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 binary16labs/prime-silo --skill groupsgit clone --depth 1 https://github.com/binary16labs/prime-siloWrote 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/binary16labs/prime-silo/groups)<a href="https://agentmods.dev/skills/binary16labs/prime-silo/groups"><img src="https://agentmods.dev/badge/skills/binary16labs/prime-silo/groups/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/binary16labs/prime-silo/groups"><img src="https://agentmods.dev/badge/skills/binary16labs/prime-silo/groups.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 | $0.00024 | $0.00860 |
| Opus 5.5 | $0.00010 | $0.00344 |
| Sonnet 5.5 | $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 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.
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.
- 1mo 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 1mo ago), licensed MIT. It adds 24 tokens to every session and 860 once invoked, about $0.0001 per session on Opus 5.5. 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
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: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.
git-commits-and-prs
Load BEFORE creating a git commit or a GitHub pull request. Step-by-step protocol for drafting commit messages, staging safely, amend rules, and gh pr create choreography.
compose:ask
Use whenever you need a decision, clarification, or approval from the user — covers how to ask with the question tool, and how to resolve the decision yourself when no user is available (question tool absent, or a [Never-Ask] response).