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.
npx skills add golemfoundation/octant-council-builder --skill octant-council-buildergit clone --depth 1 https://github.com/golemfoundation/octant-council-builderWrote 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/octant-council-builder)<a href="https://agentmods.dev/skills/golemfoundation/octant-council-builder/octant-council-builder"><img src="https://agentmods.dev/badge/skills/golemfoundation/octant-council-builder/octant-council-builder/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/octant-council-builder"><img src="https://agentmods.dev/badge/skills/golemfoundation/octant-council-builder/octant-council-builder.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 | $0.00000 | $0.00897 |
| Opus 5 | $0.00000 | $0.00449 |
| Sonnet 5 | $0.00000 | $0.00179 |
| Haiku 4.5 | $0.00000 | $0.00090 |
Grade A, and why
octant-council-builder 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.
What it actually says
Read this file, then follow the steps below to set up the council plugin for the user.
Steps
-
Detect the user's shell (
$SHELL) and resolve the config file:- zsh →
~/.zshrc - bash →
~/.bashrc(or~/.bash_profileon macOS if.bashrcdoesn't exist) - fish →
~/.config/fish/config.fish
- zsh →
-
Check if the council repo exists locally:
- Look for
.claude-plugin/plugin.jsonin the current directory - Check common locations:
~/git/octant-council-builder,~/octant-council-builder,~/projects/octant-council-builder,~/code/octant-council-builder,~/src/octant-council-builder - If found, store the absolute path as
$PLUGIN_DIR - If not found, set
$REPO_FOUND=false
- Look for
-
Before doing anything else, explain to the user what setup will do and ask for confirmation. Include:
- How plugins work:
--plugin-dirtells Claude Code to load.claude-plugin/plugin.jsonfrom a directory and register allskills/*/SKILL.mdfiles as slash commands - If repo not found: that we'll clone it from
https://github.com/golemfoundation/octant-council-builder.git - That we'll create a shell alias (e.g.
alias council='claude --plugin-dir /path/to/repo') - Why the alias is useful: keeps things isolated — the council only loads when you use the alias, plain
claudestays clean - That we'll enable the agent teams env var (
CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS=1) - That the alias points at the local clone, so editing agent/skill markdown files takes effect immediately
- Mention
/reload-pluginsfor picking up skill changes during a live session - Wait for user confirmation before proceeding. If they cancel, stop.
- How plugins work:
-
If repo was not found, ask where to clone it (default:
~/git/octant-council-builder) and run:git clone https://github.com/golemfoundation/octant-council-builder.git "$CLONE_DIR"Set
$PLUGIN_DIRto the clone location. -
Ask the user what alias name they want (e.g.
council,pgc,eval,betty,hal). -
Check the alias isn't already taken (
command -v/alias). If it is, let them know and ask again. -
Remove any existing lines tagged
# public-goods-councilfrom the config file, then append:For zsh/bash:
alias NAME='claude --plugin-dir PLUGIN_DIR' # public-goods-council export CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS=1 # public-goods-councilFor fish:
alias NAME "claude --plugin-dir PLUGIN_DIR" # public-goods-council set -gx CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS 1 # public-goods-council -
Tell the user to run:
source [config file] && cd $PLUGIN_DIR && $ALIAS_NAMEThen explain:
- How the alias works:
--plugin-dirloads the plugin from the repo. The council skills only appear when you use the alias — plainclaudestays unaffected. - Developing your council: agents are markdown files in
agents/— edit them and changes are picked up on the next/council:evaluate. Skills are inskills/*/SKILL.md— run/reload-pluginsinside a session to pick up skill changes without restarting. No build step, no compilation. - Sharing your council: once you design your own council, push your fork and share the repo URL. Anyone can clone it and run
/council:settingsto install your council as a plugin.
- How the alias works:
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.
- 12d ago First seen · 58 lines · 0 tokens per session scan A 6b6f6669c80e
octant-council-builder is a skill published in the GitHub repository golemfoundation/octant-council-builder (3 stars, last pushed 5mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 897 tokens. 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…
stack-baseline
The pinned default technology stack for SMB Product-Builder products. One source of truth so the architect, app-scaffolder, auth-engineer, and senior-dev never re-decide the stack per build — they build ON it. Covers framework, ORM/DB, auth, UI, payments/email/SMS, files, jobs, testing, hosting, and observability…
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…