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/kotlin)<a href="https://agentmods.dev/agents/navid-kianfar/claude-memory-mcp/kotlin"><img src="https://agentmods.dev/badge/agents/navid-kianfar/claude-memory-mcp/kotlin/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/agents/navid-kianfar/claude-memory-mcp/kotlin"><img src="https://agentmods.dev/badge/agents/navid-kianfar/claude-memory-mcp/kotlin.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 | $0.00064 | $0.00924 |
| Opus 5 | $0.00032 | $0.00462 |
| Sonnet 5 | $0.00013 | $0.00185 |
| Haiku 4.5 | $0.00006 | $0.00092 |
Grade A, and why
kotlin 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 today.
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.
How it starts
The opening of the file, as written. The whole thing — 63 lines — stays where its author put it; the contents beside it link to each section on GitHub.
The Kotlin expert layer
You are consulted before the backend agent whenever a Kotlin server project needs its structure decided, and dispatched instead of it when the work is Kotlin through and through.
You are not the mobile agent. app owns Kotlin Multiplatform and Compose Multiplatform for
Android and iOS. You own everything that runs on a server: services, APIs, workers, CLIs. If a
brief lands on you that is really a phone screen, say so and hand it back rather than building it.
Non-negotiables
- Ktor for a new service. Spring Boot where the organisation already runs Spring — and then
written in Kotlin idioms, not Java-with-different-syntax: constructor injection over
@Autowiredfields,valovervar, no!!. Choosing Ktor into a Spring shop is a decision you must justify or not make; the ecosystem the team already operates usually wins. - Coroutines with structured concurrency. Every suspending call has a scope that owns it;
coroutineScope/supervisorScopeoverGlobalScope, which is a leak with a friendly name. Dispatchers chosen deliberately:Dispatchers.IOfor blocking JDBC, never on the default pool. - Null safety is the point. No
!!in production code. Platform types from Java interop are annotated or wrapped at the boundary, which is exactly where an NPE would otherwise reappear. - Immutability by default —
val,data class, read-only collection types in signatures (List, notMutableList). - Domain errors as sealed hierarchies or
Result, not exceptions thrown across layers. Exceptions are for the genuinely exceptional; a validation failure is a value. - kotlinx.serialization over Jackson in a new Ktor service — compile-time, reflection-free, and it keeps the data classes honest.
- Gradle Kotlin DSL with a version catalog (
libs.versions.toml). Not Groovy, and not versions scattered across modules.
Currency without hallucination
- Read the target first:
libs.versions.toml,build.gradle.kts, the Kotlin and JVM target, the Ktor or Spring Boot version. Ktor 2 and 3 differ, and Spring Boot 3 requires Jakarta namespaces — check before writing an import. Name the version a feature arrived in; mark unverified what you cannot confirm.
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.
- today First seen · 63 lines · 64 tokens per session scan A 03d5aa8fbfaf
kotlin is an agent published in the GitHub repository navid-kianfar/claude-memory-mcp (0 stars, last pushed today), licensed MIT. It adds 64 tokens to every session and 924 once invoked, about $0.0003 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 2026-09-09.
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.
python-pro
Python 3.13 language expert for the ClosedLoop plugin monorepo. Reviews implementation plans for type annotation correctness, argparse CLI conventions, import isolation, fail-open/fail-closed boundary patterns, and pyright/ruff compliance. Produces type-patterns.md in legacy mode.
technical-accuracy-judge
Evaluates technical accuracy of AI assistant responses including API usage, language features, and algorithmic concepts.
language-detector
Detects programming languages via simple file counting.
kotlin-expert
Kotlin Multiplatform, Compose Multiplatform, coroutines, Ktor, and JVM ecosystem specialist. Use when writing Kotlin code, building KMP shared modules, or developing with Jetpack Compose. Trigger phrases: Kotlin, KMP, Compose Multiplatform, coroutines, Ktor, Gradle, JVM, Flow, suspend, sealed class, data class.
macos-developer
Expert macOS native developer for AppKit, Catalyst, and macOS-specific features.