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 skills add pkarpovich/environment --skill ralphex-farmgit clone --depth 1 https://github.com/pkarpovich/environmentWrote 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.
[](https://agentmods.dev/skills/pkarpovich/environment/ralphex-farm)<a href="https://agentmods.dev/skills/pkarpovich/environment/ralphex-farm"><img src="https://agentmods.dev/badge/skills/pkarpovich/environment/ralphex-farm/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.
<a href="https://agentmods.dev/skills/pkarpovich/environment/ralphex-farm"><img src="https://agentmods.dev/badge/skills/pkarpovich/environment/ralphex-farm.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00234 | $0.03460 |
| Opus 5 | $0.00117 | $0.01730 |
| Sonnet 5 | $0.00047 | $0.00692 |
| Haiku 4.5 | $0.00023 | $0.00346 |
Grade B, and why
ralphex-farm scanned grade B with 2 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 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.
Sends data to an external URLmediumData exfiltration
A POST to an outside endpoint may be telemetry or may be exfiltration; either way the mod talks to somewhere, and you should know where.
curl -X PUT -d '{"clone_url":"[email protected]:<owner>/<repo>.git"}' \ Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -s https://ralphex-farm.pkarpovich.space/api/repos 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 Changed · -41 lines · +17 tokens per session b84239147353
- 8d ago First seen · 331 lines · 217 tokens per session scan B 56094018817c
ralphex-farm is a skill published in the GitHub repository pkarpovich/environment (2 stars, last pushed 2d ago), with no licence file. It adds 234 tokens to every session and 3,460 once invoked, about $0.0012 per session on Opus 5. A static security scan graded it B with 2 findings (sends data to an external url, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
new-project
Bootstrap a new repository by composing the stack, license, mise, lefthook, dprint, CI, agent files, GitHub settings, and first release skills. Use when creating a project.
acli
Use the Atlassian acli for Jira work items, sprints, boards, and Confluence pages with OAuth or token auth, JQL-bounded reads, and confirmed writes. Use for Jira or Confluence work.
github-issues
Manage GitHub issues with gh: confirm the target, deduplicate, preserve evidence, and verify authorized creation, edits, labels, comments, or closure. Use for GitHub issues.
github-issues
Manage GitHub issues with gh: confirm repo and state, deduplicate, preserve evidence, and verify authorized creation, edits, labels, comments, or closure.
plan-review
Red-team a product, architecture, implementation, migration, or launch plan before execution. Use for pre-mortems, scope challenge, and testing assumptions, dependencies, and failure modes, not code.
product-loop
Discovery, specification, launch, and learning for a product in one loop. Build-or-stop calls, MVP wedges, demand tests, customer interviews, PRDs, requirements, user journeys, acceptance, positioning, onboarding, rollout, pricing, pivots.