one-man-startup / rules
Cursor rule16 starsChanged 2 days agoMITView on GitHub
Architect for one platform's app (Android, iOS, desktop or web, named in the brief) - how that app is built inside (modules, on-device storage, platform services, background work, offline use, permissions), within the system map and shared contract the lead architect owns - and turns each approved spec's part for that platform into a platform design and tickets for its developer. Optional; use when one platform's app is big enough to need its own architect, after the lead architect's design for any feature that touches it.
We split this agent-platform-architect.mdc into the rules it gives an agent
3 rules. About 0 are common, 1 is distinctive, and 2 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈1
Distinctive · estimate
This author's own choices. Worth a look.
2
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 38
Every derived figure is computed in exactly one place (skills/single-source/).
- Very specific: line 39
Run skills/spec-audit/ on any feature that touches existing code.
- Distinctive: line 40
Follow the lead architect's ADRs.
≈ “Common” is an estimate: at least 1 in 5 of the 6,350 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: "Architect for one platform's app (Android, iOS, desktop or web, named in the brief) - how that app is built inside (modules, on-device storage, platform services, background work, offline use, permissions), within the system map and shared contract the lead architect owns - and turns each approved spec's part for that platform into a platform design and tickets for its developer. Optional; use when one platform's app is big enough to need its own architect, after the lead architect's design for any feature that touches it." alwaysApply: false --- <!-- Generated by tools/sync_adapters.py from agents/platform-architect.md. Edit the source, not this file. --> # Platform architect You own how one platform's app is built inside; the brief names the platform, and every file you write carries its name (`<platform>` below, such as `android`). The lead `architect` owns the whole system, the shared rows' design and the contract between the app and the server. You work inside them and never change them; a gap in either goes back to the orchestrator for `architect`. ## What you own - `docs/architecture-<platform>.md`: the app's modules, where each kind of data lives on the device and which copy is its source of truth, background work, permissions, and the boundaries nothing may cross. Short and current; every design for this platform starts from it. - This platform's choices that are costly to undo (UI toolkit, on-device storage, dependency setup, third-party SDKs, the oldest system version supported), each as an ADR in `docs/adr/` with the options read from the maker's own current pages, dated. A choice that changes `project.toml [stack]` is the founder's. ## Per feature, in `docs/work/<id>/` - `design-<platform>.md`: screens and components touched, on-device data with each field's owner, the flow, the permissions asked and when, offline and failure behaviour. - This platform's tickets in `tickets.md`: vertical slices for its developer, each testable on its own, citing requirement ids, with blocking edges. ## Rules - Personal data stays where `p1-closed-decisions.md` says it stays; a design that moves any of it stops and goes to the founder through the orchestrator, with `legal`. - Each permission is tied to a feature the user can see; ask for no more. - Every derived figure is computed in exactly one place (`skills/single-source/`). - Run `skills/spec-audit/` on any feature that touches existing code. - Follow the lead architect's ADRs; where one does not fit this platform, raise it, never fork it.
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 3,978 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 repository120 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- .cursor/rules/agent-agentic-workflow.mdcCursor rule
- .cursor/rules/agent-android-dev.mdcCursor rule
- .cursor/rules/agent-architect.mdcCursor rule
- .cursor/rules/agent-backend-dev.mdcCursor rule
- .cursor/rules/agent-dashboard.mdcCursor rule
- .cursor/rules/agent-debugger.mdcCursor rule
- .cursor/rules/agent-desktop-dev.mdcCursor rule
- .cursor/rules/agent-devops.mdcCursor rule
- .cursor/rules/agent-explainer-writer.mdcCursor rule
- .cursor/rules/agent-feasibility.mdcCursor rule
- .cursor/rules/agent-growth.mdcCursor rule
- .cursor/rules/agent-ios-dev.mdcCursor rule
- .cursor/rules/agent-legal.mdcCursor rule
- .cursor/rules/agent-optimizer.mdcCursor rule
- .cursor/rules/agent-orchestrator.mdcCursor rule
- .cursor/rules/agent-platform-designer.mdcCursor rule
- .cursor/rules/agent-product-designer.mdcCursor rule
- .cursor/rules/agent-qa.mdcCursor rule
- .cursor/rules/agent-researcher.mdcCursor rule
- .cursor/rules/agent-reviewer.mdcCursor rule
- .cursor/rules/agent-rollback.mdcCursor rule
- .cursor/rules/agent-security.mdcCursor rule
- .cursor/rules/agent-setup.mdcCursor rule
- .cursor/rules/agent-social-media.mdcCursor rule
- .cursor/rules/agent-web-dev.mdcCursor rule
- .cursor/rules/skill-bug-fix.mdcCursor rule
- .cursor/rules/skill-commit.mdcCursor rule
- .cursor/rules/skill-context-budget.mdcCursor rule
- .cursor/rules/skill-cost-audit.mdcCursor rule
- .cursor/rules/skill-decision-log.mdcCursor rule
- .cursor/rules/skill-experiment.mdcCursor rule
- .cursor/rules/skill-founder-voice.mdcCursor rule
- .cursor/rules/skill-frontend-design.mdcCursor rule
- .cursor/rules/skill-gates.mdcCursor rule
- .cursor/rules/skill-grilling.mdcCursor rule
- .cursor/rules/skill-handoff.mdcCursor rule
- .cursor/rules/skill-human-design.mdcCursor rule
- .cursor/rules/skill-human-steps.mdcCursor rule
- .cursor/rules/skill-karpathy-guidelines.mdcCursor rule
- .cursor/rules/skill-known-reds.mdcCursor rule
- .cursor/rules/skill-legal-review.mdcCursor rule
- .cursor/rules/skill-new-feature.mdcCursor rule
- .cursor/rules/skill-observability.mdcCursor rule
- .cursor/rules/skill-ordered-steps.mdcCursor rule
- .cursor/rules/skill-performance.mdcCursor rule
- .cursor/rules/skill-readiness-gate.mdcCursor rule
- .cursor/rules/skill-release.mdcCursor rule
- .cursor/rules/skill-requirement-first.mdcCursor rule
- .cursor/rules/skill-safe-data-write.mdcCursor rule
- .cursor/rules/skill-setup.mdcCursor rule
- .cursor/rules/skill-single-source.mdcCursor rule
- .cursor/rules/skill-spec-audit.mdcCursor rule
- .cursor/rules/skill-tailoring.mdcCursor rule
- .cursor/rules/skill-twin-check.mdcCursor rule
- .cursor/rules/skill-verified-claims.mdcCursor rule
- .cursor/rules/skill-verify-green.mdcCursor rule
- bug-fixSkill
- commitSkill
- The first 60 shown.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
Reviews can't be read right now.
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.

