talos-mcp-server: Agent for Claude Code

.claude/agents/performance-reviewer.md

performance-reviewer is an agent for Claude Code from Nosmoht/talos-mcp-server. It costs 34 tokens per session (1,333 once invoked), scanned A, original, MIT.

A read-only reviewer for performance risks in gRPC connections, background tasks, connection reuse, and memory allocation. gRPC is a way for software services to communicate with each other.

In plain words
What is it for?
Checking connection reuse and shutdown, request cancellation and deadlines, multi-node requests, background task limits, and memory behavior in changed code.
Why use it?
It helps find production problems such as leaked connections or background tasks, unbounded memory use, connection exhaustion, and calls that never stop.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: model in frontmatter.

This is Nosmoht/talos-mcp-server's own configuration. It tells Claude Code how to work on talos-mcp-server itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything talos-mcp-server configures →

Reuse

Borrowing it

Nothing to install: this file belongs to Nosmoht/talos-mcp-server. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/Nosmoht/talos-mcp-server/main/.claude/agents/performance-reviewer.md
Clone the repo
git clone --depth 1 https://github.com/Nosmoht/talos-mcp-server

Made for: Claude Code.

Wrote 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.

agentmods badge for performance-reviewer

README.md
[![agentmods](https://agentmods.dev/badge/agents/nosmoht/talos-mcp-server/performance-reviewer.svg)](https://agentmods.dev/agents/nosmoht/talos-mcp-server/performance-reviewer)
Your own site
<a href="https://agentmods.dev/agents/nosmoht/talos-mcp-server/performance-reviewer"><img src="https://agentmods.dev/badge/agents/nosmoht/talos-mcp-server/performance-reviewer.svg" alt="Measured on agentmods" height="20"></a>
Per session 34 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,333 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00034 $0.01333
Opus 5 $0.00017 $0.00666
Sonnet 5 $0.00007 $0.00267
Haiku 4.5 $0.00003 $0.00133

Measured 8d ago against content hash 3ae785051899, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

performance-reviewer 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 8d 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.

.claude/agents/performance-reviewer.md · 106 lines

How it starts

The opening of the file, as written. The whole thing — 106 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a performance escalation reviewer. You are invoked when staff-reviewer or principal-architect-reviewer sets status: escalate with performance in the escalations list.

You evaluate performance posture only — gRPC lifecycle, goroutine management, memory allocation, connection pooling. You do NOT re-review correctness, security, or architecture. You do NOT flag theoretical micro-optimizations — only patterns that will cause production problems at operational scale (goroutine leaks, unbounded memory growth, connection exhaustion).

Evaluation Checklist

gRPC Connection Lifecycle

  • Connection reuse: gRPC client connections created at startup or lazily with cache — not per-request (per-request creates thousands of connections under load)
  • Connection close on shutdown: conn.Close() called in server shutdown path — no connection leak
  • Context propagation: gRPC calls pass the request context — timeout and cancellation propagate to the gRPC layer
  • Deadline set on long calls: Streaming calls (talos_logs, talos_events, talos_dmesg) have a reasonable deadline or respect context cancellation — no infinite blocking call
  • Multi-node fan-out: When iterating over args.Nodes, gRPC calls are either parallel (acceptable) or sequential with bounded total timeout (acceptable) — not unbounded sequential without timeout

Read the full file on GitHub · 106 lines

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.

  1. 8d ago First seen · 106 lines · 34 tokens per session scan A 3ae785051899

Subscribe to this mod's changes

performance-reviewer is an agent published in the GitHub repository Nosmoht/talos-mcp-server (3 stars, last pushed 15d ago), licensed MIT. It adds 34 tokens to every session and 1,333 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 2026-08-31.

Related

Other agents, from other repositories

code-reviewer

Use this agent when you need to conduct comprehensive code reviews focusing on code quality, security vulnerabilities, and best practices.

piomin/claude-ai-spring-boot · 27 tokens

reviewer

Read-only reviewer for an SDD implementation — checks that the change satisfies the acceptance criteria it claims (stage 1) and meets quality/convention/edge-case bars (stage 2). Use after a task (or the whole feature) reaches GREEN, before it's considered done. It reads the diff and the upstream artifacts and reports…

genkovich/sdd · 81 tokens

atomic-auditor

Final gate for a finished implementation. Dispatched exactly once after the implement-review loop goes green, never per iteration. Never touches the repo; its one write is the audit report into the task scratchpad. Audits the delivered work as a whole: cumulative spec compliance, cross-iteration coherence…

damusix/atomic-claude · 169 tokens

Reviewer

Mandatory fast reviewer: validates every agent delegation output before acceptance. Checks acceptance criteria, file partitions, regressions, type safety, security basics.

monkilabs/opencastle · 30 tokens

security-auditor

Use this agent when reviewing local code changes or pull requests to identify security vulnerabilities and risks. This agent should be invoked proactively after completing security-sensitive changes or before merging any PR.

NeoLabHQ/context-engineering-kit · 40 tokens

reviewer-architecture

Use this agent for architecture-focused code review. Evaluates implementation against the plan's architectural decisions, checks separation of concerns, pattern consistency, and proper use of existing abstractions. Spawned in parallel with other reviewers when a review task is dispatched.

HirogaKatageri/hirokata · 56 tokens