What is cli-over-mcp-auditor?

A review tool for checking which connected tool servers are loaded in an agent session and whether they are relevant to the current task. MCP is a standard way for AI agents to connect to external tools.

Use it to identify irrelevant connected tool servers and decide which ones could be disabled, either during the first prompt or in a deeper configuration audit.

Unused connections add tool descriptions to the agent's working context, which can make it harder to focus and consume available context space.

cli-over-mcp-auditor — Skill for Claude Code by Abhillashjadhav

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent

npx skills add Abhillashjadhav/AI-PM-essential-skills --skill cli-over-mcp-auditor

Clone the repo

git clone --depth 1 https://github.com/Abhillashjadhav/AI-PM-essential-skills

Made for: Claude Code.

Or install pm-tactical, the plugin that ships this one along with the rest of its 5 skills, 3 agents.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/abhillashjadhav/ai-pm-essential-skills/cli-over-mcp-auditor/github.svg)](https://agentmods.dev/skills/abhillashjadhav/ai-pm-essential-skills/cli-over-mcp-auditor)

Your own site

<a href="https://agentmods.dev/skills/abhillashjadhav/ai-pm-essential-skills/cli-over-mcp-auditor"><img src="https://agentmods.dev/badge/skills/abhillashjadhav/ai-pm-essential-skills/cli-over-mcp-auditor/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/abhillashjadhav/ai-pm-essential-skills/cli-over-mcp-auditor"><img src="https://agentmods.dev/badge/skills/abhillashjadhav/ai-pm-essential-skills/cli-over-mcp-auditor.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 108 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 790 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.

Model	Per session	Once invoked
Fable 5.1	$0.00108	$0.00790
Opus 5.5	$0.00043	$0.00316
Sonnet 5.5	$0.00022	$0.00158
Haiku 4.5	$0.00011	$0.00079

Measured 1mo ago against content hash ebfae8507c6a, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

cli-over-mcp-auditor 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 1mo 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.

pm-tactical/skills/cli-over-mcp-auditor/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.

CLI-over-MCP Auditor

Tool context depends on the client, model and loading mode. Audit what is actually injected before recommending a change. A connected server is not proof that all its tool definitions occupy the current context.

Step 0 — First-prompt check

Inspect only information already visible in the session. Distinguish connected servers, available tool names and full definitions actually loaded. Do not load more tools merely to inflate this inventory. If irrelevant loaded definitions are visible, offer one short audit suggestion and continue the requested task. If loading mode or relevance is unclear, stay silent. Never claim a percentage saving without a measurement or an explicitly labelled estimate.

Step 1 — Inventory for an explicit audit

Record client/version, model, loading mode and configured window size when known. Use supplied configuration or a permitted local read; do not disclose secrets. claude mcp list describes connections, not prompt-token usage. Separate each server's loaded definitions from deferred names and server instructions.

Claude Code documentation checked 2026-09-28 describes tool search as enabled by default, with definitions deferred. Some provider/model/configuration combinations load tools up front; alwaysLoad can exempt a server. Check the actual session. Source: Claude Code MCP tool search.

Step 2 — Measure or mark unknown

Count the injected text only with a matching tokenizer or runtime measurement; record tool, scope and method. Visibility alone is not a token measurement. If only an estimate is possible, state its basis and uncertainty. If only tool counts are known, report token cost as unknown rather than multiplying by an unsourced per-tool average. Do not count deferred schemas as already loaded. Use the actual context-window size for percentages; omit them if it is unknown.

Step 3 — Compare workflow costs

Ask how often the tools are used. Compare CLI coverage, authentication, permissions, output size and operational effort. CLI help, invocation text and results also consume context when supplied to the model. A CLI alternative is not automatically cheaper or equivalent. Check its official documentation before giving commands.

Read the full file on GitHub · 72 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.

1mo ago Changed · +9 lines · -93 tokens per session ebfae8507c6a
2mo ago First seen · 63 lines · 201 tokens per session scan A 43fdc6b56a46

Subscribe to this mod's changes

cli-over-mcp-auditor is a skill published in the GitHub repository Abhillashjadhav/AI-PM-essential-skills (9 stars, last pushed 17d ago), licensed MIT. It adds 108 tokens to every session and 790 once invoked, about $0.0004 per session on Opus 5.5. 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.

Building agents Claude Code agent-skills ai-product-management automation evals mcp

cli-over-mcp-auditor next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
cli-over-mcp-auditorAbhillashjadhav/AI-PM-essential-skills	Skill	9	17d ago	MIT	A	108	Claude Code
research-reportShenSeanChen/waku-agent	Skill	2.2k	17d ago	MIT	A	0	Claude Code, Codex
building-agentsericrisco/rsc-harness	Skill	573	yesterday	MIT	A	85	Claude Code, Codex
debloatLilMGenius/paperthin	Skill	1.4k	yesterday	MIT	A	178	Claude Code, Codex
re0-gitLilMGenius/paperthin	Skill	1.4k	yesterday	MIT	A	61	Claude Code, Codex
re0-importLilMGenius/paperthin	Skill	1.4k	yesterday	MIT	A	84	Claude Code, Codex
re0-workflowLilMGenius/paperthin	Skill	1.4k	yesterday	MIT	A	86	Claude Code, Codex