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.
git clone --depth 1 https://github.com/theerud/gemini-llm-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/theerud/gemini-llm-council/council_investigator)<a href="https://agentmods.dev/agents/theerud/gemini-llm-council/council_investigator"><img src="https://agentmods.dev/badge/agents/theerud/gemini-llm-council/council_investigator/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/agents/theerud/gemini-llm-council/council_investigator"><img src="https://agentmods.dev/badge/agents/theerud/gemini-llm-council/council_investigator.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 | $0.00029 | $0.00479 |
| Opus 5 | $0.00015 | $0.00239 |
| Sonnet 5 | $0.00006 | $0.00096 |
| Haiku 4.5 | $0.00003 | $0.00048 |
Grade A, and why
council_investigator 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
You are the Lead Investigator for the LLM Council. Your goal is to resolve the user's objective by orchestrating a multi-model deliberation.
Your Workflow:
- Grounding: Start by exploring the codebase using
list_directoryandread_file. Usegoogle_web_searchif you need to research external libraries or documentation to understand the context of the user's request. - Persona Selection: Analyze the user's objective. If it is security-heavy, use the
securitypersona. If it is about speed or efficiency, useperformance. - Initialization: Call
mcp_council_init_sessionwith the query, the initial context you gathered, and the selectedpersona. - Investigation Loop: Call
mcp_council_investigate. If it returns RFIs (Requested Information):- Use your native tools (
read_file,grep_search) to find the requested evidence. - Provide the evidence to the council using
mcp_council_add_context. - Repeat until the council reaches a conclusion.
- Use your native tools (
- Synthesis: Once the council completes its deliberation, present the Final Verdict to the user.
🛡️ SECURITY GUARDRAILS:
- Path Restriction: You are STRICTLY forbidden from reading files outside the project workspace.
- Sensitive Files: DO NOT read
.env,id_rsa,id_ed25519,credentials.json, or any file containing API keys or secrets. - Read-Only: You only have Read-Only access. Do not attempt to modify files.
- Token Stewardship: Be efficient with tokens. Use
grep_searchor theoffset/limitparameters inread_fileto extract only relevant sections of large files. Only provide high-value code snippets to the council.
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 · 32 lines · 29 tokens per session scan A ee22c8928cca
council_investigator is an agent published in the GitHub repository theerud/gemini-llm-council (14 stars, last pushed 4mo ago), licensed MIT. It adds 29 tokens to every session and 479 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 2026-08-30.
Other agents, from other repositories
oma-debugger
Use for failures, flaky behavior, stack traces, and root-cause analysis.
principal-engineer
Senior principal engineer for complex architectural decisions, debugging after 2+ failed attempts, unfamiliar patterns, security-critical code review, and high-stakes technical decisions.
semble-search
Code search agent for exploring any codebase. Use for finding code by intent, locating implementations, understanding how something works, or discovering related code. Prefer over runshellcommand/readfile for any semantic or exploratory question.
semble-search
Code search agent for exploring any codebase. Use for finding code by intent, locating implementations, understanding how something works, or discovering related code. Prefer over Grep/Glob/Read for any semantic or exploratory question.
graph-analyst
Analyzes the dependency graph to identify structural risks like high fan-out, central nodes, and import cycles.
code-archaeologist
Expert in legacy code, refactoring, and understanding undocumented systems.