fable-grok-subagents

fable-grok-subagents is a cursor rule for Cursor from codejunkie99/agentic-stack. It costs 518 tokens per session, scanned A, original, Apache-2.0.

A repository setup that assigns different AI models to the main agent and delegated helper agents. The main agent handles decisions and communication, while helpers handle bounded tasks such as file searches, small edits, and test runs.

In plain words
What is it for?
It is for routing investigations, surgical edits, review, and test loops to designated helper agents.
Why use it?
It separates planning and judgment from repetitive implementation work. The advertised model split only applies when the required parent model is selected.

Cursor rule for Cursor

Written for Cursor: installed under .cursor/. Also seen: mentions subagents.

Good fit It is for routing investigations, surgical edits, review, and test loops to designated helper agents.

Compare 6 cursor rules from other repositories ↓
Install with agentmods
npx agentmods add rules/codejunkie99/agentic-stack/fable-grok-subagents
About the project

agentic-stack is a portable layer of agent memory, skills, and protocols stored in a .agent/ folder that can be used across multiple coding-agent tools. It is for people who switch between agent harnesses while keeping shared knowledge and monitoring data. The catalogue entries provide skills and rules for this shared agent layer.

codejunkie99/agentic-stack · 2,253 stars · on GitHub

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.

Clone the repo
git clone --depth 1 https://github.com/codejunkie99/agentic-stack

Made for: Cursor.

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-grok-subagents

README.md
[![agentmods](https://agentmods.dev/badge/rules/codejunkie99/agentic-stack/fable-grok-subagents.svg)](https://agentmods.dev/rules/codejunkie99/agentic-stack/fable-grok-subagents)
Your own site
<a href="https://agentmods.dev/rules/codejunkie99/agentic-stack/fable-grok-subagents"><img src="https://agentmods.dev/badge/rules/codejunkie99/agentic-stack/fable-grok-subagents.svg" alt="Measured on agentmods" height="20"></a>
Per session 518 This file is loaded in full into every session.
When invoked 518 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 $0.00518 $0.00518
Opus 5 $0.00259 $0.00259
Sonnet 5 $0.00104 $0.00104
Haiku 4.5 $0.00052 $0.00052

Measured yesterday against content hash 9885b9d75bf9, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

fable-grok-subagents 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 yesterday.

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.

.cursor/rules/fable-grok-subagents.mdc · 51 lines

What it actually says

Fable parent, Grok subagents

Prerequisite: select Claude Fable 5.1 for the parent in Cursor's model picker before starting the session. Cursor project rules cannot pin the parent model. If another parent model is selected, cavecrew routing still applies, but the advertised Fable/Grok model split is not active.

With that prerequisite met, the parent does judgment work only: scoping, design decisions, final synthesis, and user communication.

Subagents run on Grok 4.6, pinned by model: grok-4.6 in .cursor/agents/*.md. Never set a cavecrew subagent to model: inherit.

Delegate, do not do

This table is the narrow Cursor-specific exception permitted by .agent/protocols/delegation.md. Other delegation decisions follow that general protocol.

Job Subagent
Locate, bulk grep, file discovery cavecrew-investigator
1–2 file surgical edit cavecrew-builder
Diff review before commit or PR cavecrew-reviewer
Test loops and verbose shell runs cavecrew-builder (edit, then run tests, report shortest decisive line)
Parallel scouting 2–3 cavecrew-investigator in one message

Never burn Fable on grunt work

Parent never runs bulk grep, test loops, or multi-file mechanical edits itself.

Do not use built-in Explore for locate; it may pick its own helper model. Use cavecrew-investigator.

Parent reads subagent summaries only. Do not re-read the same diffs the reviewer already summarized.

Style

Caveman full on parent and cavecrew subagents (see .cursor/rules/caveman.mdc, .cursor/skills/caveman/SKILL.md).

Cavecrew contracts in .cursor/skills/cavecrew/SKILL.md. Investigator returns path:line hits. Builder returns path:line-range plus verified. Reviewer returns findings or No issues.

Limits

Cursor overrides a pinned model only when a team admin blocks it, the plan lacks it, or a legacy Max Mode rule applies (per Cursor docs).

This file is config only. It changes no product code.

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. yesterday First seen · 51 lines · 518 tokens per session scan A 9885b9d75bf9

Subscribe to this mod's changes

fable-grok-subagents is a cursor rule published in the GitHub repository codejunkie99/agentic-stack (2,253 stars, last pushed yesterday), licensed Apache-2.0. It adds 518 tokens to every session, about $0.0026 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 2026-09-06.