fusebase-flow / rules
Cursor rule9 starsChanged 27 days agoMITView on GitHub
Fusebase Flow specification phase rules. Use when drafting docs/specs/*, docs/decisions/*, docs/tmp/handoff/*, docs/backlog/*.
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 4,187 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 repository119 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- .github/copilot-instructions.mdCopilot instructions
- .cursor/rules/fusebase-flow-always.mdcCursor rule
- .cursor/rules/fusebase-flow-implementation.mdcCursor rule
- .cursor/rules/fusebase-flow-security.mdcCursor rule
- .cursor/rules/fusebase-flow-validation.mdcCursor rule
- api-explorationSkill
- app-api-contract-testingSkill
- app-backendSkill
- app-business-docsSkill
- app-dev-practicesSkill
- app-e2e-testsSkill
- app-quality-patternsSkill
- app-routingSkill
- app-secretsSkill
- app-sidecarSkill
- app-ui-designSkill
- business-logic-guardianSkill
- client-vs-internalSkill
- code-reviewSkill
- comment-policySkill
- communicationSkill
- design-discovery-ideationSkill
- dev-debug-logsSkill
- documentation-budgetSkill
- file-uploadSkill
- find-wasted-codeSkill
- find-wasted-effortSkill
- fusebase-cliSkill
- fusebase-dashboardsSkill
- fusebase-flow-health-checkSkill
- fusebase-gateSkill
- fusebase-portal-specific-appsSkill
- git-history-diagnosticSkill
- git-workflowSkill
- handling-authentication-errorsSkill
- handoffSkill
- implementation-planningSkill
- invite-with-passwordSkill
- lightweight-laneSkill
- liveness-disciplineSkill
- managed-integrationsSkill
- mcp-gate-debugSkill
- module-size-disciplineSkill
- north-starSkill
- phase-auditSkill
- product-apps-decompositionSkill
- product-docs-firstSkill
- product-ownerSkill
- project-onboardingSkill
- release-deploy-reportingSkill
- remote-logsSkill
- repo-onboarding-context-mapSkill
- requirements-specificationSkill
- role-disciplineSkill
- security-permissions-reviewSkill
- skill-authoringSkill
- smoke-testingSkill
- task-delegationSkill
- The first 60 shown.
The file
We split this fusebase-flow-specs.mdc into the rules it gives an agent
4 rules. About 0 are common, 4 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈4
Distinctive · estimate
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 18
No narrative storytelling — "Decision: X.
- Distinctive: line 20
No restatement of context already in adjacent loaded files.
- Distinctive: line 22
No hedging unless filing as a clarify item.
- Distinctive: line 24
No human-onboarding preamble — open with payload.
≈ “Common” is an estimate: at least 1 in 5 of the 6,668 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: Fusebase Flow specification phase rules. Use when drafting docs/specs/*, docs/decisions/*, docs/tmp/handoff/*, docs/backlog/*.
globs: ["docs/specs/**", "docs/decisions/**", "docs/tmp/handoff/**", "docs/backlog/**", "docs/problem-catalog/**"]
alwaysApply: false
---
# Fusebase Flow — Mode B (full) for spec-side artifacts
Files in this glob are read by AI sessions, not human readers. Optimize for AI context efficiency.
## Mode B principles (full)
1. Front-load the answer — first sentence/cell IS the answer; reasoning second.
2. Tables over prose for structured data (3+ comparable rows → table).
3. Bullets over paragraphs for enumerables (3+ items → bullets).
4. Concrete over abstract — `T17`, `sha:abc1234`, `repository.ts:42-58` — never "the earlier change".
5. Predictable section names — use `templates/` headers verbatim.
6. No narrative storytelling — "Decision: X. Reason: Y. Alternatives: Z (rejected: A)." not "I considered X then thought about Y..."
7. Cross-references precise — `spec.md:42-58` not "see above".
8. No restatement of context already in adjacent loaded files.
9. Status fields tag-style — `Status: DONE`, `Lock status: LOCKED`.
10. No hedging unless filing as a clarify item.
11. Consistent vocabulary — use FLOW_RULES.md / AGENTS.md project-specific terms verbatim.
12. No human-onboarding preamble — open with payload.
## Substrates
- `docs/specs/<slug>/spec.md` ← `templates/spec.md`
- `docs/specs/<slug>/decisions.md` ← `templates/decisions.md`
- `docs/specs/<slug>/tasks.md` ← `templates/tasks.md`
- `docs/specs/<slug>/verification-gate.md` ← `templates/verification-gate.md`
- `docs/tmp/handoff/<YYYY-MM-DD>-<slug>-<stage>.md` ← workflow templates in `workflows/`
- `docs/problem-catalog/<slug>/problem.md` ← `templates/problem-catalog-entry.md`
## Anti-patterns
- ASCII visuals in spec.md/decisions.md/tasks.md (visuals belong in chat per FR-08)
- Restating constitution / spec content inside decisions.md
- Free-form decision write-ups instead of letter-prefixed matrix
- Long preambles ("This document captures...")
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.