Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/golemfoundation/octant-council-buildernpx agentmods add skills/golemfoundation/octant-council-builder/settingsWrote 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/golemfoundation/octant-council-builder/settings)<a href="https://agentmods.dev/skills/golemfoundation/octant-council-builder/settings"><img src="https://agentmods.dev/badge/skills/golemfoundation/octant-council-builder/settings/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/golemfoundation/octant-council-builder/settings"><img src="https://agentmods.dev/badge/skills/golemfoundation/octant-council-builder/settings.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00012 | $0.01721 |
| Opus 5 | $0.00006 | $0.00860 |
| Sonnet 5 | $0.00002 | $0.00344 |
| Haiku 4.5 | $0.00001 | $0.00172 |
Grade A, and why
settings scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 10d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 229 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Council Setup
Sets up the council plugin for a user. Detects or clones the repo, explains everything that will happen, asks for confirmation, then configures the shell.
Step 1: Detect Environment + Check for Repo
Detect shell and config file:
echo "SHELL=$SHELL"
Map shell to config:
zsh→~/.zshrcbash→~/.bashrc(or~/.bash_profileon macOS if.bashrcdoesn't exist)fish→~/.config/fish/config.fish- Other →
~/.${shell}rc
Check if we're inside the council repo (or can find it nearby):
# Check current directory
if [ -f ".claude-plugin/plugin.json" ]; then
PLUGIN_DIR="$(pwd)"
echo "REPO_FOUND=true"
echo "PLUGIN_DIR=$PLUGIN_DIR"
else
# Check common locations
for dir in \
"$HOME/git/octant-council-builder" \
"$HOME/octant-council-builder" \
"$HOME/projects/octant-council-builder" \
"$HOME/code/octant-council-builder" \
"$HOME/src/octant-council-builder" \
"$HOME/dev/octant-council-builder" \
"../octant-council-builder"; do
if [ -f "$dir/.claude-plugin/plugin.json" ]; then
PLUGIN_DIR="$(cd "$dir" && pwd)"
echo "REPO_FOUND=true"
echo "PLUGIN_DIR=$PLUGIN_DIR"
break
fi
done
if [ -z "$PLUGIN_DIR" ]; then
echo "REPO_FOUND=false"
fi
fi
Store $REPO_FOUND and $PLUGIN_DIR.
Step 2: Explain Everything, Ask for Confirmation
Before doing anything, tell the user exactly what will happen and why. The preview content depends on whether the repo was found.
AskUserQuestion:
question: "Here's what setup will do. Ready to proceed?"
header: "Council Setup"
options:
- label: "Let's go"
description: "Proceed with setup"
preview: |
HOW PLUGINS WORK
Claude Code can load plugins from any directory via --plugin-dir.
It reads .claude-plugin/plugin.json from that directory and registers
all skills/*/SKILL.md files as slash commands under the plugin's name.
This repo is a plugin called "council" — loading it gives you
/council:evaluate, /council:setup, /council:add-agent, and more.
[IF REPO NOT FOUND:]
STEP 1: CLONE THE REPO
The council repo wasn't found on your machine. We'll clone it from:
https://github.com/golemfoundation/octant-council-builder.git
You can pick where to put it (default: ~/git/octant-council-builder).
STEP 2: CREATE A SHELL ALIAS
Creates an alias so you can launch Claude Code with the council
plugin loaded. Example: alias council='claude --plugin-dir /path/to/repo'
The alias keeps things isolated — plain "claude" stays clean.
The council only loads when you use the alias.
STEP 3: ENABLE AGENT TEAMS
The council's evaluate skill uses Claude Code's teams feature to run
parallel agent waves. This requires an env var:
export CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS=1
Both shell config changes are tagged with "# public-goods-council"
so they can be cleanly removed or updated by re-running setup.
WHY THIS IS USEFUL FOR DEVELOPMENT
The alias points at your local clone. Edit agent .md files or skill
files and changes take effect immediately — no reinstall, no rebuild.
Run /reload-plugins inside a session to pick up skill changes without
restarting.
- label: "Cancel"
description: "Exit without 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.
- 10d ago First seen · 229 lines · 12 tokens per session scan A 2c72c5ff44ef
settings is a skill published in the GitHub repository golemfoundation/octant-council-builder (3 stars, last pushed 5mo ago), licensed MIT. It adds 12 tokens to every session and 1,721 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.
Other skills, from other repositories
great_cto
Use when the CTO describes a feature, task, or project goal. Orchestrates the full SDLC pipeline automatically based on project type.
anti-patterns
Catalogue of known SDLC anti-patterns that greatcto agents must actively reject when reviewing architecture, plans, code, or post-mortems. Used by architect (pre-impl), pm (planning), senior-dev (impl), l3-support (post-incident).
cost-model
Standardized cost-estimation framework for greatcto plans. Forces explicit LLM cost, infra cost, human-supervision time, and the (defensible) human-equivalent comparison. Output format is parsable by the board's /api/cost path — must follow exactly.
migration-ready-schema
Data-model rules that make a schema importable from day one, so the migration-import-engineer is never blocked on missing columns. Every SMB Product-Builder product must let a customer bring their data from an incumbent (ServiceTitan/Toast/Mindbody/Shopify) — that requires provenance (sourceref) and rollback…
agent-workflow-playbook
AI Agent Workflow & Skill Architecture Guide — turn expert work into measurable, reusable agent systems. Covers workflow discovery, skill decomposition, harness design, evaluation, human escalation, observability, cost control, and multi-agent orchestration. Includes a measured marketing-delivery case: 15 people × 3–4…
vertical-construction
Domain knowledge for the construction vertical (contractors, field crews) so architect and pm don't spec construction products naively. Covers the vocabulary (bid vs estimate, takeoff, retainage, change order, AIA G702/G703, lien waiver, draw schedule), the non-obvious money rules that incumbents like Procore price…