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 happycapy-ai/Happycapy-skills --skill llm-councilgit clone --depth 1 https://github.com/happycapy-ai/Happycapy-skillsWrote 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/happycapy-ai/happycapy-skills/llm-council)<a href="https://agentmods.dev/skills/happycapy-ai/happycapy-skills/llm-council"><img src="https://agentmods.dev/badge/skills/happycapy-ai/happycapy-skills/llm-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/happycapy-ai/happycapy-skills/llm-council"><img src="https://agentmods.dev/badge/skills/happycapy-ai/happycapy-skills/llm-council.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Rogue Agent · line 24 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
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 | $0.00132 | $0.00630 |
| Opus 5 | $0.00066 | $0.00315 |
| Sonnet 5 | $0.00026 | $0.00126 |
| Haiku 4.5 | $0.00013 | $0.00063 |
Grade A, and why
llm-council scanned grade A with 1 finding 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
sleep 2 && curl -s --max-time 5 http://localhost:8787/health What it actually says
LLM Council
Query multiple AI models in parallel with a live web dashboard.
Launch
cd ~/.claude/skills/llm-council/scripts
# Kill any existing server on the port
fuser -k 8787/tcp 2>/dev/null
# Start server
nohup python3 server.py > /tmp/council-server.log 2>&1 &
# Wait for startup, verify health
sleep 2 && curl -s --max-time 5 http://localhost:8787/health
# Export port for browser access
/app/export-port.sh 8787
Environment: COUNCIL_PORT (default 8787), AI_GATEWAY_API_KEY (required, auto-detected from environment).
Files
scripts/server.py- ThreadingHTTPServer, serves static files + API routes, SSE streamingscripts/ai_gateway.py- AI Gateway client: query, parallel query, streaming, synthesis, anonymous votingscripts/static/index.html- Dashboard UI (HappyCapy design system, light/dark theme)scripts/static/app.js- Client-side logic (model selector, SSE parsing, markdown rendering, voting UI)
API
| Method | Path | Description |
|---|---|---|
| GET | / |
Dashboard |
| GET | /api/models |
List models |
| GET | /health |
Health check |
| POST | /api/council/stream |
Query models (SSE) |
| POST | /api/council/synthesize |
Synthesize consensus |
| POST | /api/council/vote |
Anonymous model vote (SSE with keepalive) |
Key Details
- Server uses
ThreadingHTTPServerfor concurrent request handling - Vote endpoint streams SSE keepalive pings every 5s to prevent proxy timeouts (Cloudflare 524)
- Static files served with
Cache-Control: no-store, no-cacheheaders - Script tag uses cache-busting version param:
app.js?v=...(bump when editing app.js) - Model IDs use dots not hyphens:
anthropic/claude-sonnet-4.5(notclaude-sonnet-4-5)
What ships with it
6 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 132 tokens per session scan A 123a0f37b55d
llm-council is a skill published in the GitHub repository happycapy-ai/Happycapy-skills (139 stars, last pushed 9d ago), licensed MIT. It adds 132 tokens to every session and 630 once invoked, about $0.0007 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
llm-app-patterns
Production-ready patterns for building LLM applications. Covers RAG pipelines, agent architectures, prompt IDEs, and LLMOps monitoring. Use when designing AI applications, implementing RAG, building agents, or setting up LLM observability.
prompt-optimization
Improve a prompt on the evaluations workbench through a measured loop. Score the baseline first, then duplicate the target column, form a hypothesis from failing rows, edit the copy's prompt draft, run, compare pass rate and cost, and repeat until the numbers hold. Use when the user asks to optimize or improve a…
enhance-prompt
Transforms vague UI ideas into polished, Stitch-optimized prompts. Enhances specificity, adds UI/UX keywords, injects design system context, and structures output for better generation results.
prompt-engineer
Writes, refactors, and evaluates prompts for LLMs — generating optimized prompt templates, structured output schemas, evaluation rubrics, and test suites. Use when designing prompts for new LLM applications, refactoring existing prompts for better accuracy or token efficiency, implementing chain-of-thought or few-shot…
seedance-vocab-en
This skill should be used when an English Seedance 2.0 prompt needs clearer production wording, less generic prose, or precise vocabulary for camera, lighting, motion, VFX, audio, and constraints. Route blocked prompts through seedance-filter for context and boundary review.
ideogram4
Prompting patterns for Ideogram 4 text-to-image — best-in-class in-image text rendering and exact color/layout control via structured JSON captions. Use when generating images that need legible on-image text (title cards, thumbnails, logos, signage, CTAs), precise brand colors, or controlled spatial layout. Triggers…