swag2mcp: Skill for Claude Code

.agents/skills/swag2mcp-format/SKILL.md

swag2mcp-format is a skill for Claude Code, Codex from mmadfox/swag2mcp. It costs 93 tokens per session (5,023 once invoked), scanned A, original, Apache-2.0.

Formatting guidance for displaying results from swag2mcp tools, which expose searchable API specifications and can inspect or call API endpoints. It defines compact, readable formats for lists, searches, endpoint details, authentication, and status information.

In plain words
What is it for?
Use it when presenting outputs from swag2mcp operations such as finding APIs, inspecting specifications, listing endpoints, invoking calls, or checking authentication.
Why use it?
It makes technical API results easier to scan and keeps related responses consistent. It also specifies when raw JSON or a user-defined format should take priority.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: installed under .agents/ (shared by several agents).

This is mmadfox/swag2mcp's own configuration. It tells Claude Code and Codex how to work on swag2mcp 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 swag2mcp configures →

Reuse

Borrowing it

Nothing to install: this file belongs to mmadfox/swag2mcp. 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/mmadfox/swag2mcp/main/.agents/skills/swag2mcp-format/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/mmadfox/swag2mcp

Made for: Claude Code, Codex.

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 swag2mcp-format

README.md
[![agentmods](https://agentmods.dev/badge/skills/mmadfox/swag2mcp/swag2mcp-format/github.svg)](https://agentmods.dev/skills/mmadfox/swag2mcp/swag2mcp-format)
Your own site
<a href="https://agentmods.dev/skills/mmadfox/swag2mcp/swag2mcp-format"><img src="https://agentmods.dev/badge/skills/mmadfox/swag2mcp/swag2mcp-format/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 swag2mcp-format

Your own site · 80×15
<a href="https://agentmods.dev/skills/mmadfox/swag2mcp/swag2mcp-format"><img src="https://agentmods.dev/badge/skills/mmadfox/swag2mcp/swag2mcp-format.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 93 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 5,023 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 $0.00093 $0.05023
Opus 5 $0.00046 $0.02511
Sonnet 5 $0.00019 $0.01005
Haiku 4.5 $0.00009 $0.00502

Measured 9d ago against content hash 100e4894f173, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

swag2mcp-format 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.

.agents/skills/swag2mcp-format/SKILL.md · 566 lines

How it starts

The opening of the file, as written. The whole thing — 566 lines — stays where its author put it; the contents beside it link to each section on GitHub.

swag2mcp-format — Response Formatting Skill

This document defines how to format every swag2mcp MCP tool response into human-readable markdown. Each response type has a dedicated format optimized for clarity and usability.

When to Use

TRIGGERS (use when user says or tool returns):

  • "show me specs" / "list APIs" → spec_list
  • "show spec details" → spec_by_id
  • "list collections" → collection_by_spec / collection_by_id
  • "show tags" → tag_by_*
  • "list endpoints" / "show endpoints" → endpoint_by_*
  • "search for ..." / "find endpoint" → search
  • "inspect endpoint" / "show me the full spec" → inspect
  • "call API" / "invoke" / "make request" → invoke
  • "get auth token" → auth
  • "show system info" / "status" → info
  • ANY response from swag2mcp MCP tools

When NOT to Use

  • User asks to display their OWN data structure (not from swag2mcp tools)
  • User explicitly requests raw/unformatted JSON output
  • User asks for a custom format different from these rules

1. General Rules

1.1 HTTP Methods

Display methods as plain uppercase text in table cells and headers. Do not use emoji or color markers.

Method Display
GET GET
POST POST
PUT PUT
PATCH PATCH
DELETE DELETE
HEAD HEAD
OPTIONS OPTIONS

1.2 Sorting

  • Endpoints within a list: sort by HTTP method (GET < POST < PUT < PATCH < DELETE < HEAD < OPTIONS), then by path alphabetically.
  • Collections, tags, specs: sort by title alphabetically (case-insensitive).
  • Search results: keep the order returned by the search engine (relevance-based).

1.3 ID Display

  • Show IDs in the last column of tables.
  • Truncate to first 6 characters and wrap in backticks: `a1b2c3`.
  • Full ID is available via endpoint_by_id or inspect if needed.

1.4 Pagination

Never display more than 5 items at once. Paginate all list responses (search, endpoint_by_*, tag_by_*, collection_by_*, spec_list). Exceptions: single-item responses (tag_by_id, endpoint_by_id, spec_by_id).

Read the full file on GitHub · 566 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 · 566 lines · 93 tokens per session scan A 100e4894f173

Subscribe to this mod's changes

swag2mcp-format is a skill published in the GitHub repository mmadfox/swag2mcp (0 stars, last pushed 29d ago), licensed Apache-2.0. It adds 93 tokens to every session and 5,023 once invoked, about $0.0005 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.