advisor

advisor is an agent for coding agents from cdeust/zetetic-team-subagents. It costs 24 tokens per session (2,665 once invoked), scanned A, original, MIT.

A reviewing agent that checks plans at important decision points and verifies whether work is complete. A cheaper model carries out the work, while this agent gives a verdict and correction list.

In plain words
What is it for?
Use it to review a plan before implementation or check completion afterward. Send its corrections to an engineer or refactoring agent.
Why use it?
It helps catch a bad plan or incomplete result before the task moves on. It is read-only and does not make code changes itself.

Agent

Part of the zetetic-team-subagents plugin — 15 skills, 1 command, 23 agents, 6 hooks, 1 MCP server shipped together

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/cdeust/zetetic-team-subagents/advisor
Clone the repo
git clone --depth 1 https://github.com/cdeust/zetetic-team-subagents

Or install zetetic-team-subagents, the plugin that ships this one along with the rest of its 15 skills, 1 command, 23 agents, 6 hooks, 1 MCP server.

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 advisor

README.md
[![agentmods](https://agentmods.dev/badge/agents/cdeust/zetetic-team-subagents/advisor.svg)](https://agentmods.dev/agents/cdeust/zetetic-team-subagents/advisor)
Your own site
<a href="https://agentmods.dev/agents/cdeust/zetetic-team-subagents/advisor"><img src="https://agentmods.dev/badge/agents/cdeust/zetetic-team-subagents/advisor.svg" alt="Measured on agentmods" height="20"></a>
Per session 24 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,665 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 5.1 $0.00024 $0.02665
Opus 5 $0.00012 $0.01333
Sonnet 5 $0.00005 $0.00533
Haiku 4.5 $0.00002 $0.00266

Measured today against content hash 9fa2cf3bb717, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

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/advisor.md · 65 lines

How it starts

The opening of the file, as written. The whole thing — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.

The economics are the contract. In Anthropic's internal benchmarks (webinar "Building on the Claude Platform: Claude Fable 5 and model orchestration patterns", Abrams & Hadfield, Anthropic Technical Staff, July 2026), the Advisor pattern reached ~92% of Fable-alone quality at ~63% of its cost on SWE-bench Pro — with Fable consulted roughly once per task. Every extra consultation erodes the pattern. If you are being called more than twice on one task, say so in your report: the caller is misusing the loop.

Distinct from [[architect]] — architect owns durable structure and emits an ADR; this agent resolves one decision point in-loop and emits a verdict, not an artifact the repo keeps. Distinct from [[code-reviewer]] — that agent reviews a diff against the standard after it exists; this one reviews a plan before it does. Hand off to [[engineer]] or [[refactorer]] with the correction list once a verdict lands (this agent holds no write tools, by design); hand off to [[architect]] when a fork turns out to be structural rather than tactical, and to [[test-engineer]] when a verification fails for want of a test that could have caught it.

Read the full file on GitHub · 65 lines

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 9fa2cf3bb717
  2. 5d ago First seen · 65 lines · 24 tokens per session scan A 74c2c472e0e1

Subscribe to this mod's changes

advisor is an agent published in the GitHub repository cdeust/zetetic-team-subagents (7 stars, last pushed today), licensed MIT. It adds 24 tokens to every session and 2,665 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 2026-08-31.