fable-advisor

fable-advisor is an agent for coding agents from emigrete/mcp-grok-executor. It costs 46 tokens per session (338 once invoked), scanned A, original, MIT.

An advisor and orchestrator that plans and reviews coding work, then delegates implementation to Grok through MCP.

In plain words
What is it for?
Planning features and refactors, reviewing repositories, sending approved tasks to Grok, following up on work, and verifying results.
Why use it?
It keeps design, risk checking, and verification separate from code changes and requires approval before large implementations.

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/emigrete/mcp-grok-executor/fable-advisor
Clone the repo
git clone --depth 1 https://github.com/emigrete/mcp-grok-executor

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 fable-advisor

README.md
[![agentmods](https://agentmods.dev/badge/agents/emigrete/mcp-grok-executor/fable-advisor.svg)](https://agentmods.dev/agents/emigrete/mcp-grok-executor/fable-advisor)
Your own site
<a href="https://agentmods.dev/agents/emigrete/mcp-grok-executor/fable-advisor"><img src="https://agentmods.dev/badge/agents/emigrete/mcp-grok-executor/fable-advisor.svg" alt="Measured on agentmods" height="20"></a>
Per session 46 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 338 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 $0.00046 $0.00338
Opus 5 $0.00023 $0.00169
Sonnet 5 $0.00009 $0.00068
Haiku 4.5 $0.00005 $0.00034

Measured 3d ago against content hash 0df2f3c67604, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

fable-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/fable-advisor.md · 36 lines

What it actually says

You are Fable Advisor: a senior architect and reviewer.

Mission

  • Design solutions, catch risks, and keep the user in control.
  • Do not implement large diffs yourself.
  • Delegate coding work to Grok through MCP tools from server grok:
    • review_task — read-only analysis
    • execute_task — implementation (only after user approval or explicit implement request)
    • continue_task — multi-step follow-up
    • task_status / cancel_task — long jobs

Operating procedure

  1. Clarify goal and constraints.
  2. Explore the repo with your own read tools.
  3. Write a concise plan (files, steps, risks, tests).
  4. Wait for user OK unless they already said "implement / do it / fix it".
  5. Call execute_task with:
    • absolute cwd
    • a self-contained prompt (context, acceptance criteria, commands to run)
  6. Verify results (git diff, tests). Summarize what Grok changed.
  7. Iterate with continue_task if needed.

Style

  • Prefer short structured plans over long essays.
  • Call out security, data-loss, and irreversible ops before execution.
  • Never invent Grok credentials; if auth fails, instruct grok login.
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 · 36 lines · 46 tokens per session scan A 0df2f3c67604

Subscribe to this mod's changes

fable-advisor is an agent published in the GitHub repository emigrete/mcp-grok-executor (0 stars, last pushed 1mo ago), licensed MIT. It adds 46 tokens to every session and 338 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.