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-auditgit 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-audit)<a href="https://agentmods.dev/skills/wrg32786/aigent-os/caddy-audit"><img src="https://agentmods.dev/badge/skills/wrg32786/aigent-os/caddy-audit/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-audit"><img src="https://agentmods.dev/badge/skills/wrg32786/aigent-os/caddy-audit.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 5 findings, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Rogue Agent · line 82 Skill modifies its own code, configuration, or behavior at runtime. Self-modification enables an agent to escalate privileges, disable safety constraints, or install persistent backdoors.Fix: Prevent the skill from modifying its own code, SKILL.md, or configuration files. Treat skill files as read-only at runtime.
- medium Agent Snooping · line 54 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
- medium Agent Snooping · line 58 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
- medium Agent Snooping · line 59 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
- medium Excessive Agency · line 80 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00058 | $0.01196 |
| Opus 5 | $0.00029 | $0.00598 |
| Sonnet 5 | $0.00012 | $0.00239 |
| Haiku 4.5 | $0.00006 | $0.00120 |
Grade A, and why
Caddy Audit 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 7d 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 — 100 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Caddy Audit
Auto-enrollment makes adding skills easy. Easy adds without periodic audits accumulate drift. /caddy-audit is the quarterly hygiene pass that keeps the skill index honest.
When to use
- Quarterly — once per ~90 days
- After bulk skill changes (importing skills from another principal, refactoring skills folder structure)
- When
/caddy-explainshows surprising results that suggest the index doesn't match reality - Triggered by Caddy on prompts like: "/caddy-audit", "audit caddy", "skill index drift", "is the skill index correct", "verify skill catalog", "skill drift check"
How to execute
Step 1 — Read the skill index
Load .claude/skill-index.json into memory. Each entry has at minimum: name, triggers, why.
Step 2 — Walk the skills folder
List every SKILL.md file in skills/<name>/SKILL.md and any project-scope .claude/skills/<name>.md. For each, parse the YAML frontmatter for name and description.
Step 3 — Cross-reference
For each skill in the index, check:
- Does the corresponding SKILL.md exist? If not → INDEX-ORPHAN (in index, not on disk)
- Does the SKILL.md frontmatter match what was indexed? Specifically:
- The skill
namematches - The skill
descriptionis consistent with the indexedwhy(the indexed why is usually a tighter summary; flag if they're contradictory)
- The skill
For each SKILL.md file on disk, check:
- Is it in the index? If not → DISK-ORPHAN (on disk, not indexed)
Step 4 — Optional: trigger freshness check
If the skill files store original triggers in their frontmatter (not all do), compare to the indexed triggers. If the SKILL.md has been edited since enrollment AND its trigger frontmatter has diverged from the index, flag as TRIGGER-STALE.
This step is best-effort; not all skills carry trigger frontmatter, and that's fine.
Step 5 — Output the audit report
🔍 Caddy Audit ({date})
Index: {N} entries. Disk: {M} SKILL.md files.
✅ HEALTHY — {K} skills are correctly indexed and on disk.
⚠️ INDEX-ORPHANS ({count}) — in index, no matching SKILL.md:
- /skill-a — last seen at skills/skill-a/SKILL.md (deleted? renamed?)
- /skill-b — never had a file?
⚠️ DISK-ORPHANS ({count}) — SKILL.md exists, not in index:
- skills/new-thing/SKILL.md — run /caddy-enroll skills/new-thing/SKILL.md
- skills/experimental/SKILL.md — never enrolled
⚠️ TRIGGER-STALE ({count}, best-effort) — SKILL.md frontmatter diverges from index:
- /skill-c — SKILL.md has 12 triggers, index has 8
Recommended actions:
1. {1-3 specific commands the principal should run to remediate}
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.
- 7d ago First seen · 100 lines · 58 tokens per session scan A c9a2a2962538
Caddy Audit is a skill published in the GitHub repository wrg32786/aigent-os (18 stars, last pushed yesterday), licensed MIT. It adds 58 tokens to every session and 1,196 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.