What is council-update?

A migration procedure for updating stored Council project data after the Council plugin changes version. It checks the project’s .council folder, identifies the old format, and updates the version record while preserving existing memory.

Use it after upgrading the Council plugin to migrate its data, preserve existing entries, and report the changes introduced by the new version.

It prevents project decisions, lessons, and other Council memory from being lost or left in an older format after an update.

council-update — Skill for Claude Code by southlab-ai

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-update

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/southlab-ai/claude-plugin-marketplace/council-update/github.svg)](https://agentmods.dev/skills/southlab-ai/claude-plugin-marketplace/council-update)

Your own site

<a href="https://agentmods.dev/skills/southlab-ai/claude-plugin-marketplace/council-update"><img src="https://agentmods.dev/badge/skills/southlab-ai/claude-plugin-marketplace/council-update/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/southlab-ai/claude-plugin-marketplace/council-update"><img src="https://agentmods.dev/badge/skills/southlab-ai/claude-plugin-marketplace/council-update.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 21 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 2,165 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.

Model	Per session	Once invoked
Fable 5.1	$0.00021	$0.02165
Opus 5	$0.00010	$0.01082
Sonnet 5	$0.00004	$0.00433
Haiku 4.5	$0.00002	$0.00216

Measured 11d ago against content hash 86b6f29cd370, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

council-update 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 11d 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-update/SKILL.md · 123 lines

How it starts

The opening of the file, as written. The whole thing — 123 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Update Council

Run this after updating The Council plugin to a new version. Migrates .council/ data and reports what's new.

Step 1: Check initialization

Check if .council/ exists in the current project directory. If not, tell the user: "No council found. Run /council:init to start fresh." and stop.

Step 2: Read current version

Read .council/memory/index.json. Check for the plugin_version field:

If plugin_version exists: that's the installed version.
If plugin_version is missing: this is a pre-v3.0.0 installation (v2.x or earlier).

Step 3: Run migrations

From v2.x (no plugin_version) to v3.0.0

Add version tracking: Add "plugin_version": "3.0.0" to index.json and save it.
Preserve all existing data: Do NOT delete or modify existing decisions, lessons, active memory, or archives. All v2.x memory is fully compatible with v3.0.0.
Report what's new in v3.0.0:
- 4 consultation modes (default, debate, plan, reflect) — auto-routed, no flags needed
- Configurable roles via ROLES: clause (architect, security-auditor, ux-reviewer, planner, or custom)
- Debate mode with 1 rebuttal round (teammates cross-read positions)
- Plan mode outputs numbered actionable steps (all mandatory)
- Reflect mode analyzes your decision history and recommends future consultations
- "Hub" renamed to "team-lead" in all protocols and documentation

From v3.0.0 to v3.1.0-beta

Add original_prompt field: Read index.json, add "original_prompt": "" if missing, save it.
Preserve all existing data: Do NOT delete or modify existing decisions, lessons, active memory, or archives. All v3.0.0 memory is fully compatible with v3.1.0-beta.
Update plugin_version: Set "plugin_version": "3.1.0-beta" in index.json and save.
Report what's new in v3.1.0-beta:
- Anti-deferral system: Agents never cut, defer, or deprioritize features. Everything the user asks for gets implemented.
- Quality Engineer critic: The critic now improves quality (security, architecture, error handling) instead of managing scope. Never classifies features into priority tiers.
- Claude Velocity: All agents understand that Claude Code implements in ~2 hours, not weeks. No human timeline estimates.
- Feature completeness gate: /council:build now runs a gate check between backlog and implementation to verify 100% of requested features are assigned.
- Scaled implementation: Build pipeline uses 1 team with 3-4 members (each can use subagents for internal parallelization).
- Original prompt tracking: Memory stores the original user prompt for feature-tracking throughout the build pipeline.
- Plan mode updated: Outputs implementation order (all mandatory) instead of P0/P1/P2 priorities.
- Banned words: Agent outputs no longer contain "scope creep", "P0/P1/P2", "defer", "out of scope", "fast-follow", "future phase", "descope", "weeks", "months", "sprint".
- Consistent banned words: All 5 agents (strategist, critic, planner, architect, security-auditor) now share the same complete banned words list including "P0/P1/P2" and "Never classify features into priority tiers".

Read the full file on GitHub · 123 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.

11d ago First seen · 123 lines · 21 tokens per session scan A 86b6f29cd370

Subscribe to this mod's changes

council-update is a skill published in the GitHub repository southlab-ai/Claude-Plugin-Marketplace (2 stars, last pushed 1mo ago), licensed MIT. It adds 21 tokens to every session and 2,165 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 2026-08-31.

Claude Code DevOps and cloud Multi-Agent ai-agents computer-vision marketplace mcp

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