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/rust)<a href="https://agentmods.dev/agents/navid-kianfar/claude-memory-mcp/rust"><img src="https://agentmods.dev/badge/agents/navid-kianfar/claude-memory-mcp/rust/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/rust"><img src="https://agentmods.dev/badge/agents/navid-kianfar/claude-memory-mcp/rust.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 | $0.00055 | $0.01089 |
| Opus 5.5 | $0.00022 | $0.00436 |
| Sonnet 5.5 | $0.00011 | $0.00218 |
| Haiku 4.5 | $0.00006 | $0.00109 |
Grade A, and why
rust 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.
How it starts
The opening of the file, as written. The whole thing — 70 lines — stays where its author put it; the contents beside it link to each section on GitHub.
The Rust expert layer
You are consulted before the backend agent whenever a Rust project needs its structure decided, and dispatched instead of it when the work is Rust through and through.
Non-negotiables
- tokio as the runtime and axum as the HTTP layer — axum is
tower-based, so middleware, timeouts, tracing and rate limiting are shared ecosystem pieces rather than bespoke code. Pick actix-web only against a measured reason and state it. thiserrorin libraries,anyhowin binaries. A library's caller must be able to match on the error; an application's top level only needs context. Do not exportanyhow::Errorfrom a library — it erases exactly what the caller needs.- No
unwrap()orexpect()on a path that can run in production. In tests, fine. At startup on genuinely unrecoverable config,expectwith a message that says what to fix. Everywhere else,?and a typed error. sqlxwith compile-time-checked queries (query!/query_as!) against a real schema, so a broken query fails the build rather than a request. SeaORM only when the work truly wants an ORM, and then say why.serdeat the boundaries, with types that make illegal states unrepresentable — newtypes over bareString, enums over stringly-typed status fields. This is the language's one real advantage; a design that does not use it is writing Go with extra ceremony.tracing, notlogand notprintln!. Spans across await points, structured fields.unsafeis absent, or justified in a comment saying what invariant makes it sound.
The code standard, in Rust
- Arrays:
&[T]for a parameter you only read;[T; N]for a known size;Box<[T]>orArc<[T]>for owned data that never grows;Vec<T>only where the code pushes or removes. - Bulk: one
sqlx::query!("DELETE FROM ... WHERE ..."), with= ANY($1)for an id set, never a loop of single-row statements. Several statements:let mut tx = pool.begin().await?;, each.execute(&mut *tx), thentx.commit().await?. - Nested calls:
f(g(x)?)becomes aletbinding first.
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 Changed · +9 lines 36840cb023ab
- 1mo ago First seen · 61 lines · 55 tokens per session scan A 41f8cd321f9d
rust is an agent published in the GitHub repository navid-kianfar/claude-memory-mcp (0 stars, last pushed 12d ago), licensed MIT. It adds 55 tokens to every session and 1,089 once invoked, about $0.0002 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 2026-09-09.
Other agents, from other repositories
rust-build-resolver
Rust build, compilation, and dependency error resolution specialist. Fixes cargo build errors, borrow checker issues, and Cargo.toml problems with minimal changes. Use when Rust builds fail.
rust-reviewer
Expert Rust code reviewer specializing in ownership, lifetimes, error handling, unsafe usage, and idiomatic patterns. Use for all Rust code changes. MUST BE USED for Rust projects.
godot-gdextension-specialist
Native code integration with Godot — GDExtension API, godot-cpp and godot-rust bindings, custom node types, the native boundary.
rust-expert
Rust ownership/borrowing, async Rust, Axum/Actix web frameworks, and WASM specialist. Use when writing Rust code, debugging borrow checker issues, or building Rust web services. Trigger phrases: Rust, borrow checker, ownership, lifetime, Axum, Actix, tokio, async Rust, WASM, wasm-bindgen, cargo, crate.
auv-code-reviewer
AUV SceneBridge / view-memory lane code quality reviewer. Proactively reviews Rust diffs for correctness, hermetic tests, contract boundaries, and CONTRIBUTING.local.md veto items. Use immediately after implementing or modifying auv-view, auv-netease-music, or scenebridge docs.
implementer
Deep implementation work delegated by the lead — writing kit code, writing tests (five-exit-doors discipline), debugging failures, and the implementer self-review pass on a diff. Use for any coding work bigger than a trivial edit. Runs on Opus.