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/groupsnpx skills add binary16labs/prime-silo --skill groupsgit 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 | $0.00024 | $0.00860 |
| Opus 5 | $0.00012 | $0.00430 |
| Sonnet 5 | $0.00005 | $0.00172 |
| Haiku 4.5 | $0.00002 | $0.00086 |
Grade A, and why
Admin Groups 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 Groups — 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 — 117 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Use this skill for group creation, membership changes, manager changes, or explaining how _all and _admin work.
Canonical Group Tree
- Runtime-managed groups live under
L1/<group>/. L1/<group>/group.yamlis the canonical membership and manager file.L1/<group>/mod/is that group's customware module root.
Do not write group membership into arbitrary files. group.yaml is the contract.
Special Groups
_allis the implicit everyone group.- Do not create or rely on
L1/_all/group.yamlfor membership._allmembership is universal, not file-driven. _adminis the admin group.- Adding a user or included group to
_adminmakes those users admins.
Canonical group.yaml Fields
included_usersincluded_groupsmanaging_usersmanaging_groups
Meaning:
included_users: direct members of the groupincluded_groups: groups whose members also become members of this groupmanaging_users: users who may write this group'sL1/<group>/treemanaging_groups: groups whose members may write this group'sL1/<group>/tree
Manager inheritance is separate from membership inheritance. Do not treat included_* as manager fields or vice versa.
Create A Group
Runtime-created groups belong in L1, not L0.
const groupId = "team-red";
return await space.api.fileWrite({
files: [
{ path: `L1/${groupId}/` },
{ path: `L1/${groupId}/mod/` },
{
path: `L1/${groupId}/group.yaml`,
content: space.utils.yaml.stringify({
included_groups: [],
included_users: [],
managing_groups: [],
managing_users: []
})
}
]
});
Update Membership Or Managers
Read, parse, normalize, then write group.yaml.
const path = "L1/team-red/group.yaml";
const current = await space.api.fileRead(path);
const config = space.utils.yaml.parse(current.content || "");
config.included_users = [...new Set([...(config.included_users || []), "alice"])].sort();
config.managing_users = [...new Set([...(config.managing_users || []), "alice"])].sort();
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 · 117 lines · 24 tokens per session scan A 7dfed573d4d3
Admin Groups is a skill published in the GitHub repository binary16labs/prime-silo (5 stars, last pushed 9d ago), licensed MIT. It adds 24 tokens to every session and 860 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 Groups, 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: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:plan
Use when you have a spec or requirements for a multi-step task, before touching code.
compose:report
Use after implementation is verified and before merge — consolidates multiple spec iterations into a single final-state report, marks related specs, and records key lessons.
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.