spec-to-linear / rules
Cursor rule0 starsChanged 53 days agoMITView on GitHub
Break a ready spec into Linear tickets and sync them. Use when asked to plan, decompose, estimate or create tickets for a spec.
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 repository4 other files it gives its agents.
- AGENTS.mdAGENTS.md
- .cursor/rules/spec-coauthoring.mdcCursor rule
- spec-coauthorSkill
- spec-to-ticketsSkill
The file
We split this spec-to-tickets.mdc into the rules it gives an agent
5 rules. About 0 are common, 1 is distinctive, and 4 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.
4
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 11
Call get_architecture_context.
- Very specific: line 15
every new import edge goes in newDependencies
- Very specific: line 20
Call validate_plan. Fix every error, then warnings where reasonable.
- Very specific: line 23
Call preview_linear_sync and show the diff.
- Distinctive: line 24
After applying, reply with the Linear project URL and the epic URLs from the report.
≈ “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: Break a ready spec into Linear tickets and sync them. Use when asked to plan, decompose, estimate or create tickets for a spec. globs: plans/**/*.json, examples/*/plans/**/*.json alwaysApply: false --- # Spec to tickets to Linear Preconditions: `lint_spec` returns `ready: true`. If not, stop and go back to the spec. 1. Call `get_architecture_context`. Read the boundary rules closely; they decide ticket boundaries. 2. Draft a plan object that matches `packages/core/src/schema.ts`: - epics are shippable slices, tickets are one reviewable PR each (one package, two at most) - scaffolding a new package is its own ticket with `createsPackages` (name, path, layer tag) - every new import edge goes in `newDependencies` - `dependsOn` expresses order; build bottom-up: domain and migrations, then infra, features, apps - estimates on 1, 2, 3, 5, 8; split anything bigger - two to four acceptance criteria each, observable and testable - keys `<PREFIX>-E<n>` for epics and `<PREFIX>-<n>` for tickets; keep keys stable across revisions 3. Call `validate_plan`. Fix every error, then warnings where reasonable. Repeat until it returns no errors. Do not argue with a boundary finding; route the call through an allowed layer. 4. Show the engineer the ticket tree from the validation output and ask for changes before saving. 5. Call `save_plan`. 6. Call `preview_linear_sync` and show the diff. Only call `apply_linear_sync` after an explicit yes. 7. After applying, reply with the Linear project URL and the epic URLs from the report. Re-planning later: edit the saved plan, keep keys, validate, preview, apply. Sync updates changed tickets and reports removed ones; it never deletes.
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.

