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-coding-craft)<a href="https://agentmods.dev/rules/madebyaris/advance-minimax-m3-cursor-rules/fable5-coding-craft"><img src="https://agentmods.dev/badge/rules/madebyaris/advance-minimax-m3-cursor-rules/fable5-coding-craft.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 | $0.00060 | $0.02084 |
| Opus 5 | $0.00030 | $0.01042 |
| Sonnet 5 | $0.00012 | $0.00417 |
| Haiku 4.5 | $0.00006 | $0.00208 |
Grade A, and why
fable5-coding-craft 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 8d 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 — 130 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Fable 5 Coding Craft
Distilled from how frontier coding agents earn SWE-Bench-class scores. The score does not come from knowing more syntax — it comes from judgment: finding the right place to change, changing as little as possible, and proving the change at the surface that matters. This rule transfers that judgment to any model.
The always-on core Code Discipline section is canonical for workflow (read-before-edit, CI discovery, minimal diff, verification). This rule goes deeper on the judgment calls inside that workflow.
The Craft Hierarchy
When choices conflict, optimize in this order:
- Correct — does what the user actually needs, including edge cases the repo already cares about
- Clear — a maintainer who has never seen this diff understands it in one read
- Consistent — matches this repo's naming, layering, error style, and test style
- Small — smallest honest diff; no opportunistic changes
- Fast / clever — only after the above, and only with a measurement justifying it
Never trade a level up for a level down. Clever-but-unclear is a defect, not a style.
Locate Before You Write
The highest-leverage minutes in any coding task are spent finding where the change belongs, not writing it. Most weak fixes are correct code in the wrong place.
- Start from the strongest signal: a failing test, a stack trace, an error string you can grep, or the user-visible symptom.
- Trace from symptom to mechanism: which function produced this output? Which caller decided to call it with these inputs? Where does the data originate?
- Read the neighbors before editing: the callers, the tests, and at least one sibling implementation of the same pattern. They tell you the contract you must not break and the conventions you must follow.
- Identify the owner of the behavior: the one place that is responsible for the decision you need to change. A fix at the owner is 5 lines; a fix at every symptom site is 50 and rots.
- Only then write. If you cannot name why the change belongs in this file rather than its caller or callee, you have not finished locating.
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.
- 8d ago First seen · 130 lines · 60 tokens per session scan A 16480361bfc5
fable5-coding-craft 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 2,084 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.