Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
git clone --depth 1 https://github.com/emrecanozturk/intentflow-iosWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/rules/emrecanozturk/intentflow-ios/intentflow)<a href="https://agentmods.dev/rules/emrecanozturk/intentflow-ios/intentflow"><img src="https://agentmods.dev/badge/rules/emrecanozturk/intentflow-ios/intentflow/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/rules/emrecanozturk/intentflow-ios/intentflow"><img src="https://agentmods.dev/badge/rules/emrecanozturk/intentflow-ios/intentflow.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00349 | $0.00349 |
| Opus 5.5 | $0.00140 | $0.00140 |
| Sonnet 5.5 | $0.00070 | $0.00070 |
| Haiku 4.5 | $0.00035 | $0.00035 |
Grade A, and why
intentflow scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
IntentFlow Rules
IntentFlow features are workflow-first.
Required Feature Files
Prefer this shape for non-trivial features:
<Feature>Contract.swift<Feature>Flow.swift<Feature>Effects.swift<Feature>Projection.swift<Feature>Tests.swift<Feature>.intentflow.yamlfor AI mode
Reducer Rules
- Reducers must be pure.
- Reducers may return
Next.state,.effect,.cancel,.output, and.route. - Reducers must not create
Task, call async APIs, access UI, read storage, or perform networking. - Add an explicit failure state for async workflows.
- Add an explicit in-progress state for async workflows.
Effect Rules
- Effects belong in a
FlowEffectHandler. - Long-running effects must have an
EffectID. - Replaceable effects should use
.cancelInFlight. AsyncStreameffects must cancel internal tasks inonTermination.
UI Rules
- SwiftUI views and UIKit view controllers are adapters.
- UI may render projected state and send intents.
- UI must not decide product workflow transitions.
- Navigation is emitted as a
Routeand interpreted by the app shell.
AI Mode Rules
- Update the manifest before changing contract types.
- Every new state must appear in the manifest.
- Every new effect must have a test or acceptance trace.
- Invariants must not be weakened silently.
- If a generated change violates an invariant, stop and ask for a design decision.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 1mo ago First seen · 53 lines · 349 tokens per session scan A 1bd3b95b517b
intentflow is a cursor rule published in the GitHub repository emrecanozturk/intentflow-ios (10 stars, last pushed 3mo ago), licensed MIT. It adds 349 tokens to every session, about $0.0014 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other cursor rules, from other repositories
react-native-debugger-mcp
A tool connection for reading logs from a React Native app, a framework for building mobile apps with JavaScript.
storage-rules
A local-storage rule that forbids direct use of AsyncStorage, a library for saving data on a device.
create-ios-release
As an AI assistant helping with iOS app releases, I should guide through the following process for successfully deploying iOS applications to the App Store.
203-healthkit-integration-detailed
Detailed rules for integrating Apple HealthKit and WorkoutKit. HealthKit stores health and fitness data on Apple devices, while WorkoutKit supports workout-related features.
010-healthkit-workoutkit
010: HealthKit and WorkoutKit integration patterns for iOS health apps.
main-refactoring-rules
ios cursor rules.