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 skillgit 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/skill)<a href="https://agentmods.dev/skills/geml-spec/geml/skill"><img src="https://agentmods.dev/badge/skills/geml-spec/geml/skill/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/skill"><img src="https://agentmods.dev/badge/skills/geml-spec/geml/skill.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 | $0.00167 | $0.02518 |
| Opus 5.5 | $0.00067 | $0.01007 |
| Sonnet 5.5 | $0.00033 | $0.00504 |
| Haiku 4.5 | $0.00017 | $0.00252 |
Grade A, and why
geml 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 21d 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.
This is a copy
100% identical to geml — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 172 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Reading and editing documents blockwise
Two jobs. The first is the common one, and it needs none of GEML's syntax.
A document that is NOT GEML — use this as a read layer
geml list, geml find and geml get read Markdown directly. Use them to
locate and read one block of a long document. Nothing is converted, nothing is
written, and the file stays exactly the Markdown it already was.
Only when you would otherwise read the whole file to change part of it. If
the file is short, or you already know the exact string to replace, open it the
ordinary way — the round trip costs more than it saves. What is saved is only
ever the part you did not have to read: on this project's own docs a list map
runs 5–11% of the file it maps, but on a changelog of many small sections it is
37%.
geml list <file>— every block: address, kind, line range.geml find "<text>" <file>— which block holds those words, answered as an ADDRESS rather than a line number, so it survives the next edit. (On a file that is not.gemlthis needs 1.7.5 or newer; older builds report no match rather than an error, so if a search you expect to hit comes back empty, uselist.)geml get <file> '<address>'— that block and nothing else.- Change it. Two ways, and the choice is about consent, not capability:
- Ordinary file-editing tool, using the text from step 3 as the string to replace. The default: a document nobody asked to address by block is edited the way its author edits it.
geml set <file> '#id' …, when block-addressed editing is what was asked for — a knowledge base, a generated index, a log that only grows. Measured on a real vault: the frontmatter and every block you did not address come out byte-for-byte unchanged, and the body you write lands verbatim — no escaping, no reflowing. Readreferences/markdown-writes.mdfirst; two of its rules are silent when broken.
What ships with it
2 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.
- 21d ago Changed · +1 lines b6c3a1812cf9
- 1mo ago Changed · +3 lines 71f75136d97a
- 1mo ago Changed bc63cdab3bfb
- 1mo ago Changed fab08af9905b
- 1mo ago First seen · 168 lines · 167 tokens per session scan A e1087405c9c5
geml is a skill published in the GitHub repository geml-spec/geml (29 stars, last pushed today), licensed MIT. It adds 167 tokens to every session and 2,518 once invoked, about $0.0007 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 100% identical to geml, differing in 0 lines, and is treated as a copy.
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".