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.
npx agentmods add instructions/emrecanozturk/intentflow-ios/agents-mdgit 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/instructions/emrecanozturk/intentflow-ios/agents-md)<a href="https://agentmods.dev/instructions/emrecanozturk/intentflow-ios/agents-md"><img src="https://agentmods.dev/badge/instructions/emrecanozturk/intentflow-ios/agents-md.svg" alt="Measured on agentmods" 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 | $0.00431 | $0.00431 |
| Opus 5 | $0.00216 | $0.00216 |
| Sonnet 5 | $0.00086 | $0.00086 |
| Haiku 4.5 | $0.00043 | $0.00043 |
Grade A, and why
intentflow-ios AGENTS.md 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 6d 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
Agent Instructions
IntentFlow is a workflow-first Swift architecture for iOS. Treat feature behavior as the source of truth, then adapt SwiftUI or UIKit to that behavior.
Read First
- Start with
.ai/agent-context.mdfor the compact repository map. - For AI-mode feature work, read the feature
.intentflow.yamlmanifest before Swift implementation files. - For architecture rationale, read
docs/ai/intentflow-ai.md,docs/rationale/design-principles.md, anddocs/advanced/memory-and-concurrency.md. - Avoid reading generated Xcode project internals unless the task is explicitly about the demo app project.
Architecture Rules
- Update the manifest before changing AI-mode state, intent, event, effect, output, or route contracts.
- Keep reducers pure. Reducers must not call networking, persistence, analytics, timers, UI APIs, or start
Task. - Put async work in
FlowEffectHandlerand return events to the store. - Use
EffectIDand cancellation policies for long-running, repeatable, or replaceable work. - Model navigation as typed
Routeoutput and parent communication as typedOutput. - Keep SwiftUI views and UIKit view controllers as adapters over projected state.
- Add reducer/trace tests for every behavior branch you introduce.
Commands
swift test
swift run intentflow validate .intentflow/login.intentflow.yaml
swift run intentflow ai-context .intentflow/login.intentflow.yaml --tool codex
./scripts/check.sh
Token Budget
- Prefer
swift run intentflow ai-context <manifest> --tool <codex|claude|gemini|copilot>over loading the whole repository. - Use
.ai/agent-context.mdas the short map and only open files directly touched by the requested change. - Do not paste complete generated files into discussion unless the user asks for them.
Release Standard
A change is not ready if it only changes prose or code. It should also update the relevant manifest, tests, docs, and agent instructions when behavior or workflow changes.
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.
- 6d ago First seen · 40 lines · 431 tokens per session scan A e278f60ef02e
intentflow-ios AGENTS.md is an instructions file published in the GitHub repository emrecanozturk/intentflow-ios (10 stars, last pushed 1mo ago), licensed MIT. It adds 431 tokens to every session, about $0.0022 per session on Opus 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 instructions, from other repositories
Bark CLAUDE.md
Claude Code instructions for Finb/Bark, a project described as: Bark is an iOS App which allows you to push custom notifications to your iPhone.
Navigator CLAUDE.md
Instructions for hmlongco/Navigator, covering claude.md, core pattern, key patterns, source layout and skill.
MarkdownView AGENTS.md
Instructions for keitaoouchi/MarkdownView, covering agents, technical components, relationships (data/event flow overview), extension points (overview) and platform / distribution.
tv-maniac GEMINI.md
Gemini CLI instructions for thomaskioko/tv-maniac, covering tv maniac agent rules, project overview, architecture & tech stack, core mandates & conventions and 1. modularization & dependencies.
swift-architecture-skill CLAUDE.md
Instructions for efremidze/swift-architecture-skill, covering swift architecture skill, project structure, how the skill works and key conventions.
swift-architecture-skill AGENTS.md
Instructions for efremidze/swift-architecture-skill, covering agents guidelines for swift architecture skill, working with this repository, 1. understanding the skill, 2. modifying architecture playbooks and 3. testing and validation.