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 wrg32786/aigent-os --skill caddy-enrollgit clone --depth 1 https://github.com/wrg32786/aigent-osWrote 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/wrg32786/aigent-os/caddy-enroll)<a href="https://agentmods.dev/skills/wrg32786/aigent-os/caddy-enroll"><img src="https://agentmods.dev/badge/skills/wrg32786/aigent-os/caddy-enroll/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/wrg32786/aigent-os/caddy-enroll"><img src="https://agentmods.dev/badge/skills/wrg32786/aigent-os/caddy-enroll.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00057 | $0.00845 |
| Opus 5 | $0.00028 | $0.00423 |
| Sonnet 5 | $0.00011 | $0.00169 |
| Haiku 4.5 | $0.00006 | $0.00085 |
Grade A, and why
caddy-enroll 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 9d 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 — 101 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/caddy-enroll
Enroll a skill into Caddy's skill-index.json so prompts matching the skill's triggers surface it as a hint.
When to Use
- A new skill was created (often by
/skills-builder) and needs to join the index - A skill was copied in from outside (cloned plugin, downloaded skill)
- An existing skill's triggers need refreshing after its SKILL.md changed
- User says "enroll this skill" / "add this to Caddy" / "update Caddy for /X"
When NOT to Use
- The skill is already indexed with correct triggers (check
.claude/skill-index.jsonfirst) - The skill has no SKILL.md / no description / no clear use case (fix the skill first, enroll after)
Arguments
$1 = path to the skill's SKILL.md or .md file. If omitted, ask which skill.
Protocol
Step 1: Read the target skill
Read the full SKILL.md at the given path. Parse:
- name — from the
name:frontmatter field, or the filename stem - description — from the
description:frontmatter field, or first heading/line
Step 2: Extract structured metadata
Produce this five-field structure:
- what: <one-line what it does>
- triggers: <comma-separated keywords/intents a prompt matcher could catch — 6-12 items, mix multi-word phrases and single keywords>
- use_cases: <3-5 concrete "when user says X, use this">
- anti_cases: <1-3 "do NOT use when...">
- related: <comma-separated related skills from the existing index>
Trigger quality rules:
- Multi-word phrases score 3x — prefer them for specific intents
- Single words only for unambiguous terms
- Avoid stopwords and generic terms ("help", "check", "run", "fix" alone)
- Aim for prompts a user would actually type — not jargon from the skill's own docs
Anti-case quality:
- Name the sibling skill that SHOULD be used instead
- Name any confidentiality or scope boundaries
Step 3: Append to skill-index.json
Read .claude/skill-index.json (relative to AIGENT_ROOT).
If a skill with this name already exists: update its triggers and why — don't clobber triggers the user added manually.
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.
- 9d ago First seen · 101 lines · 57 tokens per session scan A cd04709122db
caddy-enroll is a skill published in the GitHub repository wrg32786/aigent-os (18 stars, last pushed 2d ago), licensed MIT. It adds 57 tokens to every session and 845 once invoked, about $0.0003 per session on Opus 5. 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 2026-09-01.
Other skills, from other repositories
hive.note-taking
Maintain a free-form scratchpad of decisions, extracted values, and open questions so context pruning doesn't lose anything you still need.
article
Write a publication-ready article in one of three angles - a trending long-form piece, a watched-repo thesis, or a project-through-a-lens essay. Optional Replicate hero image with --visual.
fork-fleet
Fork divergence monitor - tracks where the fleet's active forks diverge in CODE (unique commits, new/modified skills) and CONFIG (enable/var/model/schedule vs upstream), gated on real change.
fleet-control
Operate managed Aeon instances from memory/instances.json - health-check, dispatch, and status snapshots (control), plus a fleet scorecard of runs, tokens, cost, and reliability (scorecard).
github-trending
Curated trending across GitHub repos and the Hugging Face Hub (models, datasets, spaces) - filtered, clustered, and labeled by momentum with a one-line why-notable per pick.
token-pick
One token recommendation and one prediction market pick - scored, quantified, with a skip branch when signals are weak.