one-man-startup / rules
Cursor rule16 starsChanged 2 days agoMITView on GitHub
No unconfirmed assumptions - every factual claim the founder or a user will read is confirmed by a source, test or measurement, or cut, or registered in docs/ASSUMPTIONS.md and labelled. Use when writing any document, copy, report, estimate or recommendation, and when reviewing one.
We split this skill-verified-claims.mdc into the rules it gives an agent
1 rule. About 0 are common, 1 is distinctive, and 0 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.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 47
When you review someone else's artifact, a claim with no source is a finding, the same as a bug.
≈ “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: "No unconfirmed assumptions - every factual claim the founder or a user will read is confirmed by a source, test or measurement, or cut, or registered in docs/ASSUMPTIONS.md and labelled. Use when writing any document, copy, report, estimate or recommendation, and when reviewing one."
alwaysApply: false
---
<!-- Generated by tools/sync_adapters.py from skills/verified-claims/SKILL.md. Edit the source, not this file. -->
# Verified claims
A plausible guess reads exactly like a fact. Once it is written down, the next agent repeats it
and the founder makes a decision on it. So guesses are not written down as facts.
## Before a claim goes in
For each statement of fact (a price, a duration, a limit, a count, a date, legal status, what a
tool or service supports, what a test covers), ask: how do I know?
- **A source:** link it and the date you read it. Prefer the primary source (the provider's
pricing page, the law, the official docs) over a blog about it. **Cite only a page you opened
in this session**, and quote the sentence that supports the claim. A page you could not open
is not a source: say so, or mark the claim UNSETTLED. Never write "checked" for a page you
did not read. `python tools/link_check.py <files>` finds cited links that do not exist.
- **A test or measurement:** name it, or the command and its output. A platform fact whose
page cannot be fetched (some design guideline sites return only a title) is measured instead:
`qa` confirms it on a real device or emulator and names the device and version.
- **Neither:** cut the claim, or say the true thing instead ("check the tool's pricing page"
rather than a price you remember).
## When we have to rely on it anyway
Some things can only be confirmed later (how long setup takes, whether a tool loads a file the
way its docs say). Register each one in `docs/ASSUMPTIONS.md`:
| ID | Assumption | Used in | How to confirm | Confirm by | Status |
and label it where it is used, linking the register. The sweep fails when an open assumption is
past its confirm-by date. When it is confirmed or disproved, update the status and fix every
place it was used in the same change.
## Estimates
An estimate is allowed when it is labelled as one, with what it is based on: "about 3 hours,
estimated from the last two features of this size". An unlabelled number is a claim.
## Reviewing
When you review someone else's artifact, a claim with no source is a finding, the same as a bug.
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-architect.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-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.

