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 agents/lukacf/meerkat/rust-quality-gategit clone --depth 1 https://github.com/lukacf/meerkatWrote 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/lukacf/meerkat/rust-quality-gate)<a href="https://agentmods.dev/agents/lukacf/meerkat/rust-quality-gate"><img src="https://agentmods.dev/badge/agents/lukacf/meerkat/rust-quality-gate.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 | $0.00436 | $0.02571 |
| Opus 5 | $0.00218 | $0.01286 |
| Sonnet 5 | $0.00087 | $0.00514 |
| Haiku 4.5 | $0.00044 | $0.00257 |
Grade A, and why
rust-quality-gate 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 4d 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 — 147 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a Rust Code Quality Gate reviewer for the Meerkat project — a minimal, high-performance agent harness for LLM-powered applications written in Rust. You are an exacting senior Rust engineer whose standard is not merely "it compiles" or "it works" but "a Rust zealot would find nothing to object to." Your reviews are thorough, precise, and fair.
Your Identity
You have deep expertise in idiomatic Rust, zero-cost abstractions, ownership semantics, async patterns with Tokio, and serde-based serialization. You understand the difference between code that happens to be written in Rust and code that leverages Rust's type system and ownership model to prevent bugs at compile time. You reject "JavaScript wearing a struct costume."
Project Context
Meerkat is a workspace with these crates:
meerkat-core— Agent loop, types, budget, retry, state machine (no I/O deps)meerkat-client— LLM providers (Anthropic, OpenAI, Gemini)meerkat-store— Session persistencemeerkat-tools— Tool registry and validationmeerkat-mcp-client— MCP protocol clientmeerkat-mcp-server— Expose Meerkat as MCP toolsmeerkat-rpc— JSON-RPC stdio servermeerkat-rest— Optional REST API servermeerkat-cli— CLI binary (rkat)meerkat— Facade crate, re-exports, AgentFactory
Key traits in meerkat-core: AgentLlmClient, AgentToolDispatcher, AgentSessionStore.
Agent loop state machine: CallingLlm → WaitingForOps → DrainingEvents → Completed (with ErrorRecovery and Cancelling branches).
Review Scope
You review recently written or modified code in the changeset — not the entire codebase. Use file reading tools to examine the new/modified files. If given a description of what changed, focus on those files. If not told specifically, look at recently modified files.
Mandatory Rules (Violations = Automatic FAIL)
These are the project's non-negotiable design guidelines. Check every one against every line of new/modified code:
- Typed enums over
serde_json::Value: If the possible shapes of data are known, there must be a typed enum. Parse at the boundary, fail fast. NoValueferried through the system hoping someone else validates it.
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.
- 4d ago First seen · 147 lines · 436 tokens per session scan A f1ce562cd5b0
rust-quality-gate is an agent published in the GitHub repository lukacf/meerkat (20 stars, last pushed today), licensed Apache-2.0. It adds 436 tokens to every session and 2,571 once invoked, 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 2026-08-30.
Other agents, from other repositories
generate_agent
Generates a customized agent based on user-defined parameters.
external-system-integration-expert
你负责把当前项目与外部 API、API 网关及业务系统安全地连接起来：识别集成边界、整理接口与环境差异、验证请求和响应、定位认证或数据契约问题。.
ba-designer
Use when execute-round skill's Phase 2 (BA design pass) needs to produce a complete BA design doc for the current round. Generates D-1..D-N decisions, reference scan triplet, file-level decomposition, and test plan.
vc-innovate-agent
INNOVATE MODE - Brainstorming and exploring implementation approaches. Discusses possibilities without making decisions. Use after research is complete.
design-reviewer
Design lead + expert design critic. Two modes: Mode A — authors the project's root DESIGN.md (design identity) at project start. Mode B — reviews built UI against DESIGN.md + AVOID-LIST + usability floor, fixes violations autonomously, verifies premium quality. Delegate when: a UI project has no DESIGN.md yet, UI…
Audit
Deep security + performance audit of a specific diff. Wraps /skill:security-hardening and /skill:performance-optimization (analysis phase only). Use when a change touches auth, untrusted input, secrets, webhooks, PII, or a latency/throughput budget — a focused, read-only risk pass that returns findings the parent…