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.
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.
git clone --depth 1 https://github.com/codejunkie99/agentic-stackWrote 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.
[](https://agentmods.dev/rules/codejunkie99/agentic-stack/fable-grok-subagents)<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>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.
| Model | Per session | Once 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 |
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.
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.
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.
- yesterday First seen · 51 lines · 518 tokens per session scan A 9885b9d75bf9
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.
Other cursor rules, from other repositories
ponytail
Ponytail, lazy senior dev mode. Always pick the simplest solution that works.
angular-20
This rule provides comprehensive best practices and coding standards for Angular development, focusing on modern TypeScript, standalone components, signals, and performance optimizations.
dev-standard
Apache Superset development standards and guidelines for Cursor IDE.
cli-error-handling
CLI command error handling patterns.
prefer-direct-imports-over-module-mocks
Prefer extracting a testable core over vi.mock / vi.resetModules when unit tests need to reach production logic entangled with config, env, or singletons.
control-plane-descriptors
Control plane descriptor and instance implementation patterns.