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/madebyaris/advance-minimax-m3-cursor-rulesWrote 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/madebyaris/advance-minimax-m3-cursor-rules/fable5-reasoning)<a href="https://agentmods.dev/rules/madebyaris/advance-minimax-m3-cursor-rules/fable5-reasoning"><img src="https://agentmods.dev/badge/rules/madebyaris/advance-minimax-m3-cursor-rules/fable5-reasoning/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/rules/madebyaris/advance-minimax-m3-cursor-rules/fable5-reasoning"><img src="https://agentmods.dev/badge/rules/madebyaris/advance-minimax-m3-cursor-rules/fable5-reasoning.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00060 | $0.01751 |
| Opus 5 | $0.00030 | $0.00875 |
| Sonnet 5 | $0.00012 | $0.00350 |
| Haiku 4.5 | $0.00006 | $0.00175 |
Grade A, and why
fable5-reasoning 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 10d 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.
How it starts
The opening of the file, as written. The whole thing — 108 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Fable 5 Reasoning Protocols
The always-on core defines the short Reasoning Protocol. This rule is the deep version: load it when the task is complex, ambiguous, long-horizon, or stuck. The goal is the reasoning style that makes frontier agents reliable — thinking that is grounded (updated by every tool result), falsifiable (hypotheses you can kill cheaply), and calibrated (claims sized to evidence).
These protocols are model-agnostic. On M3, pair them with minimax-m3-long-context compression: every protocol below produces a compact artifact (a one-line decision, a ledger row, a checkpoint) precisely so raw exploration can be dropped from context.
Task Interpretation: Three Readings
Before planning, read the request three ways:
- Literal — exactly what was typed.
- Intent — the problem the user is trying to solve. ("Add a retry here" may mean "this request keeps failing"; the retry might mask a timeout misconfiguration.)
- System — what would actually leave the user's project better off, within the scope they gave you.
Work at the intent reading by default. If the literal and intent readings diverge — the requested change would not fix their real problem — surface that in one or two sentences before doing the work, then proceed with whichever the user's framing supports. Never silently substitute your own goal for theirs.
Close the interpretation step by writing (for yourself) one operational sentence: "Done means ___, proven by ___." If you cannot fill in the second blank, you do not understand the task yet.
Decomposition: Vertical And Risk-First
- Slice vertically, not horizontally. Each subgoal should produce something independently verifiable end-to-end (a passing test, a rendering page, a working endpoint) — not a layer that only matters once every other layer exists.
- Front-load the riskiest unknown. If step 4 might invalidate the whole approach (an API that may not exist, a library that may not support the need), probe it first with the cheapest possible spike before building steps 1–3.
- Keep the plan falsifiable: each step has an observable success signal. "Set up the service" is not a step; "service responds 200 on /health" is.
- Re-plan when reality disagrees. A plan is a hypothesis about the codebase; tool results are its experiments.
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.
- 10d ago First seen · 108 lines · 60 tokens per session scan A 26cd13944835
fable5-reasoning is a cursor rule published in the GitHub repository madebyaris/advance-minimax-m3-cursor-rules (125 stars, last pushed 2mo ago), licensed MIT. It adds 60 tokens to every session and 1,751 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 2026-08-30.
Other cursor rules, from other repositories
git-commit
Use this when the user asks for a git commit, commit message, or commit command.
learnship
Activate learnship agentic engineering workflows — structured phases, persistent memory, learning partner, and impeccable UI design. Use whenever a user is working on a software project or asks about project planning, phases, workflows, or how to build something.
behavior-principles
Global behavioral principles for all AI-assisted work in this repository. Covers thinking before coding, simplicity, surgical changes, goal-driven execution, and communication standards.
coding
Core coding behavior for this repository. Always prefer cautious, minimal, reversible changes.
testing
Optional Spring Boot example-pack testing rules. Apply only when editing an adopted project or spring-boot profile output.
workflow
Workflow canonical adapter and intent routing rules.