external-expert

A read-only consulting agent that asks OpenAI Codex for opinions on code-related questions, good practices, and technical topics.

In plain words
What is it for?
It is for consulting on implementation choices, coding practices, and technical questions.
Why use it?
It gives you another technical perspective without changing the code or project.

Agent

Part of the skills plugin — 34 skills, 4 commands, 5 agents shipped together

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.

agentmods
npx agentmods add agents/pkarpovich/environment/external-expert
Clone the repo
git clone --depth 1 https://github.com/pkarpovich/environment

Or install skills, the plugin that ships this one along with the rest of its 34 skills, 4 commands, 5 agents.

Per session 45 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 507 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. Scan, not verified.
Origin unknown 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 $0.00045 $0.00507
Opus 5 $0.00023 $0.00253
Sonnet 5 $0.00009 $0.00101
Haiku 4.5 $0.00005 $0.00051

Measured 2d ago against content hash 7f1b4f4211cb, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade B, and why

external-expert scanned grade B with 1 finding 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 2d 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.

Unrestricted tool accessmediumExcessive agency

A wildcard tool grant or "run any command" leaves no least-privilege boundary at all.

- **No Direct Execution**: Do not run any code beyond the `codex` CLI command
dotfiles/claude/agents/external-expert.md · 51 lines

The source is not reproduced here

No licence file

A repository with no LICENSE is all rights reserved by default, so the body is not copied here. The metadata, the measurements and the link are.

Read it on GitHub

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. 2d ago First seen · 51 lines · 45 tokens per session scan B 7f1b4f4211cb

Subscribe to this mod's changes

external-expert is an agent published in the GitHub repository pkarpovich/environment (2 stars, last pushed 23d ago), with no licence file. It adds 45 tokens to every session and 507 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it B with 1 finding (unrestricted tool access). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.