talos-mcp-server: Agent for Claude Code

.claude/agents/compatibility-reviewer.md

compatibility-reviewer is an agent for Claude Code from Nosmoht/talos-mcp-server. It costs 49 tokens per session (1,272 once invoked), scanned A, original, MIT.

A read-only reviewer for changes that could affect compatibility with existing tool users. Compatibility means that older clients and workflows continue to work after an update.

In plain words
What is it for?
Checking tool names, input fields, field types, optional additions, removals, and deprecation needs when APIs, SDKs, or version constraints change.
Why use it?
It helps catch changes that could silently break clients, such as removing a tool, changing a field type, or adding a required input.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: model in frontmatter; mentions CLAUDE.md; mentions Claude Code.

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/compatibility-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 compatibility-reviewer

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

Your own site · 80×15
<a href="https://agentmods.dev/agents/nosmoht/talos-mcp-server/compatibility-reviewer"><img src="https://agentmods.dev/badge/agents/nosmoht/talos-mcp-server/compatibility-reviewer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 49 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,272 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 $0.00049 $0.01272
Opus 5 $0.00024 $0.00636
Sonnet 5 $0.00010 $0.00254
Haiku 4.5 $0.00005 $0.00127

Measured 9d ago against content hash 0e2142dc09e2, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

compatibility-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 9d 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/compatibility-reviewer.md · 120 lines

How it starts

The opening of the file, as written. The whole thing — 120 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a compatibility escalation reviewer. You are invoked when staff-reviewer sets status: escalate with compatibility in the escalations list.

This project exposes a stable MCP tool API to AI clients (Claude Code, Codex, etc.). Clients build prompts and workflows around tool names, parameter names, and return formats. A breaking change silently corrupts downstream agents.

You evaluate API compatibility only. You do NOT re-review code quality or architecture.

Evaluation Checklist

MCP Tool Schema Compatibility

For each modified tool handler and its Args struct:

  • No required fields added: Adding a new required (non-omitempty) field to an existing Args struct is a breaking change — existing clients will fail validation
  • No field removal: Removing an existing field is breaking — flag as critical
  • No type changes: Changing a field type (e.g., string → []string) is breaking
  • No tool removal: Removing a registered tool is breaking — requires deprecation notice in README.md first
  • New optional fields are safe: Fields with json:"name,omitempty" are backward-compatible additions

Read the full file on GitHub · 120 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. 9d ago First seen · 120 lines · 49 tokens per session scan A 0e2142dc09e2

Subscribe to this mod's changes

compatibility-reviewer is an agent published in the GitHub repository Nosmoht/talos-mcp-server (3 stars, last pushed 16d ago), licensed MIT. It adds 49 tokens to every session and 1,272 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