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/KaelSensei/MagicAIBuilderWrote 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/kaelsensei/magicaibuilder/version-management)<a href="https://agentmods.dev/rules/kaelsensei/magicaibuilder/version-management"><img src="https://agentmods.dev/badge/rules/kaelsensei/magicaibuilder/version-management/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/kaelsensei/magicaibuilder/version-management"><img src="https://agentmods.dev/badge/rules/kaelsensei/magicaibuilder/version-management.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 | $0.00709 | $0.00709 |
| Opus 5.5 | $0.00284 | $0.00284 |
| Sonnet 5.5 | $0.00142 | $0.00142 |
| Haiku 4.5 | $0.00071 | $0.00071 |
Grade A, and why
version-management 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 1mo 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 — 83 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Version Management Rules
Automatically commit and push changes after completing any feature, bug fix, or significant addition.
Commit Workflow
CRITICAL: Do this automatically without asking for user confirmation.
After completing a task (feature, bug fix, or new addition), immediately and automatically execute:
-
Quality gate (required):
- Ensure lint + tests pass
- Run
pnpm sonar - Verify SonarCloud open issues are 0
-
Stage all changes:
git add -A -
Commit with descriptive message using conventional commits:
git commit -m "type: brief description" -
Push to current branch:
git push origin $(git branch --show-current)
Do NOT ask "Should I commit?" or "Do you want me to push?" - just do it automatically.
Commit Message Types
feat:- New feature or functionalityfix:- Bug fixdocs:- Documentation changesrefactor:- Code restructuring without changing functionalitytest:- Adding or updating testschore:- Maintenance tasks, dependencies, config changesperf:- Performance improvementsstyle:- Code style changes (formatting, no logic change)
Commit Message Format
type: brief description
- Detailed bullet point 1
- Detailed bullet point 2
Examples (MagicTheOfflining):
feat: add sideboard and considering tabs to deck detailfix: show board (mainboard/sideboard/considering) in card search resultsdocs: update PLAY_STORE_DEPLOYMENT with keystore stepstest: add scraping integration tests for Moxfield decks
Rules
- ALWAYS create a branch first for fixes and features:
fix/descriptionorfeature/description— never work directly on main/master - ALWAYS commit automatically after completing a feature, fixing a bug, or adding something new - DO NOT ASK FOR PERMISSION
- ALWAYS push immediately after committing (unless push fails due to permissions) - DO NOT ASK FOR PERMISSION
- Never commit to main/master directly - always use feature branches
- Use descriptive messages that explain what and why
- Group related changes in a single commit when they're part of the same task
- No confirmation prompts - the AI assistant must execute git commands automatically as part of completing any task
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.
- 1mo ago First seen · 83 lines · 709 tokens per session scan A 6ef19d34696f
version-management is a cursor rule published in the GitHub repository KaelSensei/MagicAIBuilder (2 stars, last pushed today), licensed MIT. It adds 709 tokens to every session, about $0.0028 per session on Opus 5.5. 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.
Other cursor rules, from other repositories
git-flow
Branching, commits and PR hygiene. Always applies.
review-scope-overrides
Honor explicitly provided base branches in review artifacts.
speckit_speckit.git.commit
Proxy for the speckit.git.commit workflow.
commit
Conventional Commits specification and git commit workflow rules.
ai-coding
A set of rules for AI-assisted coding, including Chinese-language communication and comments, commit-message formatting, small changes, and human review of sensitive code.
project-core
Repository-wide project instructions. Canonical rules are in AGENTS.md.