherwise, dispatch delegation-runner (the Agent tool, this plugin's agent) with the parsed fields: backend, prompt, and any optional fields given (posture defaults to read-only if omitted — never choose dangerous on the caller's behalf). If handle= was given, this is a continuation of an existing delegation — pass it through so the runner resumes rather than starting fresh.
  3. Report the runner's return verbatim — the ## External Delegation block, ## Answer, and ## Errors if present. Do not summarize away the status line, handle, or session id; the caller may need them to continue the conversation later.

Remember the fan-out cap of 5 concurrent external sessions (see council-policy) if this command is being invoked multiple times in quick succession for a manual compare — /…:delegate itself only ever dispatches one backend per call.

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. 10d ago First seen · 48 lines · 29 tokens per session scan A a61e1f8118e4

Subscribe to this mod's changes

delegate is a command published in the GitHub repository SteveGJones/ai-first-sdlc-practices (41 stars, last pushed 1mo ago), licensed MIT. It adds 29 tokens to every session and 624 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 2026-09-03.