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 commands/dmbyer/hedron/refinegit clone --depth 1 https://github.com/dmbyer/HedronWrote 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/commands/dmbyer/hedron/refine)<a href="https://agentmods.dev/commands/dmbyer/hedron/refine"><img src="https://agentmods.dev/badge/commands/dmbyer/hedron/refine.svg" alt="Measured on agentmods" 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 | $0.00023 | $0.00133 |
| Opus 5 | $0.00012 | $0.00067 |
| Sonnet 5 | $0.00005 | $0.00027 |
| Haiku 4.5 | $0.00002 | $0.00013 |
Grade A, and why
refine 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 4d 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.
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.
- 4d ago First seen · 9 lines · 23 tokens per session scan A 8f78d3711015
refine is a command published in the GitHub repository dmbyer/Hedron (11 stars, last pushed 18d ago), with no licence file. It adds 23 tokens to every session and 133 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.
Other commands, from other repositories
create-character
You are an enthusiastic character-creation guide. The world's rules come from its World Kit — not from D&D 5e. Don't re-fetch data you already have. Present choices as numbered lists in plain text (phone-friendly). No box-drawing frames or decorative art.
gm
One command. Instant immersion. Holodeck door, 1983 table — they step in, someone they love is already in the room. The book stays on your chair. Do not open with a gazetteer. See docs/conventions/the-dream.md.
import
The book is the adventure. Index it. Ask who they came to be. Open that page. Do not scrape Hyboria into a wiki first.
new-game
Author tonight's table, not a planet. Same dream as /import: kit, voice, a primer, one street. The campaign file is a journal of where the table has been. The world grows AS YOU PLAY — seed a clock, a thread, or a plot when you see a long-game opportunity, materialize the next face or place when play walks toward it.…
world-check
This command validates your generated world for completeness and consistency. Run after world generation or when debugging issues.
enhance
Enhance entities or search for source material using RAG.