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 geml-spec/geml --skill benchgit clone --depth 1 https://github.com/geml-spec/gemlWrote 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/geml-spec/geml/bench)<a href="https://agentmods.dev/skills/geml-spec/geml/bench"><img src="https://agentmods.dev/badge/skills/geml-spec/geml/bench/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/geml-spec/geml/bench"><img src="https://agentmods.dev/badge/skills/geml-spec/geml/bench.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 | $0.00000 | $0.01083 |
| Opus 5.5 | $0.00000 | $0.00433 |
| Sonnet 5.5 | $0.00000 | $0.00217 |
| Haiku 4.5 | $0.00000 | $0.00108 |
Grade A, and why
bench 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.
How it starts
The opening of the file, as written. The whole thing — 114 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Writing GEML — one-page cheatsheet
GEML is plain text. Every structured thing is one typed block:
=== <type> {#id .class key=val}
<body>
===
The opening fence is ≥ 3 =. The closing fence must be the same length.
To nest a block inside a block, make the outer fence longer:
==== note
Example code:
=== code {lang=python}
print("hi")
===
====
Easier — close by name. Give a block an #id and close it with === #id.
That closes by name, not by length, so you can nest with all === fences and
never miscount:
=== note {#ex}
Example code:
=== code {#snippet lang=python}
print("hi")
=== #snippet
=== #ex
Body modes: code / diagram / math / table / embed are raw;
note are parsed prose; meta is one key=val per line.
Metadata
=== meta
title = "My doc"
version = 0.1
===
In prose, {{title}} inserts a meta value (an unknown key is a build error).
Headings & lists (ATX only)
# Title ## Section {#explicit-id}
- bullet 1. ordered
- nested by indentation (2 spaces)
- [ ] task - [x] done
Inline
*em* **strong** `code` ~~strike~~ $a^2$ (inline math)
[text](https://x) [text](#id) [[#id]] (auto text) [^note] 
A reference to a missing id is a build error. Define a footnote with
a note block (e.g. === note {#note}), then cite it inline with [^note].
Tables
=== table {#fy caption="Sales" format=csv header=1}
Seg, Q1, Q2, Q3, Q4
Cloud, 1, 2, 3, 4
===
=== view {#fy-report src=#fy compute="FY [%.1f] = Q1 + Q2 + Q3 + Q4" summary="Seg = 'Total'; Q1 = sum(Q1); FY = sum(FY)"}
===
- A
tableholds FACTS.compute/summary— andwhere/order/limit/select/by/aggregate— belong to aviewwhosesrc=names the table. - The attribute object
{…}is one physical line (don't wrap it). compute:Name = exprover+ - * / ( ), columns by header name (quote names with spaces:'Unit Price') or letterA,B,…;;-separate multiple formulas;[%.1f]sets number display.summary: one foot row; each cell is a literal ('Total') or an aggregate expression oversum/avg/min/max/count. A bare (non-aggregated) column is an error.- Visual form also works:
| a | b |rows with a|---|separator.
What ships with it
4 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · +2 lines 6ff9621988db
- 1mo ago Changed · +5 lines dd4883f6835d
- 1mo ago First seen · 107 lines · 0 tokens per session scan A 3eb4acb10ed3
bench is a skill published in the GitHub repository geml-spec/geml (29 stars, last pushed today), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,083 tokens. 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 skills, from other repositories
handoff
Hand work to another tool, account or machine and pick it up there, in two words. Use when the user says "hand off", "hand off all", "out of tokens", "switching accounts", "pick up" or "continue".
sw-handoff
Hand work to another tool, account or machine and pick it up there, in two words. Use when the user says "hand off", "hand off all", "out of tokens", "switching accounts", "pick up" or "continue".
increment
Plan work as a SpecWeave increment - one spec.md with Problem, Scope, numbered ACs, Approach and Tasks - before writing code. Use for "plan a feature", "new increment", "let's build X".
sw-do
Work a SpecWeave increment task by task - claim, implement inside its Files, test, commit, done with evidence - alone, unattended or in lanes, then close. Use for "implement", "continue", "auto".
sw-increment
Plan work as a SpecWeave increment - one spec.md with Problem, Scope, numbered ACs, Approach and Tasks - before writing code. Use for "plan a feature", "new increment", "let's build X".
review
Adversarial review of an increment before it ships, by a fresh context or another model family; every finding cites path:line and is re-verified. Use for "review", "qa", "critique this".