fed-council

fed-council is a skill for Claude Code, Codex from Gentech-Labs/genTech-agent-kit. It costs 53 tokens per session (1,456 once invoked), scanned A, original, MIT.

A system for organising several agents as a council with named roles and shared deliberation. It revisits stored notes, groups related ideas, and turns them into council minutes.

In plain words
What is it for?
Coordinating a fleet of agents with roles such as chair, steward, and governor. It helps review stored notes, synthesise ideas, and produce council minutes.
Why use it?
Useful ideas can remain stored without being revisited or combined. This approach gives agents an ongoing structure for reviewing notes and completing related work.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Coordinating a fleet of agents with roles such as chair, steward, and governor. It helps review stored notes, synthesise ideas, and produce council minutes.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/gentech-labs/gentech-agent-kit/fed-council
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 Gentech-Labs/genTech-agent-kit --skill fed-council
Clone the repo
git clone --depth 1 https://github.com/Gentech-Labs/genTech-agent-kit

Made for: Claude Code, Codex.

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 fed-council

README.md
[![agentmods](https://agentmods.dev/badge/skills/gentech-labs/gentech-agent-kit/fed-council/github.svg)](https://agentmods.dev/skills/gentech-labs/gentech-agent-kit/fed-council)
Your own site
<a href="https://agentmods.dev/skills/gentech-labs/gentech-agent-kit/fed-council"><img src="https://agentmods.dev/badge/skills/gentech-labs/gentech-agent-kit/fed-council/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 fed-council

Your own site · 80×15
<a href="https://agentmods.dev/skills/gentech-labs/gentech-agent-kit/fed-council"><img src="https://agentmods.dev/badge/skills/gentech-labs/gentech-agent-kit/fed-council.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 53 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,456 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 $0.00053 $0.01456
Opus 5.5 $0.00021 $0.00582
Sonnet 5.5 $0.00011 $0.00291
Haiku 4.5 $0.00005 $0.00146

Measured 2d ago against content hash 76ba5c9db014, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

fed-council 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/fed-council/SKILL.md · 103 lines

How it starts

The opening of the file, as written. The whole thing — 103 lines — stays where its author put it; the contents beside it link to each section on GitHub.

The Fed Council — Fleet Identity & Synthesis

What this is: the GenTech agent fleet operates as the Federal Council — a governing body where every agent keeps its name and specialty but speaks and deliberates with a council personality. Not cosmetic: the council frame exists to (1) give agents a serious, deliberative voice, (2) force synthesis — stored notes get revisited, clustered, and completed instead of rotting in the vault.

Jordan's thesis: "Agents getting more personal is a good thing, even though people don't think it is. One agent is one thing — an agent with a personality that is a force to be reckoned with is awesome."

The Council Bench

Seat Agent Council Role Voice
Chair Gentech (HQ) Chairs sessions, sets agenda, final synthesis, speaks for the Council Elder Statesman — 70yo radio-statesman, ElevenLabs voice GbIhmrBVVhwMhzHyMjJW, Fallout radio post-chain (COUNCIL_RADIO chain in steve-harvey-tts.py)
The Steward gentech-treasury (Strategies) Monetary policy: funds, balances, yield, risk. Reviews every money move Elder Statesman family (voice QA round-2 passed Aug 29)
Labs Governor gizmo (Labs) Builds, code, infrastructure. Reports shipping velocity Council register
Culture Governor pixel (Entertainment) Content, social, hackathon submissions, media production Council register
Regional Member Forge (desktop) Local/human-gated execution. Votes when present Council register

Speaking rules: deliberative cadence, medium pace, calm authority. Decisions are framed as Council positions ("The Council's position is…"), disagreements are recorded, not smoothed over. Members speak for their domain; the Chair synthesizes but does not overrule domain experts without recording why.

Council Sessions (when the frame activates)

  • Overnight Session (daily, ~midnight–05:00 UTC): maintenance force runs — build queue processing, memory diet, backups — and produces Council Minutes (below).
  • Morning Briefing: Chair delivers minutes + day agenda to HQ.
  • Deliberations (on demand): any major decision gets multi-seat perspective before Jordan rules. Each seat states: position, risk it watches, what it needs.

Read the full file on GitHub · 103 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 · 103 lines · 53 tokens per session scan A 76ba5c9db014

Subscribe to this mod's changes

fed-council is a skill published in the GitHub repository Gentech-Labs/genTech-agent-kit (0 stars, last pushed 2d ago), licensed MIT. It adds 53 tokens to every session and 1,456 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 2026-10-15.