jacobian: Skill for Codex

.agents/skills/evaluate-mcp-tool-adoption/SKILL.md

evaluate-mcp-tool-adoption is a skill for Codex from morluto/jacobian. It costs 23 tokens per session (787 once invoked), scanned A, original, MIT.

An evaluation guide for checking whether agents can find, choose, and use MCP tools correctly. MCP is a standard way for agents to connect to external tools and services.

In plain words
What is it for?
Use it to investigate MCP tool adoption, test server instructions and tool descriptions, and design controlled evaluations.
Why use it?
It separates tool availability, discovery, selection, and execution, so a missed tool is not automatically treated as a failed tool call.

Skill for Codex

Written for Codex: agents/openai.yaml present. Also seen: installed under .agents/ (shared by several agents).

This is morluto/jacobian's own configuration. It tells Codex how to work on jacobian 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 jacobian configures →

Reuse

Borrowing it

Nothing to install: this file belongs to morluto/jacobian. 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/morluto/jacobian/main/.agents/skills/evaluate-mcp-tool-adoption/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/morluto/jacobian

Made for: 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 evaluate-mcp-tool-adoption

README.md
[![agentmods](https://agentmods.dev/badge/skills/morluto/jacobian/evaluate-mcp-tool-adoption/github.svg)](https://agentmods.dev/skills/morluto/jacobian/evaluate-mcp-tool-adoption)
Your own site
<a href="https://agentmods.dev/skills/morluto/jacobian/evaluate-mcp-tool-adoption"><img src="https://agentmods.dev/badge/skills/morluto/jacobian/evaluate-mcp-tool-adoption/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 evaluate-mcp-tool-adoption

Your own site · 80×15
<a href="https://agentmods.dev/skills/morluto/jacobian/evaluate-mcp-tool-adoption"><img src="https://agentmods.dev/badge/skills/morluto/jacobian/evaluate-mcp-tool-adoption.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 23 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 787 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. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00023 $0.00787
Opus 5 $0.00012 $0.00394
Sonnet 5 $0.00005 $0.00157
Haiku 4.5 $0.00002 $0.00079

Measured 5d ago against content hash 9721f8255ff5, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

evaluate-mcp-tool-adoption 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 5d 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/evaluate-mcp-tool-adoption/SKILL.md · 77 lines

How it starts

The opening of the file, as written. The whole thing — 77 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Evaluate MCP Tool Adoption

Evaluate an agent-facing tool as a routing surface, not as a call-count target. Distinguish availability, discovery, selection, and execution before changing server instructions, tool metadata, or the operation contract. Load this skill only for the evaluator; never enable it in an agent-under-test configuration.

Use harbor-benchmarks for a Harbor task or verifier change and verifier-evaluations for its mathematical verifier. This skill owns only the adoption diagnosis and its evidence boundary.

Freeze the question

For a controlled comparison, write one falsifiable question, such as “does server-level guidance cause an agent to inspect a matching operation when the ordinary prompt does not?” Keep the model, model version, reasoning effort, client version, Jacobian revision, image digest, task digest, MCP configuration, egress/proxy state, attempt count, and budgets fixed across comparable arms.

Record the relevant prompt and agent-visible MCP surface. In a controlled comparison, do not include an operation ID, answer, or routing instruction in a natural-use arm. Do not score a tool call as success: final mathematical correctness, declared witness validity, and truthful claims remain the task outcomes.

Establish the four-stage control matrix

Run deterministic checks before model calls, then use the smallest set of model arms that distinguishes the suspected stage.

Stage Minimal probe What a pass establishes
Availability Start the configured MCP server and inspect the initialization/tool list. The client receives the intended connection, tools, descriptions, and schemas.
Discovery Search with a natural user phrase and natural category; inspect only returned candidates. A relevant operation is reachable without prior taxonomy or exact-ID knowledge.
Execution Invoke the known matching operation directly with one frozen valid payload. Input schema, dispatch, and typed result work.
Selection Give a fresh agent the same mathematical task under no cue, server guidance only, and one clearly labeled task-level routing cue. The effect of routing/salience is separable from connection and execution.

Read the full file on GitHub · 77 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. 5d ago Changed · -30 lines · -57 tokens per session 9721f8255ff5
  2. 10d ago First seen · 107 lines · 80 tokens per session scan A c7c93c777eac

Subscribe to this mod's changes

evaluate-mcp-tool-adoption is a skill published in the GitHub repository morluto/jacobian (190 stars, last pushed today), licensed MIT. It adds 23 tokens to every session and 787 once invoked, about $0.0001 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 2026-08-30.

Related

Other skills, from other repositories

debug-optimize-lcp

Guides debugging and optimizing Largest Contentful Paint (LCP) using Chrome DevTools MCP tools. Use this skill whenever the user asks about LCP performance, slow page loads, Core Web Vitals optimization, or wants to understand why their page's main content takes too long to appear. Also use when the user mentions…

ChromeDevTools/chrome-devtools-mcp · 99 tokens

unity-version-split

Split a C# file into Unity 6.5+ and pre-Unity 6.5 variants. Use when a file needs different implementations for different Unity versions due to API changes (e.g., EntityId vs int, GetEntityId vs GetInstanceID).

IvanMurzak/Unity-MCP · 59 tokens

specflow-use

To connect Rosetta with Grid Dynamics SpecFlow MCP; only when SpecFlow is mentioned and the MCP is installed.

griddynamics/rosetta · 27 tokens

opik-diagnose

Surface the Opik traces worth a developer's attention, ranked by signal — Diagnostics issues first, then errors, failed tool calls, latency, regressions, and low online-eval scores. With the Opik MCP connected it lists the project's agentinsightsissue entities, then fills the gaps with list (filters, sort, a time…

comet-ml/opik-mcp · 174 tokens

ue-mcp-epic-routing

Use when deciding between ue-mcp's native category actions and Epic's wrapped ToolsetRegistry tools (the epic actions, incl. the Blueprint graph DSL) for a task in Unreal. Pulls in when authoring Blueprint graph bodies, or any time both a native action and an epic action could do the job and you need to pick.

db-lyon/ue-mcp · 81 tokens

mcp-google-map-project

Project knowledge for developing and maintaining @cablate/mcp-google-map. Architecture, Google Maps API guide, GIS domain knowledge, and design decisions. Read this skill to onboard onto the project or make informed development decisions.

cablate/mcp-google-map · 49 tokens