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 skills add PyModel/claude-architect --skill delegategit clone --depth 1 https://github.com/PyModel/claude-architectWrote 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.
[](https://agentmods.dev/skills/pymodel/claude-architect/delegate)<a href="https://agentmods.dev/skills/pymodel/claude-architect/delegate"><img src="https://agentmods.dev/badge/skills/pymodel/claude-architect/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.
<a href="https://agentmods.dev/skills/pymodel/claude-architect/delegate"><img src="https://agentmods.dev/badge/skills/pymodel/claude-architect/delegate.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium MCP Rug Pull · line 271 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
- low Excessive Agency · line 93 Skill's behavior or capabilities extend beyond its stated purpose. Scope creep allows an agent to perform actions unrelated to its documented functionality, increasing the attack surface.Fix: Limit the skill's scope to its documented purpose. Remove instructions that enable the agent to perform actions outside its stated functionality.
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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00047 | $0.05563 |
| Opus 5.5 | $0.00019 | $0.02225 |
| Sonnet 5.5 | $0.00009 | $0.01113 |
| Haiku 4.5 | $0.00005 | $0.00556 |
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 5d 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 — 225 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Delegate
PROTOCOL_VERSION: 3.0.0
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 /architect:delegate. Never show a shorter command.
Superpowers across the trust boundary
When the upstream Superpowers plugin is available, keep its host-loop skills on the architect side: brainstorming before freezing the Delegation Spec, writing-plans to turn an agreed design into objectively checkable work or slices, verification-before-completion before recording a decision. Generic executing-plans and subagent-driven-development may coordinate architect-owned non-writing analysis only, never a writing task.
To execute any multi-task plan that writes files, use /architect:subagent-driven-delegation: the Superpowers subagent-driven-development loop — ledger, per-task brief, per-task review, final whole-branch review — with the delegation lifecycle below replacing the generic implementer subagent. No skill grants a Producer permission to plan instead of editing, dispatch nested agents, review itself, accept a candidate, or integrate bytes. Without the plugin, proceed without those skills rather than approximating them.
Edit-lane Producers receive a deliberately smaller, vendored procedure subset:
test-driven-developmentfor every behavior change or bug fix, before implementation code;systematic-debuggingwhen a test, build, or behavior fails unexpectedly, before proposing a fix;verification-before-completionbefore claiming success.
The runtime supplies these by absolute path inside each isolated attempt. Never put architect-only skills in the Delegation Spec or tell a Producer to discover skills from the operator's home directory. Vendored from obra/superpowers 6.2.0, MIT.
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.
- 5d ago Changed cdc3f7a91858
- 22d ago Changed · -126 lines 1b5a990044a4
- 1mo ago First seen · 351 lines · 47 tokens per session scan A c14bf19131d0
delegate is a skill published in the GitHub repository PyModel/claude-architect (31 stars, last pushed today), licensed MIT. It adds 47 tokens to every session and 5,563 once invoked, about $0.0002 per session on Opus 5.5. 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
delegation-core
Delegates execution to eight CLIs (Gemini, Qwen, MiniMax, GLM, Muse, Codex, OpenCode, Glimmer). Use for execution tasks. Do not use for secrets.
opencode-delegation
Delegates tasks to OpenCode (opencode run) via delegation-core. Use when delegation-core selects OpenCode or a provider-agnostic harness is wanted.
AI Agent Review Readiness
Checks whether AI-assisted work defines review criteria, accessible context, explicit review loop, human judgment boundary, and feedback capture before delegating to an agent.
project-profile
Create or revise backlog/docs/critical-areas.md, the project profile that names the areas where work always runs on the top tier. Use when the file is missing, the user asks for it, the project changed substantially, a misclassification caused a mistake, or sbl doctor reports the profile as provisional.
evolution-guide
Explains how Evolving Lite works when the user asks about the system, its features, or how to use it. Triggers on questions like "how does this work", "what is evolving lite", "what hooks are running", "explain the system".
architecture-summary
Create or refresh backlog/docs/architecture.yml, the curated source of the project summary page (architecture diagram, flows, highlights, tech stack, commands). Use when the user asks for a project summary, an architecture overview or diagram, or after structural changes to the codebase.