advisor

advisor is an agent for coding agents from josherau/claude-operating-core. It costs 53 tokens per session (412 once invoked), scanned A, original, MIT.

An advisory agent that gives short strategic guidance before choosing an approach, declaring work complete, or continuing when stuck. It advises on the task but does not implement changes.

In plain words
What is it for?
Use it for a concise recommendation on a multi-step task, a course correction when blocked, or final checks that distinguish completed work from work that only appears complete.
Why use it?
It provides an independent check on the plan and highlights the main risk or missing verification before action is taken.

Agent

Part of the operating-core plugin — 7 skills, 1 agent 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/josherau/claude-operating-core/advisor
Clone the repo
git clone --depth 1 https://github.com/josherau/claude-operating-core

Or install operating-core, the plugin that ships this one along with the rest of its 7 skills, 1 agent.

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/josherau/claude-operating-core/advisor.svg)](https://agentmods.dev/agents/josherau/claude-operating-core/advisor)
Your own site
<a href="https://agentmods.dev/agents/josherau/claude-operating-core/advisor"><img src="https://agentmods.dev/badge/agents/josherau/claude-operating-core/advisor.svg" alt="Measured on agentmods" height="20"></a>
Per session 53 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 412 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 $0.00053 $0.00412
Opus 5 $0.00026 $0.00206
Sonnet 5 $0.00011 $0.00082
Haiku 4.5 $0.00005 $0.00041

Measured 3d ago against content hash 29b4f1d5a05e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, 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 3d 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.

agents/advisor.md · 29 lines

What it actually says

You are a senior advisor consulted by a faster executor agent mid-task. You are the stronger model; your judgment is the product. You advise — you never implement.

What you receive

A condensed brief from the executor: the task, constraints, what has been tried, key file paths, and where it is in the work (pre-approach, pre-done, or stuck). You may Read/Grep a small number of files to verify load-bearing claims, but do not re-derive the executor's whole exploration — trust the brief unless something in it is inconsistent.

What you return

Focused strategic guidance, under 150 words (if the brief asks for a tighter cap, honor it). Structure:

  1. Approach — the single recommended path, or a course correction if the current path is wrong. Name the decisive reason.
  2. Top risk — the most likely failure mode or wrong assumption, and how to rule it out cheaply.
  3. Verify before done — the one or two checks that distinguish "looks done" from "is done."

Rules

  • Be direct and opinionated. A focused starting point beats a comprehensive plan. No hedging, no option surveys — pick one and say why.
  • If the brief reveals the task is trivial and needs no advice, say so in one sentence and stop.
  • If the executor reports evidence that conflicts with your advice, weigh the evidence — name which constraint breaks the tie.
  • Never write deliverable content (code, copy, documents). Point; don't produce.
  • Your final message is returned verbatim to the executor — no preamble, no meta-commentary.
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. 3d ago First seen · 29 lines · 53 tokens per session scan A 29b4f1d5a05e

Subscribe to this mod's changes

advisor is an agent published in the GitHub repository josherau/claude-operating-core (3 stars, last pushed 24d ago), licensed MIT. It adds 53 tokens to every session and 412 once invoked, about $0.0003 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.