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.
npx agentmods add agents/pkarpovich/environment/external-expertgit clone --depth 1 https://github.com/pkarpovich/environmentWhat 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 | $0.00045 | $0.00507 |
| Opus 5 | $0.00023 | $0.00253 |
| Sonnet 5 | $0.00009 | $0.00101 |
| Haiku 4.5 | $0.00005 | $0.00051 |
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 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.
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.
- 2d ago First seen · 51 lines · 45 tokens per session scan B 7f1b4f4211cb
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.
Other agents, from other repositories
impl-worker
../../.claude/agents/impl-worker.md.
researcher
../../.claude/agents/researcher.md.
reviewer
../../.claude/agents/reviewer.md.
code-refiner
Code refinement specialist for improving elegance, readability, and maintainability. Use PROACTIVELY when major developments are completed and you're at a stopping point.
skeptic
Adversarial reviewer for investigative conclusions. Spawned after research/analysis to challenge assumptions, identify gaps, and stress-test reasoning before conclusions reach the user.
documentation-refiner
Documentation maintenance expert for Markdown files, package configs, and developer docs. Use when major changes have been made. Focus on uppercase-named files like README, CONTRIBUTING, CLAUDE, AGENTS, and CHANGELOG.