file-search-on: Skill for Claude Code

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

add-mcp-tool is a skill for Claude Code from richardwooding/file-search-on. It costs 143 tokens per session (1,763 once invoked), scanned A, original, MIT.

A development guide for adding a new tool to a Go-based MCP server. An MCP tool is an operation that connected agents or applications can call.

In plain words
What is it for?
Use it when extending the file-search-on server with a new operation or an additional search option, including its Go code and in-memory test.
Why use it?
It explains where to define the tool's inputs and outputs, how to connect its handler, how to register it, and how to test it without manually writing a JSON schema.

Skill for Claude Code

Written for Claude Code: installed under .claude/. Also seen: mentions CLAUDE.md.

This is richardwooding/file-search-on's own configuration. It tells Claude Code how to work on file-search-on 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 file-search-on configures →

Reuse

Borrowing it

Nothing to install: this file belongs to richardwooding/file-search-on. 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/richardwooding/file-search-on/main/.claude/skills/add-mcp-tool/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/richardwooding/file-search-on

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/richardwooding/file-search-on/add-mcp-tool/github.svg)](https://agentmods.dev/skills/richardwooding/file-search-on/add-mcp-tool)
Your own site
<a href="https://agentmods.dev/skills/richardwooding/file-search-on/add-mcp-tool"><img src="https://agentmods.dev/badge/skills/richardwooding/file-search-on/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/richardwooding/file-search-on/add-mcp-tool"><img src="https://agentmods.dev/badge/skills/richardwooding/file-search-on/add-mcp-tool.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 143 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,763 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 $0.00143 $0.01763
Opus 5 $0.00072 $0.00881
Sonnet 5 $0.00029 $0.00353
Haiku 4.5 $0.00014 $0.00176

Measured 11d ago against content hash 016998972ebd, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, 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 · 119 lines

How it starts

The opening of the file, as written. The whole thing — 119 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Add MCP Tool

The MCP server in internal/mcpserver/server.go exposes tools to MCP clients (Claude Desktop, IDE plugins) via the official Go SDK at github.com/modelcontextprotocol/[email protected]. Adding a tool is four small things in one file plus a test in another. The schema is generated from struct tags — you don't write JSON schema by hand.

Prefer extending the existing search tool's input over forking a new tool when the new capability is "search but with one more filter / option". MCP clients see fewer entry points and the model picks the right one more reliably.

The four parts of a tool

  1. Input/output structs with json and jsonschema tags. The SDK derives the JSON schema from these.
  2. Handler function matching ToolHandlerFor[In, Out]:
    func(ctx context.Context, req *mcp.CallToolRequest, in In) (*mcp.CallToolResult, Out, error)
    
  3. Registration via mcp.AddTool(s, &mcp.Tool{...}, handler) inside New(version).
  4. Test in server_test.go driving the new tool through mcp.NewInMemoryTransports().

Quick start

Adding a hypothetical read_attributes tool that returns the full attribute set for a single file:

  1. Add the structs in internal/mcpserver/server.go, near the existing SearchInput / SearchOutput:

    type ReadAttributesInput struct {
        Path string `json:"path" jsonschema:"Path to a single file. Required."`
    }
    
    type ReadAttributesOutput struct {
        Path        string         `json:"path"`
        ContentType string         `json:"content_type"`
        Size        int64          `json:"size"`
        Attributes  map[string]any `json:"attributes"`
    }
    
  2. Write the handler, near the existing searchHandler:

    func readAttributesHandler(ctx context.Context, _ *mcp.CallToolRequest, in ReadAttributesInput) (*mcp.CallToolResult, ReadAttributesOutput, error) {
        attrs, err := celexpr.BuildAttributes(in.Path, content.DefaultRegistry())
        if err != nil {
            return nil, ReadAttributesOutput{}, fmt.Errorf("build attributes: %w", err)
        }
        return nil, ReadAttributesOutput{
            Path:        attrs.Path,
            ContentType: attrs.ContentType,
            Size:        attrs.Size,
            Attributes:  attrs.Extra,
        }, nil
    }
    

Read the full file on GitHub · 119 lines

Files

What ships with it

1 file 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 · 119 lines · 143 tokens per session scan A 016998972ebd

Subscribe to this mod's changes

add-mcp-tool is a skill published in the GitHub repository richardwooding/file-search-on (5 stars, last pushed 2d ago), licensed MIT. It adds 143 tokens to every session and 1,763 once invoked, about $0.0007 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

go

Use when writing, reviewing, testing, or shipping Go code and HTTP services: idioms, %w error wrapping, goroutine/context/errgroup concurrency, net/http 1.22 routing, log/slog, project layout, table-driven tests, Go hardening. NOT language-agnostic threat modeling (that is secure-coding), NOT Dockerfile/CI shipping…

ericrisco/rsc-harness · 86 tokens

go-docs

Go 1.26 — language specification, standard library, concurrency, modules, tools, testing, crypto, networking, database access, and idiomatic patterns.

pledgeandgrow/pledge-skills · 36 tokens

golang-samber-do

Dependency injection in Golang using samber/do — service containers, lifecycle management, scopes, health checks, graceful shutdown, and module organization. Apply when using or adopting samber/do, when the codebase imports github.com/samber/do or github.com/samber/do/v2, or when refactoring manual constructor…

alexastrum/skl · 74 tokens

cartograph-use-case

Compile use-case trees into docs/hops.md: Input → Branches → Output. Use when hops.md is missing or stale, the user asks to map a flow, an event is a different use case, or traces break across async calls.

jeunessegamesee/clew · 54 tokens

go

Use when writing Go/Golang code — goroutines/channels concurrency, net/http web servers, database/sql, generics (1.18+), module management, testing and benchmarking. Go: the language powering Docker, Kubernetes, and cloud-native infrastructure.

znlgis/opengis-skills · 53 tokens

golang-grpc

Provides gRPC usage guidelines, protobuf organization, and production-ready patterns for Golang microservices. Use when implementing, reviewing, or debugging gRPC servers/clients, writing proto files, setting up interceptors, handling gRPC errors with status codes, configuring TLS/mTLS, testing with bufconn, or…

alexastrum/skl · 72 tokens