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 gamgee-ai/council-of-gamgee --skill councilgit clone --depth 1 https://github.com/gamgee-ai/council-of-gamgeeWrote 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/gamgee-ai/council-of-gamgee/council)<a href="https://agentmods.dev/skills/gamgee-ai/council-of-gamgee/council"><img src="https://agentmods.dev/badge/skills/gamgee-ai/council-of-gamgee/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.
<a href="https://agentmods.dev/skills/gamgee-ai/council-of-gamgee/council"><img src="https://agentmods.dev/badge/skills/gamgee-ai/council-of-gamgee/council.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 | $0.00028 | $0.00871 |
| Opus 5 | $0.00014 | $0.00436 |
| Sonnet 5 | $0.00006 | $0.00174 |
| Haiku 4.5 | $0.00003 | $0.00087 |
Grade A, and why
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 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.
How it starts
The opening of the file, as written. The whole thing — 94 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Council of Gamgee — Team Debate
The user has invoked /council with the following question:
$ARGUMENTS
You must now orchestrate a full council debate. Follow these steps exactly.
Step 1: Create the Team
Call TeamCreate with team_name: "council-session".
Step 2: Spawn All Seven Advisors in Parallel
Send one message containing seven Task tool calls — all in the same response. Each call uses:
| Parameter | Value |
|---|---|
subagent_type |
The advisor's agent name (e.g., council-kautilya) |
team_name |
"council-session" |
name |
The short name (e.g., kautilya) |
prompt |
See the prompt template below |
description |
Short label (e.g., "Kautilya analysis") |
Prompt template for each advisor
Analyze the following question using your full analytical framework:
{question}
Apply every step of your methodology. Be specific and concrete — no vague generalities. When your analysis is complete, send your full analysis to team-lead via SendMessage. Then talk to the other advisors to try to disprove each other's theories, like a scientific debate. Send a final revised summary to team-lead with any positions you've updated.
Replace {question} with the user's actual question ($ARGUMENTS).
The seven advisors to spawn:
council-kautilya(name:kautilya) — Power & strategycouncil-khaldun(name:khaldun) — Historical cyclescouncil-shannon(name:shannon) — Information & evidencecouncil-girard(name:girard) — Mimetic desire & rivalrycouncil-burt(name:burt) — Network topologycouncil-musashi(name:musashi) — Timing & actioncouncil-adversary(name:adversary) — Red team & failure analysis
Step 3: Wait for the Debate to Conclude
Advisors will send initial analyses, then debate each other directly. Wait for the debate to play out — you'll see advisors going idle as they finish engaging. Once all seven have gone idle after their debate exchanges, proceed to synthesis.
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 · 94 lines · 28 tokens per session scan A cdd0f9feef0e
council is a skill published in the GitHub repository gamgee-ai/council-of-gamgee (2 stars, last pushed 6mo ago), licensed MIT. It adds 28 tokens to every session and 871 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
crewai-multi-agent
Multi-agent orchestration framework for autonomous AI collaboration. Use when building teams of specialized agents working together on complex tasks, when you need role-based agent collaboration with memory, or for production workflows requiring sequential/hierarchical execution. Built without LangChain dependencies…
shogun-bloom-config
An interactive wizard that creates model-routing settings from your AI subscription choices. Model routing decides which available model handles each kind of task.
shogun-screenshot
A screenshot tool for getting images from a computer or web page and then cropping, resizing, or masking sensitive information. Playwright is a browser-automation tool used here to capture web pages.
shogun-agent-status
A skill that shows whether the agents in a multi-agent Japanese feudal-themed team are working, waiting, missing, or assigned tasks. It combines terminal session status, task files, and unread messages.
sdlc-accelerate
End-to-end SDLC ramp-up from idea to construction-ready with automated phase transitions.
cross-task-learner
Enable agent loops to learn from similar past tasks and share patterns across loops.