codex-in-claude: Skill for Claude Code

.agents/skills/agent-friendly-mcp/SKILL.md

agent-friendly-mcp is a skill for Claude Code from briandconnelly/codex-in-claude. It costs 130 tokens per session (3,320 once invoked), scanned A, original, MIT.

A set of practices for designing MCP servers, which let AI agents discover and call external tools, so those tools are clear and economical to use.

In plain words
What is it for?
Designing, building, auditing, or reviewing MCP servers and their tool descriptions, schemas, discovery, error recovery, and token use.
Why use it?
It helps prevent agents from choosing the wrong tool, wasting tokens on tool definitions, or sending invalid requests because the tool schema is unclear.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: mentions Claude Code; installed under .agents/ (shared by several agents); mentions Codex.

This is briandconnelly/codex-in-claude's own configuration. It tells Claude Code how to work on codex-in-claude 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 codex-in-claude configures →

Part of the codex-in-claude plugin — 8 skills, 1 MCP server shipped together

Reuse

Borrowing it

Nothing to install: this file belongs to briandconnelly/codex-in-claude. 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/briandconnelly/codex-in-claude/main/.agents/skills/agent-friendly-mcp/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/briandconnelly/codex-in-claude

Made for: Claude Code.

Or install codex-in-claude, the plugin that ships this one along with the rest of its 8 skills, 1 MCP server.

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 agent-friendly-mcp

README.md
[![agentmods](https://agentmods.dev/badge/skills/briandconnelly/codex-in-claude/agent-friendly-mcp/github.svg)](https://agentmods.dev/skills/briandconnelly/codex-in-claude/agent-friendly-mcp)
Your own site
<a href="https://agentmods.dev/skills/briandconnelly/codex-in-claude/agent-friendly-mcp"><img src="https://agentmods.dev/badge/skills/briandconnelly/codex-in-claude/agent-friendly-mcp/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 agent-friendly-mcp

Your own site · 80×15
<a href="https://agentmods.dev/skills/briandconnelly/codex-in-claude/agent-friendly-mcp"><img src="https://agentmods.dev/badge/skills/briandconnelly/codex-in-claude/agent-friendly-mcp.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 130 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,320 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 $0.00130 $0.03320
Opus 5 $0.00065 $0.01660
Sonnet 5 $0.00026 $0.00664
Haiku 4.5 $0.00013 $0.00332

Measured 11d ago against content hash 865589ba8db8, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

agent-friendly-mcp 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.

The scan reads SKILL.md. This mod also ships 7 executable files (tests/check_fact_sync.py, tests/check_rule_ids.py, tests/check_stale_terms.py, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

.agents/skills/agent-friendly-mcp/SKILL.md · 127 lines

How it starts

The opening of the file, as written. The whole thing — 127 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent-Friendly MCP

Use this skill to make MCP servers easy for agents to discover, invoke correctly, recover from, and use at low token cost without sacrificing correctness.

Spec Baseline

This skill is written against the MCP 2026-07-28 specification (final, released 2026-07-28); the field names, capability paths, method set, and task lifecycle it uses follow that revision, including the io.modelcontextprotocol/tasks extension (SEP-2663). Status caveat: the 2026-07-28 changelog calls tasks an official extension while the ext-tasks specification repository still labels itself experimental — treat the task contract as extension-versioned and re-verify it against the extension spec when it cuts a release. The protocol core is stateless: there is no initialize handshake or session id — every request carries io.modelcontextprotocol/protocolVersion and io.modelcontextprotocol/clientCapabilities in _meta (both required), and servers advertise their own capabilities via the mandatory server/discover method. Server-initiated requests are gone: elicitation, sampling, and roots requests ride Multi Round-Trip Requests (resultType: "input_required" with inputRequests, answered by retrying with inputResponses), and subscription notifications — list-changed, resource-updated, and task notifications — ride an opt-in subscriptions/listen stream, while request-scoped notifications (notifications/progress, notifications/message) stay on the originating request's response stream. Every result carries a required resultType, and server/discover, list, and read results carry the native cache hints ttlMs and cacheScope on their resultType: "complete" results — MRTR interim results are never cacheable. Roots, sampling, logging, the HTTP+SSE transport, and Dynamic Client Registration are deprecated on a twelve-month minimum window; design new servers without them. The extensions framework is formal but demanding: an extension needs a reverse-DNS identifier, its own maintained specification, and negotiation by both peers (declared in clientCapabilities.extensions and server/discover), so a namespaced _meta key remains a private convention until someone does that work. This section is the single home for revision-level facts: which revision is baseline, its release status, the tasks-extension caveat, and what is deprecated or removed. Checklist rules and native-wire-shapes.md necessarily restate the mechanics they govern, including a governed surface's deprecation status; for the revision-level frame they cite this section rather than restating it. For clients that still speak 2025-11-25, the binding rules here still govern what you build; the old revision's wire differences and version-bound failure modes are cataloged in the informative mcp-2025-11-25-compat.md, and decisions/001-mcp-2026-07-28-rebase.md records the rebase decision, verified fact sheet, and impact matrix.

Read the full file on GitHub · 127 lines

Files

What ships with it

45 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 · 127 lines · 130 tokens per session scan A 865589ba8db8

Subscribe to this mod's changes

agent-friendly-mcp is a skill published in the GitHub repository briandconnelly/codex-in-claude (3 stars, last pushed yesterday), licensed MIT. It adds 130 tokens to every session and 3,320 once invoked, about $0.0006 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

writing-release-notes

Use when preparing, refreshing, backfilling, or redrafting a release-notes page under docs/releases/ before opening a normal review pull request.

pvliesdonk/markdown-vault-mcp · 35 tokens

pr-alignment-loop

Iterate a PR to its final form by running two opposing reviewer droids (reviewer-robustness and reviewer-minimalist) in a bounded back-and-forth loop. The main orchestrator synthesizes their feedback, makes edits, runs tests, and stops when both approve, on stagnation, or after 3 rounds. Use when the user asks to…

nikships/skills-registry · 122 tokens

skills

Generate a complete SVG file from a natural language description using SEP-1577 multi-step sampling.

sandraschi/inkscape-mcp · 0 tokens

researching-references

Use when a change depends on how something outside this repository actually behaves — a markdown dialect, a file format, git, a protocol, a vendor API — and docs/design/reference/ has no current reference for it, or the one it has is past its review date. Researches from primary sources and writes a dated, versioned…

pvliesdonk/markdown-vault-mcp · 99 tokens

repository-protection

Use when changing branch or tag rulesets, required checks, or the bootstrap workflow: how repository protection is applied and kept in sync.

pvliesdonk/markdown-vault-mcp · 31 tokens

vault-workflow

Use when the user asks you to search, read, or reason about notes in their markdown vault — guides when to use which vault tool and how to chain them for good results.

pvliesdonk/markdown-vault-mcp · 40 tokens