AI-Software-Engineering-Workflow-Template / rules
Cursor rule0 starsChanged 6 months agoMITView on GitHub
Project rules for AI Software Engineering Workflow Template
Where files are headingNew Cursor rule files have more rules about planning and tracking tasks, and fewer about code style.
Of the Cursor rule files we read, the 4,243 first seen in the last six months, against the older ones: the kind of rule that gained most share, and the kind that lost most. About files like this in general, not this one, and an estimate, since a kind is a pattern in the words.
In this repository17 other files it gives its agents.
- AGENTS.mdAGENTS.md
- .cursor/rules/ai-coding-rules.mdcCursor rule
- .cursor/rules/architecture-rules.mdcCursor rule
- implementation-reportSkill
- launch-checkSkill
- mvp-scope-checkSkill
- plan-from-issueSkill
- review-artifactSkill
- scale-automation-reviewSkill
- validate-ideaSkill
- implementation-reportSkill
- launch-checkSkill
- mvp-scope-checkSkill
- plan-from-issueSkill
- review-artifactSkill
- scale-automation-reviewSkill
- validate-ideaSkill
The file
We split this project-rules.mdc into the rules it gives an agent
10 rules. About 0 are common, 9 are distinctive, and 1 is very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈9
Distinctive · estimate
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 13
DO NOT create React/Vue/Electron apps, backend services, or CLI tools as part of this template.
- Distinctive: line 25
Before editing any code, read in order:
- Distinctive: line 37
Do NOT code from vague requirements.
- Distinctive: line 38
Do NOT expand task scope without permission.
- Distinctive: line 39
Do NOT refactor unrelated code.
- Distinctive: line 40
Do NOT introduce new dependencies without justification.
- Distinctive: line 41
Do NOT bypass tests.
- Distinctive: line 42
Do NOT modify files outside the task scope.
- Distinctive: line 43
STOP and ask when uncertain.
- Distinctive: line 44
After changes, always report: what files changed, why, test results, risks.
≈ “Common” is an estimate: at least 1 in 5 of the 6,809 Cursor rule files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
--- description: Project rules for AI Software Engineering Workflow Template globs: alwaysApply: true --- # Project Rules ## Project Type This is a template repository for solo developers using AI coding tools. It is NOT a business application. DO NOT create React/Vue/Electron apps, backend services, or CLI tools as part of this template. ## Core Philosophy ``` Repository manages state, AI manages execution, CI manages quality, Human manages decisions. ``` The goal is NOT to make AI write more code, but to make AI write more maintainable code within clear boundaries and quality rules. ## Required Reading Before editing any code, read in order: 1. README.md 2. docs/00_project_brief.md 3. docs/04_architecture.md 4. docs/05_module_boundaries.md 5. docs/06_coding_standards.md 6. docs/07_testing_strategy.md 7. Current Issue or task description ## Rules 1. Do NOT code from vague requirements. Output a plan first. 2. Do NOT expand task scope without permission. 3. Do NOT refactor unrelated code. 4. Do NOT introduce new dependencies without justification. 5. Do NOT bypass tests. 6. Do NOT modify files outside the task scope. 7. STOP and ask when uncertain. 8. After changes, always report: what files changed, why, test results, risks. ## Language Documentation and comments should be primarily in Chinese, with technical terms in English where appropriate.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

