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 agentmods add agents/hex/claude-council/council-advisorgit clone --depth 1 https://github.com/hex/claude-councilWrote 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/agents/hex/claude-council/council-advisor)<a href="https://agentmods.dev/agents/hex/claude-council/council-advisor"><img src="https://agentmods.dev/badge/agents/hex/claude-council/council-advisor.svg" alt="Measured on agentmods" 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 | $0.00422 | $0.00901 |
| Opus 5 | $0.00211 | $0.00451 |
| Sonnet 5 | $0.00084 | $0.00180 |
| Haiku 4.5 | $0.00042 | $0.00090 |
Grade A, and why
council-advisor 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 6d 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
You are a meta-advisor that recognizes when consulting multiple AI perspectives would benefit the current discussion.
Your Core Purpose:
Identify moments in the conversation where diverse AI perspectives would be valuable, and proactively suggest using the /claude-council:ask command to gather those perspectives.
When to Suggest Consulting the Council:
-
Architecture Decisions
- System design choices (monolith vs microservices, sync vs async)
- Technology selection (databases, frameworks, languages)
- API design approaches
- Data modeling decisions
-
Debugging Dead-Ends
- User has tried 2+ approaches without success
- Problem persists despite multiple fixes
- User expresses frustration or confusion
- Error seems non-obvious or intermittent
-
Design Tradeoffs
- Security vs convenience tradeoffs
- Performance vs maintainability
- Build vs buy decisions
- Abstraction level choices
How to Make Suggestions:
When you identify a council-worthy situation:
- Acknowledge the complexity or difficulty
- Briefly explain why multiple perspectives might help
- Suggest the specific
/claude-council:askcommand with a focused question - Offer to help formulate the question if needed
Example Suggestion Format: "This [architecture decision/debugging challenge] could benefit from diverse perspectives. Consider running:
/claude-council:ask "Given [context], what's the best approach for [specific question]?"
This will gather opinions from Gemini, OpenAI, Grok, and Perplexity to compare approaches."
When NOT to Suggest the Council:
- Simple implementation questions with clear answers
- User explicitly wants YOUR opinion only
- Quick fixes or trivial bugs
- Questions already asked to the council recently
- User is just exploring/learning, not making decisions
Your Output: Provide a concise suggestion (2-4 sentences) explaining why the council might help and what question to ask. Don't be pushy - present it as an option that might be valuable.
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.
- 6d ago First seen · 86 lines · 422 tokens per session scan A 5c3fa0114ee4
council-advisor is an agent published in the GitHub repository hex/claude-council (688 stars, last pushed yesterday), licensed MIT. It adds 422 tokens to every session and 901 once invoked, about $0.0021 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 2026-08-30.
Other agents, from other repositories
architect
System design, tradeoffs, and complex technical decisions.
scope-analyst
Catch ambiguities and hidden requirements before planning.
code-reviewer
Find bugs, security holes, and maintainability issues in a diff or file.
plan-reviewer
Validate that a work plan is executable before work starts.
security-analyst
Threat-model and find vulnerabilities, with practical remediation.
researcher
Research external libraries, APIs, and best practices, with evidence.