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 Endokelp/DecisionCouncil --skill councilgit clone --depth 1 https://github.com/Endokelp/DecisionCouncilWrote 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/endokelp/decisioncouncil/council)<a href="https://agentmods.dev/skills/endokelp/decisioncouncil/council"><img src="https://agentmods.dev/badge/skills/endokelp/decisioncouncil/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/endokelp/decisioncouncil/council"><img src="https://agentmods.dev/badge/skills/endokelp/decisioncouncil/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 | $0.00124 | $0.02256 |
| Opus 5 | $0.00062 | $0.01128 |
| Sonnet 5 | $0.00025 | $0.00451 |
| Haiku 4.5 | $0.00012 | $0.00226 |
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 8d 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 — 159 lines — stays where its author put it; the contents beside it link to each section on GitHub.
DecisionCouncil
A disciplined, adversarial decision procedure inspired by Karpathy's LLM Council and the ECC council pattern. One orchestrator (you, the main session) frames the question, spawns sub-agents with distinct lenses, uses last30days and deep-research only where they earn their tokens, seats a Fact Checker, surfaces real disagreement, and synthesizes a ranked list with a clearly-marked #1 plus the condition that would change the answer.
Different from opinion-only councils: Scout establishes a shared baseline once. Fact Checker verifies contested claims (VERIFIED / PARTLY / FALSE / UNVERIFIABLE). Output is a ranked shortlist, not a single blended paragraph.
Companion skills (install together): last30days for recent social/web signal; deep-research for claim verification.
Install: npx skills add Endokelp/DecisionCouncil --skill council -g -y
Cursor (primary)
Install: ~/.cursor/skills/council/SKILL.md (run install.ps1 or install.sh from this repo).
Invoke: user must name the skill or use a trigger phrase (this skill does not auto-load):
council this: <question>/council <question>or/council full <question>run the council,pressure-test this,stress-test this,war room this,debate this@councilor "use the council skill"
Sub-agents: use the Task tool. Spawn each wave in one message with multiple parallel Task calls.
| Role | subagent_type |
run_in_background |
Notes |
|---|---|---|---|
| Scout, Advocate, Skeptic, Fact Checker | generalPurpose |
false |
Council waves must block until each agent returns |
| Repo/file discovery only | explore |
false |
Use when Step 0 needs codebase context, not for debate personas |
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.
- 8d ago First seen · 159 lines · 124 tokens per session scan A 4828c45a90f6
council is a skill published in the GitHub repository Endokelp/DecisionCouncil (4 stars, last pushed 11d ago), licensed MIT. It adds 124 tokens to every session and 2,256 once invoked, about $0.0006 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
roblox-input
Use when handling Roblox keyboard, mouse, gamepad, touch, motion input, or cross-platform action binding.
roblox-lighting
Use for Roblox lighting, atmosphere, day/night, or post-processing effects.
roblox-luau-core
Use for Luau language semantics, tables, control flow, string patterns, scope, closures, and cross-language translation errors.
roblox-performance
Use when profiling Roblox performance or diagnosing FPS, memory, network, mobile, or hot-path problems.
roblox-server-data
Use for Roblox server or cross-server data: OrderedDataStore leaderboards, MessagingService, world state, seasons, or guilds.
changelog-detective
Detect what changed in the product by comparing before and after a deploy or date — find new behaviors, new errors, changed user flows, and unexpected side effects that weren't in the release notes. Use after a deploy or when the user suspects something changed but doesn't know what.