agentmods.dev

spec-delegated

spec-delegated is a skill for Claude Code from Ratler/dream-team. It costs 40 tokens per session (1,248 once invoked), scanned A, original, MIT.

A command that turns an agreed brainstorming plan into a formal specification for delegated software work. Delegated execution means an orchestrator coordinates specialized sub-agents to carry out the work.

In plain words
What is it for?
It is for writing an execution spec after a prior dream-team planning session, including the task breakdown and suitable agent definitions.
Why use it?
It gives a team of agents a clear, detailed description of the requirements, approach, and responsibilities.

Skill for Claude Code

Written for Claude Code: hooks in frontmatter. Also seen: mentions subagents.

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 dream-team plugin — 5 skills, 7 commands, 11 agents, 4 hooks shipped together

not rated 16repo 3mo ago A scan 40 tokens original MIT

Good fit It is for writing an execution spec after a prior dream-team planning session, including the task breakdown and suitable agent definitions.

Compare 6 skills from other repositories ↓
View source ↗ Ratler/dream-team
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 Ratler/dream-team
Claude Code
/plugin install dream-team

Made for: Claude Code.

Or install dream-team, the plugin that ships this one along with the rest of its 5 skills, 7 commands, 11 agents, 4 hooks.

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 spec-delegated

README.md
[![agentmods](https://agentmods.dev/badge/skills/ratler/dream-team/spec-delegated/github.svg)](https://agentmods.dev/skills/ratler/dream-team/spec-delegated)
Your own site
<a href="https://agentmods.dev/skills/ratler/dream-team/spec-delegated"><img src="https://agentmods.dev/badge/skills/ratler/dream-team/spec-delegated/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 spec-delegated

Your own site · 80×15
<a href="https://agentmods.dev/skills/ratler/dream-team/spec-delegated"><img src="https://agentmods.dev/badge/skills/ratler/dream-team/spec-delegated.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 40 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,248 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 $0.00040 $0.01248
Opus 5 $0.00020 $0.00624
Sonnet 5 $0.00008 $0.00250
Haiku 4.5 $0.00004 $0.00125

Measured 9d ago against content hash 48d1c6728aa9, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

spec-delegated 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 9d 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/spec-delegated/SKILL.md · 85 lines

How it starts

The opening of the file, as written. The whole thing — 85 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Write Delegated Spec

Convert the brainstorming conversation into a formal spec file for delegated execution — single session with an orchestrator dispatching specialized sub-agents via the Task tool.

Prerequisites: This skill assumes /dream-team:plan has already been run in this session. If the conversation has no brainstorming context (no discussed requirements, no confirmed approach, no validated task breakdown), stop and tell the user: "No brainstorming context found. Run /dream-team:plan <prompt> first to explore requirements and design."

What To Do

  1. Read the spec template at ${CLAUDE_PLUGIN_ROOT}/templates/spec-template.md and the spec writing guide at ${CLAUDE_PLUGIN_ROOT}/templates/spec-writing-guide.md. Follow the guide's filename format, ambiguity elimination, and git instructions.
  2. Read the available agent definitions at ${CLAUDE_PLUGIN_ROOT}/agents/*.md to understand each agent's capabilities.
  3. Summarize the agreed plan from the conversation — confirm with the user before writing.
  4. Write the spec, filling in all sections from the brainstorming context.
  5. Set frontmatter mode: delegated and spec-version: 1.
  6. Set frontmatter playwright: true if the brainstorming decided to use Playwright MCP, otherwise playwright: false.
  7. Set frontmatter frontend-design: true if the brainstorming discussed frontend/UI work and design direction, otherwise frontend-design: false.
  8. If frontend-design: true, fill in the ## Design Direction section with the aesthetic style, stack, component libraries, and design notes from the brainstorming conversation. Auto-suggest component libraries based on the chosen stack if not explicitly discussed.
  9. Assign each task to a specific agent by name and type.
  10. Mark tasks as background: true when they can safely run in parallel (no file conflicts, no dependencies).
  11. Include Team Members and Review Policy sections.
  12. Include a reviewer agent for post-task code review.
  13. Include a validator agent for final verification.
  14. Fill in the ## Cleanup section with any teardown commands needed (stop servers, remove temp files). Use "N/A" if nothing to clean up.
  15. Save to specs/YYYY-MM-DD-<descriptive-kebab-case>.md using today's date.

Read the full file on GitHub · 85 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. 9d ago First seen · 85 lines · 40 tokens per session scan A 48d1c6728aa9

Subscribe to this mod's changes

spec-delegated is a skill published in the GitHub repository Ratler/dream-team (16 stars, last pushed 3mo ago), licensed MIT. It adds 40 tokens to every session and 1,248 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.

Building agentsPlanning
Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

insight-error-page

Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…

vercel/next.js · 83 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…

vercel/next.js · 103 tokens