talos-mcp-server: Skill for Claude Code

.claude/skills/add-mcp-tool/SKILL.md

add-mcp-tool is a skill for Claude Code from Nosmoht/talos-mcp-server. It costs 49 tokens per session (786 once invoked), scanned A, original, MIT.

A scaffold for creating a new Talos MCP tool, where MCP is a standard way for an agent to call external tools.

In plain words
What is it for?
Use it when adding a read-only or change-making Talos tool under internal/tools. It validates the tool name and stops if a file with that name already exists.
Why use it?
It handles the project’s required handler shape, registration, safety defaults, inventory update, and test stub so these pieces are not assembled manually.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: mentions CLAUDE.md; positional $N argument; mentions AGENTS.md.

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/skills/add-mcp-tool/SKILL.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 add-mcp-tool

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/nosmoht/talos-mcp-server/add-mcp-tool"><img src="https://agentmods.dev/badge/skills/nosmoht/talos-mcp-server/add-mcp-tool.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 49 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 786 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 $0.00786
Opus 5 $0.00024 $0.00393
Sonnet 5 $0.00010 $0.00157
Haiku 4.5 $0.00005 $0.00079

Measured 11d ago against content hash 1a197c389761, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

add-mcp-tool 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 11d 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/skills/add-mcp-tool/SKILL.md · 72 lines

How it starts

The opening of the file, as written. The whole thing — 72 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Add MCP Tool

Scaffold a new tool handler that conforms to the project's handler signature (func (h *Handlers) HandleXxx(ctx, req, args XxxArgs)) and safety conventions.

Arguments

Parse $ARGUMENTS:

  • $1 — snake_case tool name (required). Must start with talos_ (e.g. talos_drain_node).
  • $2 — category, one of mutating | read (default read).

Derive {{ToolName}} = PascalCase of $1 with the talos_ prefix stripped (e.g. talos_drain_nodeDrainNode).

If any required argument is missing, ask the user once for the missing value, then proceed non-interactively.

Key Steps

  1. Validate name. Reject if $1 does not match ^talos_[a-z][a-z0-9_]*$.

  2. Collision check. Use Glob to confirm internal/tools/<name>.go does not exist. If it does, stop and report — do not overwrite.

  3. Generate handler. Render references/handler-template.go.tmpl with {{ToolName}}, {{tool_name}}, {{category}} substituted. Write to internal/tools/<name>.go.

  4. Apply safety defaults. For mutating, inline confirm bool and nodes []string on {{ToolName}}Args; set dry_run / preserve / graceful defaults from references/safety-defaults.md.

  5. Register the tool. Grep for mcp.AddTool in internal/tools/ to locate the registration site. Add the new entry in alphabetical order:

    mcp.AddTool(server, &mcp.Tool{Name: "{{tool_name}}"}, h.Handle{{ToolName}})
    
  6. Generate test stub. Write internal/tools/<name>_test.go with one happy-path test and (for mutating) a guards-enforcement test.

  7. Format. Run gofmt -w internal/tools/<name>.go internal/tools/<name>_test.go.

  8. Update inventory. Edit the tool-inventory tables in AGENTS.md and README.md. Preserve alphabetical order.

Output

On success, print:

Created:   internal/tools/<name>.go
           internal/tools/<name>_test.go
Modified:  <registration-file>
           AGENTS.md  (tool inventory)
           README.md  (tool inventory)
Next:      make check
           invoke staff-reviewer  →  .claude/reviews/<change-id>/review.md
           commit  →  feat(tools): add <tool_name> handler [review:<change-id>]

Read the full file on GitHub · 72 lines

Files

What ships with it

2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 11d ago First seen · 72 lines · 49 tokens per session scan A 1a197c389761

Subscribe to this mod's changes

add-mcp-tool is a skill published in the GitHub repository Nosmoht/talos-mcp-server (3 stars, last pushed 17d ago), licensed MIT. It adds 49 tokens to every session and 786 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 skills, from other repositories

router-contract-change

Use when changing a request-visible router contract across configuration, signals, decisions, algorithms, or recipe-scoped plugins in vLLM Semantic Router.

vllm-project/semantic-router · 33 tokens

oracle-mcp-server-helper

Wire the oracle-database-mcp-server into a Python project so an LLM agent can call listtables / describetable / runsql / vectorsearch at inference time. Handles install, stdio launch, and LangChain tool conversion via langchain-mcp-adapters. Use whenever a project needs a Grok 4 / GPT-class agent that talks to a live…

oracle-devrel/oracle-ai-developer-hub · 0 tokens

spring-boot

Spring Boot 3.x development - REST APIs, JPA, Security, Testing, and Cloud-native patterns. Use for building enterprise Java applications with Spring Boot.

piomin/claude-ai-spring-boot · 36 tokens

indexing

How to read historical onchain data at scale — events, logs, The Graph subgraphs, Ponder, and indexing patterns. Use when building a backend that needs past blockchain state (not live queries — use ethereum-networks for that). Covers why you cannot loop through blocks and what to use instead.

ObolNetwork/obol-stack · 64 tokens

aima-image-gen

Generate images using AIMA's local z-image model (OpenAI-compatible API).

Approaching-AI/AIMA · 21 tokens

health-check-endpoints

Implements liveness and readiness health check endpoints following Kubernetes probe conventions. Covers response schema, dependency checks, Kubernetes probe config, and circuit breaker integration. Invoked when the user asks to add health checks, implement a /health endpoint, or set up Kubernetes probes.

soulcodex/agentic · 58 tokens