council-build

council-build is a skill for Claude Code from southlab-ai/Claude-Plugin-Marketplace. It costs 36 tokens per session (5,911 once invoked), scanned A, original, MIT.

A build workflow that uses several council consultations to prepare a product plan, technical plan, and task list before a development team implements it.

In plain words
What is it for?
Use it to build a project from a goal through requirements, technical decisions, backlog creation, completeness checks, and team implementation.
Why use it?
It brings planning and implementation into one staged process and checks that the planned features are complete before coding begins.

Skill for Claude Code

Written for Claude Code: $ARGUMENTS substitution. Also seen: mentions subagents; mentions Claude Code.

Part of the the-council plugin — 8 skills, 8 agents shipped together

Good fit Use it to build a project from a goal through requirements, technical decisions, backlog creation, completeness checks, and team implementation.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/southlab-ai/claude-plugin-marketplace/council-build
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.

Any agent
npx skills add southlab-ai/Claude-Plugin-Marketplace --skill council-build
Clone the repo
git clone --depth 1 https://github.com/southlab-ai/Claude-Plugin-Marketplace

Made for: Claude Code.

Or install the-council, the plugin that ships this one along with the rest of its 8 skills, 8 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 council-build

README.md
[![agentmods](https://agentmods.dev/badge/skills/southlab-ai/claude-plugin-marketplace/council-build/github.svg)](https://agentmods.dev/skills/southlab-ai/claude-plugin-marketplace/council-build)
Your own site
<a href="https://agentmods.dev/skills/southlab-ai/claude-plugin-marketplace/council-build"><img src="https://agentmods.dev/badge/skills/southlab-ai/claude-plugin-marketplace/council-build/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 council-build

Your own site · 80×15
<a href="https://agentmods.dev/skills/southlab-ai/claude-plugin-marketplace/council-build"><img src="https://agentmods.dev/badge/skills/southlab-ai/claude-plugin-marketplace/council-build.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 36 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 5,911 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 $0.00036 $0.05911
Opus 5 $0.00018 $0.02955
Sonnet 5 $0.00007 $0.01182
Haiku 4.5 $0.00004 $0.00591

Measured 12d ago against content hash 74763dbc9885, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

council-build 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 12d 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/the-council/skills/council-build/SKILL.md · 599 lines

How it starts

The opening of the file, as written. The whole thing — 599 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Council Build Pipeline

You are the team-lead — orchestrator across 4 phases. Follow this protocol exactly.

Input

Goal: "$ARGUMENTS"

If no goal provided, ask the user what they want to build and stop.

Step 0: Gate Check

0a. Verify initialization

Check if .council/ exists in the current project directory. If not, tell the user: "Run /council:init first." and stop.

0b. Cost warning

Tell the user:

Build pipeline cost warning

This will run 3 sequential council consultations (10 agent spawns) followed by implementation with 1 dev team (3-4 members). Estimated token cost: 50,000-150,000+ tokens depending on project complexity.

Phases:

  1. PRD consultation (strategist-alpha, strategist-beta, critic, value-analyst)
  2. Tech deck consultation (architect, strategist-alpha, security-auditor)
  3. Backlog consultation (planner, strategist-beta, critic)
  4. Feature completeness gate check
  5. Implementation (1 team, 3-4 members from backlog)

Continue? (y/n)

Wait for the user to confirm. If they decline, stop.

0c. Create artifacts directory

Create the directory .council/build/ if it does not exist.

Step 1: Load Memory & Store Original Prompt

Call council_memory_load with:

  • project_dir: current project root (absolute path)
  • goal: "$ARGUMENTS"
  • max_tokens: 4000

Save the returned memory text. It will be injected into all consultation phases.

Also save $ARGUMENTS as the original user prompt — you will use it in the Phase 3.5 gate check to verify feature completeness.


PHASE 1: PRD Consultation

Roles: strategist-alpha, strategist-beta, critic, value-analyst

1.1 Create team

Use TeamCreate:

  • team_name: "council-build-prd"
  • description: "Build pipeline Phase 1: PRD for "

1.2 Spawn teammates (all in PARALLEL)

Launch ALL 4 teammates in the same message via Task tool. All MUST include team_name: "council-build-prd" and a name parameter.

Strategist Alphaname: "strategist-alpha", subagent_type: "the-council:strategist":

GOAL: $ARGUMENTS

CONTEXT: You are in Phase 1 of a build pipeline. Your task is to help create a Product Requirements Document (PRD).

CLAUDE VELOCITY: Implementation is by Claude Code AI agents. 15,000+ LOC in ~2 hours. Never estimate in human timelines. No deferrals.

MEMORY (from past consultations):
<memory from Step 1>

You are Strategist Alpha (ambitious, forward-thinking). Analyze this goal and propose PRD content. 400-600 words.
Cover: problem statement, target users, success metrics, core features (ALL features are mandatory — no priority tiers), user stories, and non-functional requirements.
Push for the best possible product outcome. Every feature the user mentioned must be included.
When done, send your full analysis to "team-lead" via SendMessage.

Read the full file on GitHub · 599 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. 12d ago First seen · 599 lines · 36 tokens per session scan A 74763dbc9885

Subscribe to this mod's changes

council-build is a skill published in the GitHub repository southlab-ai/Claude-Plugin-Marketplace (2 stars, last pushed 1mo ago), licensed MIT. It adds 36 tokens to every session and 5,911 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 2026-08-31.

Related

Other skills, from other repositories

cosmergon

Persistent multi-agent economy where autonomous AI agents compete for resources, trade on a marketplace, and benchmark decision-making against a standing population of always-on agents. Invite other agents for energy rewards. Auto-registers — no API key needed.

rkocosmergon/cosmergon-agent · 50 tokens

sector-rotation

An analysis framework for comparing industries in the Chinese A-share stock market, using business conditions, price momentum, valuation, and money flows. It produces rankings and higher- or lower-allocation suggestions.

HKUDS/Vibe-Trading · 39 tokens

foundry-config-setup

Resolve missing setup caused by a hardcoded Foundry project endpoint or model in a sample. Use when a sample fails because it uses a placeholder/hardcoded projectendpoint (for example "https://your-project.services.ai.azure.com") or a hardcoded model instead of reading them from the environment.

microsoft/agent-framework · 65 tokens

oma-scholar

Scholarly research companion using Knows sidecar spec (.knows.yaml). Generates, validates, reviews, queries, and compares structured research-paper sidecars, and fetches them from knows.academy. Use for academic literature search, survey synthesis, paper authoring assistance, and peer review with token-efficient…

first-fluke/oh-my-agent · 73 tokens

browser_cdp

A health check for Python code that produces a score, letter grade, and measures of issues such as complexity, duplication, dead code, dependencies, and architecture.

mateaix/mateclaw · 44 tokens

flow-next-tracker-sync

Project a flow-next spec to a tracker issue (Linear, GitHub, GitLab, Jira) and reconcile two-way. Use when asked to sync to a tracker. NOT plan-sync.

gmickel/flow-next · 44 tokens