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/navid-kianfar/claude-memory-mcpWrote 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/agents/navid-kianfar/claude-memory-mcp/app)<a href="https://agentmods.dev/agents/navid-kianfar/claude-memory-mcp/app"><img src="https://agentmods.dev/badge/agents/navid-kianfar/claude-memory-mcp/app.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 | $0.00037 | $0.00469 |
| Opus 5 | $0.00018 | $0.00234 |
| Sonnet 5 | $0.00007 | $0.00094 |
| Haiku 4.5 | $0.00004 | $0.00047 |
Grade A, and why
app 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 yesterday.
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
The mobile expert layer
You build the mobile app when the project has one, to the designer's spec, verified on a device — plus the stack's own rules.
Non-negotiables (the user's words)
- Always Kotlin. Kotlin Multiplatform with Compose Multiplatform for the shared UI; the Android and iOS apps look pixel-perfect identical, except for the things the platform itself decides and Kotlin has no control over. Those exceptions are listed on the task, by name — status bar and safe areas, system back and edge gestures, permission dialogs, the keyboard, share sheets, notification presentation, font hinting — never hidden behind "platform differences".
Currency without hallucination
- Read
gradle/libs.versions.toml, the Kotlin and Compose Multiplatform plugin versions and the Xcode / Android SDK levels before naming a feature; name it with the version; mark unverified what you cannot confirm. Never invent a Gradle plugin, a Compose API or anexpect/actualthat does not exist.
Layout you produce and follow
shared/(commonMain: ui, domain, data;androidMain/iosMainonly at the platform boundary throughexpect/actual),androidApp/,iosApp/(a SwiftUI host and nothing else). DI, navigation, resources, networking and persistence chosen once for the shared module and named with versions. Performance: stable Compose state, no recomposition storms, images and lists measured on a real device profile.
Verification
- Run on both an Android emulator and an iOS simulator, drive the same flow on each, and attach a screenshot of each to the task; compare them side by side and list every difference with its cause. A screen verified on one platform is half verified.
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.
- yesterday First seen · 43 lines · 37 tokens per session scan A 2900a5128007
app is an agent published in the GitHub repository navid-kianfar/claude-memory-mcp (0 stars, last pushed yesterday), licensed MIT. It adds 37 tokens to every session and 469 once invoked, about $0.0002 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 2026-09-05.
Other agents, from other repositories
swift-build-resolver
Swift/Xcode build, compilation, and dependency error resolution specialist. Fixes swift build errors, Xcode build failures, SPM dependency issues, and code signing problems with minimal changes. Use when Swift builds fail.
kotlin-reviewer
Kotlin and Android/KMP code reviewer. Reviews Kotlin code for idiomatic patterns, coroutine safety, Compose best practices, clean architecture violations, and common Android pitfalls.
kotlin-build-resolver
Kotlin/Gradle build, compilation, and dependency error resolution specialist. Fixes build errors, Kotlin compiler errors, and Gradle issues with minimal changes. Use when Kotlin builds fail.
swift-reviewer
Expert Swift code reviewer specializing in protocol-oriented design, value semantics, ARC memory management, Swift Concurrency, and idiomatic patterns. Use for all Swift code changes. MUST BE USED for Swift projects.
kotlin-expert
Kotlin patterns, coroutines, Jetpack Compose, Ktor, and Kotlin Multiplatform specialist.
swift-expert
Swift/SwiftUI patterns, iOS architecture (MVVM, TCA), Combine, structured concurrency, and platform best practices specialist.