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 skills/binary16labs/prime-silo/usersnpx skills add binary16labs/prime-silo --skill usersgit clone --depth 1 https://github.com/binary16labs/prime-siloWhat 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 | $0.00028 | $0.00959 |
| Opus 5 | $0.00014 | $0.00479 |
| Sonnet 5 | $0.00006 | $0.00192 |
| Haiku 4.5 | $0.00003 | $0.00096 |
Grade A, and why
Admin Users 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 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.
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 Admin Users — 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 — 130 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Use this skill for concrete user-account work.
First Check
- Call
const info = await space.api.userSelfInfo(). - Confirm
info.groups.includes("_admin") === true. - Prefer logical app paths derived from the standard layer rules, not guessed disk paths.
Canonical User Tree
L2/<username>/is the user's logical root.L2/<username>/user.yamlstores user metadata such asfull_name.L2/<username>/meta/password.jsonstores the backend-sealed SCRAM verifier.L2/<username>/meta/logins.jsonstores signed session verifiers.L2/<username>/mod/is that user's customware module root.
There is no separate user registry file. The watched user index is derived from files under L2/<username>/.
Path Rules
- Use logical paths such as
L2/alice/user.yaml. - When writable storage is relocated under
CUSTOMWARE_PATH, these logical paths stay the same. fileWrite(".../")creates a directory because the path ends with/.- Do not hand-craft
meta/password.jsonor individual session entries. Usepassword_generatefor password records and only write{}when revoking sessions.
Create A User
Use a normalized username segment such as alice, ops_bot, or qa-team-1.
const username = "alice";
const fullName = "Alice Example";
const password = "replace-me";
const verifier = await space.api.call("password_generate", {
method: "POST",
body: { password }
});
return await space.api.fileWrite({
files: [
{ path: `L2/${username}/` },
{ path: `L2/${username}/mod/` },
{
path: `L2/${username}/user.yaml`,
content: space.utils.yaml.stringify({ full_name: fullName })
},
{
path: `L2/${username}/meta/password.json`,
content: `${JSON.stringify(verifier, null, 2)}\n`
},
{
path: `L2/${username}/meta/logins.json`,
content: "{}\n"
}
]
});
Update User Metadata
Read user.yaml, parse it, mutate the fields you need, and write it back.
const path = "L2/alice/user.yaml";
const current = await space.api.fileRead(path);
const config = space.utils.yaml.parse(current.content || "");
config.full_name = "Alice Example";
return await space.api.fileWrite(path, space.utils.yaml.stringify(config));
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 · 130 lines · 28 tokens per session scan A 966df9494a2a
Admin Users is a skill published in the GitHub repository binary16labs/prime-silo (5 stars, last pushed 9d ago), licensed MIT. It adds 28 tokens to every session and 959 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to Admin Users, differing in 0 lines, and is treated as a copy.
Other skills, from other repositories
draw-image
Generate an image from a text prompt using an OpenAI-compatible image generation API (gpt-image-1-mini or compatible). The image is uploaded to the gofile.io public file sharing service and ONLY the public download page URL is returned. Trigger when user asks to draw, paint, generate, or create an image.
compose:subagent
Use when executing implementation plans with independent tasks in the current session.
compose:worktree
Use when starting feature work that needs isolation from current workspace or before executing implementation plans - ensures an isolated workspace exists via native tools or git worktree fallback.
compose:merge
Use when implementation is complete, all tests pass, and you need to decide how to integrate the work - guides completion of development work by presenting structured options for merge, PR, or cleanup.
compose:new-skill
Use when creating new skills or editing existing skills for the project or personal skill library.
compose:plan
Use when you have a spec or requirements for a multi-step task, before touching code.