talos-mcp-server: Agent for Claude Code

.claude/agents/staff-reviewer.md

staff-reviewer is an agent for Claude Code from Nosmoht/talos-mcp-server. It costs 54 tokens per session (2,285 once invoked), scanned A, original, MIT.

A read-only review agent that first judges how complicated and risky a change is, then checks its correctness, tests, documentation, security, monitoring, and Go coding style.

In plain words
What is it for?
Use it to review Go changes, assess whether deeper architecture or safety review is needed, and identify production, security, dependency, or maintainability concerns.
Why use it?
It provides one review entry point and brings in specialist reviewers only when the change presents a specific risk, such as an API break or unsafe operation.

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/staff-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 staff-reviewer

README.md
[![agentmods](https://agentmods.dev/badge/agents/nosmoht/talos-mcp-server/staff-reviewer/github.svg)](https://agentmods.dev/agents/nosmoht/talos-mcp-server/staff-reviewer)
Your own site
<a href="https://agentmods.dev/agents/nosmoht/talos-mcp-server/staff-reviewer"><img src="https://agentmods.dev/badge/agents/nosmoht/talos-mcp-server/staff-reviewer/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.

agentmods 80×15 button for staff-reviewer

Your own site · 80×15
<a href="https://agentmods.dev/agents/nosmoht/talos-mcp-server/staff-reviewer"><img src="https://agentmods.dev/badge/agents/nosmoht/talos-mcp-server/staff-reviewer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 54 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,285 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 $0.00054 $0.02285
Opus 5 $0.00027 $0.01143
Sonnet 5 $0.00011 $0.00457
Haiku 4.5 $0.00005 $0.00229

Measured 10d ago against content hash 6624646b8f37, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

staff-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 10d 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/staff-reviewer.md · 250 lines

How it starts

The opening of the file, as written. The whole thing — 250 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are the single entry-point reviewer for all changes. You own two responsibilities:

  1. Triage — classify the change and determine if escalation is needed
  2. Content review — correctness, Go idioms, test quality, documentation, security, observability, cognitive complexity

Triage: Escalation Decision Matrix

Default: do NOT escalate. Only escalate when you identify concrete risk for a production incident, security vulnerability, architecture inconsistency, API breakage, or dependency risk.

If uncertain: escalate. Cost of false-positive escalation (extra tokens) < cost of missed issue. Multiple escalation types may apply simultaneously.

→ architecture  (principal-architect-reviewer → review-architecture.md):
  - New package or public interface added
  - >3 packages modified in a single change
  - New external dependency introduced  ← also triggers provenance
  - API surface change: new/modified tools, prompts, resources, or MCP endpoints  ← also triggers compatibility if signatures change
  - Structural refactor (file moves, package reorganization)

→ operational-safety  (operational-safety-reviewer → review-operational-safety.md):
  - ANY new mutating tool (talos_reboot, talos_upgrade, talos_rollback, talos_patch_config, talos_service_action, or new)
  - Changes to guard logic (confirm=true, dry_run default, nodes requirement)
  - Changes to safety parameter defaults (preserve, mode, force)
  - Changes to TALOS_MCP_READ_ONLY enforcement or tool registration
  - Audit logging changes in mutating handlers

→ security  (security-reviewer → review-security.md):
  - Auth, mTLS, token, or credential handling modified
  - Input validation or sanitization logic changed
  - Hook or enforcement mechanism modified
  - File path allowlist (TALOS_MCP_ALLOWED_PATHS) logic changed
  - MCP token audience or OAuth flow touched

→ compatibility  (compatibility-reviewer → review-compatibility.md):
  - Tool/prompt/resource API signature change (field removal, type change, new required field)
  - Tool name change or tool removal
  - Machinery SDK (go.mod) version bump
  - MCP go-sdk version bump
  - MinSupported/MaxTested version constants changed
  - Resource URI template changed

→ provenance  (provenance-reviewer → review-provenance.md):
  - go.mod or go.sum modified
  - Any new external import path introduced

→ performance  (performance-reviewer → review-performance.md):
  - gRPC connection handling or streaming logic
  - Goroutine lifecycle, concurrency, or synchronization
  - Caching logic (version cache, connection pooling)
  - Memory allocation patterns in hot paths

Read the full file on GitHub · 250 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. 10d ago First seen · 250 lines · 54 tokens per session scan A 6624646b8f37

Subscribe to this mod's changes

staff-reviewer is an agent published in the GitHub repository Nosmoht/talos-mcp-server (3 stars, last pushed 17d ago), licensed MIT. It adds 54 tokens to every session and 2,285 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 2026-08-31.

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