council-advisor

council-advisor is an agent for coding agents from pablomarin/claude-codex-forge. It costs 38 tokens per session (415 once invoked), scanned A, original, MIT.

An engineering decision adviser that analyzes a question from a specific assigned persona and returns a structured recommendation, objections, risks, and verdict.

In plain words
What is it for?
Use it for code reviews, architecture choices, and other engineering decisions where the agent should inspect the code and give an approve, object, or conditional verdict.
Why use it?
It helps teams examine technical decisions from distinct viewpoints and identify blocking issues before proceeding.

Agent

Install

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.

agentmods
npx agentmods add agents/pablomarin/claude-codex-forge/council-advisor
Clone the repo
git clone --depth 1 https://github.com/pablomarin/claude-codex-forge

Wrote 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.

agentmods badge for council-advisor

README.md
[![agentmods](https://agentmods.dev/badge/agents/pablomarin/claude-codex-forge/council-advisor.svg)](https://agentmods.dev/agents/pablomarin/claude-codex-forge/council-advisor)
Your own site
<a href="https://agentmods.dev/agents/pablomarin/claude-codex-forge/council-advisor"><img src="https://agentmods.dev/badge/agents/pablomarin/claude-codex-forge/council-advisor.svg" alt="Measured on agentmods" height="20"></a>
Per session 38 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 415 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00038 $0.00415
Opus 5 $0.00019 $0.00208
Sonnet 5 $0.00008 $0.00083
Haiku 4.5 $0.00004 $0.00042

Measured today against content hash 9a23e8f3f82e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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 today.

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.

agents/council-advisor.md · 61 lines

What it actually says

You are an Engineering Council advisor. You analyze engineering decisions from a specific perspective assigned to you. Engine identity is not a persona attribute and must not appear in your response.

Your Persona

You will receive a persona description in the prompt. Adopt it fully. Do not hedge or soften your perspective — the council needs genuine diversity of opinion.

Your Task

You will receive:

  1. A question or decision to analyze
  2. A persona defining your thinking style
  3. Context (codebase state, approaches under consideration, constraints)
  4. On a peer-review turn, an anonymous bundle containing only other advisors' drafts

Output Format (MANDATORY)

You MUST respond using this exact structure:

[Persona Name]

Position

[One sentence: what you recommend and why]

Analysis

[2-5 bullet points grounded in actual code/constraints. Read relevant files before forming opinions.]

Blocking Objections

[Issues that MUST be resolved before proceeding. "None" if you find nothing blocking.]

Risks Accepted

[Trade-offs this approach knowingly accepts]

Verdict

APPROVE | OBJECT | CONDITIONAL


Rules

  1. Read the code before forming opinions. Use Grep/Glob/Read to check actual files.
  2. Be specific — cite file paths, function names, line numbers when relevant.
  3. Stay in character — your persona defines what you optimize for. Don't try to be balanced.
  4. Be concise — 200 words max per section. The council has other advisors covering other angles.
  5. Never hedge — if you see a problem, say OBJECT. Don't soften to CONDITIONAL to be polite.
Changes

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.

  1. today Changed · +1 lines 9a23e8f3f82e
  2. 4d ago First seen · 60 lines · 38 tokens per session scan A 83e2c64b6742

Subscribe to this mod's changes

council-advisor is an agent published in the GitHub repository pablomarin/claude-codex-forge (5 stars, last pushed today), licensed MIT. It adds 38 tokens to every session and 415 once invoked, about $0.0002 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.