delegate

A controlled way to send a versioned coding specification to Claude Architect, have the result independently checked, and accept only the approved changes. A producer is the worker that writes the code; its output remains a candidate until reviewed.

In plain words
What is it for?
Use it to delegate an implementation task, choose or manage a producer, and review the exact code candidate before it crosses the acceptance boundary.
Why use it?
It separates writing code from checking and accepting it, reducing the chance that unverified changes are integrated into a project.

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/pymodel/claude-architect/delegate
Any agent
npx skills add PyModel/claude-architect --skill delegate
Clone the repo
git clone --depth 1 https://github.com/PyModel/claude-architect

Made for: Claude Code, Codex.

Per session 47 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 7,777 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 $0.00047 $0.07777
Opus 5 $0.00023 $0.03889
Sonnet 5 $0.00009 $0.01555
Haiku 4.5 $0.00005 $0.00778

Measured 2d ago against content hash c14bf19131d0, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, 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 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.

skills/delegate/SKILL.md · 351 lines

How it starts

The opening of the file, as written. The whole thing — 351 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Delegate

PROTOCOL_VERSION: 2.0.0

The current session is the architect. It owns requirements, the Delegation Spec, Producer selection, review, and acceptance. Producers are untrusted: their output is only a candidate until the runtime freezes it, independently verifies it, and the architect reviews the exact anchored bytes.

Always present this skill as /claude-architect:delegate. Never show a shorter command.

Superpowers across the trust boundary

When the upstream Superpowers plugin is available to the architect, keep its host-loop skills on the architect side of the boundary: use brainstorming to clarify requirements before freezing the Delegation Spec, writing-plans to turn an agreed design into objectively checkable work or slices, and verification-before-completion before recording a decision on a candidate. Do not use generic executing-plans or subagent-driven-development for writing tasks; they may coordinate architect-owned non-writing analysis only.

To execute any multi-task plan that writes files, use /claude-architect:subagent-driven-delegation: it runs the Superpowers subagent-driven-development loop — ledger, per-task brief, per-task review, final whole-branch review — with the delegation lifecycle below substituted for the generic implementer subagent. Those skills do not grant a Producer permission to plan instead of editing, dispatch nested agents, review itself, accept a candidate, or integrate bytes. When the plugin is not installed, proceed without those skills rather than inventing or approximating them.

Edit-lane Producers receive a deliberately smaller, vendored procedure subset:

  • test-driven-development for every behavior change or bug fix, before implementation code;
  • systematic-debugging when a test, build, or behavior fails unexpectedly, before proposing a fix;
  • verification-before-completion before claiming success.

The runtime supplies the applicable Producer skills by absolute path inside each isolated attempt. Do not put architect-only Superpowers skills in the Delegation Spec or tell a Producer to discover skills from the operator's home directory. The Producer subset is vendored from obra/superpowers, version 6.2.0, under the MIT license.

Read the full file on GitHub · 351 lines

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 · 351 lines · 47 tokens per session scan A c14bf19131d0

Subscribe to this mod's changes

delegate is a skill published in the GitHub repository PyModel/claude-architect (19 stars, last pushed 4d ago), licensed MIT. It adds 47 tokens to every session and 7,777 once invoked, about $0.0002 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