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 commands/baodq97/open-plugin/ontology-statsgit clone --depth 1 https://github.com/baodq97/open-pluginWrote 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/commands/baodq97/open-plugin/ontology-stats)<a href="https://agentmods.dev/commands/baodq97/open-plugin/ontology-stats"><img src="https://agentmods.dev/badge/commands/baodq97/open-plugin/ontology-stats.svg" alt="Measured on agentmods" 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 | $0.00009 | $0.00204 |
| Opus 5 | $0.00005 | $0.00102 |
| Sonnet 5 | $0.00002 | $0.00041 |
| Haiku 4.5 | $0.00001 | $0.00020 |
Grade A, and why
ontology-stats 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 5d 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.
What it actually says
Analyze skills usage patterns from the ontology usage log.
Instructions
- Read
.claude/ontology/usage-log.yaml. - If fewer than 3 entries exist, report
Not enough data yetand stop. - Compute and report:
- top 5 most-used skills
- top 3 chains (where
chain_usedis not null) - success rate (
outcome: success/ total) - unused skills (in registry but never used)
- frequent unlinked skill pairs (appear together >= 3 times but no graph edge)
- Suggest edge tuning:
- frequent unlinked pairs -> add
complementary - chain success >= 80% -> increase edge strength by 5
- chain failure >= 50% -> decrease edge strength by 10
- frequent unlinked pairs -> add
- Return concise summary tables, not raw YAML.
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.
- 5d ago First seen · 23 lines · 9 tokens per session scan A a9e93f9ace05
ontology-stats is a command published in the GitHub repository baodq97/open-plugin (4 stars, last pushed 3mo ago), licensed MIT. It adds 9 tokens to every session and 204 once invoked, about $0.0000 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 2026-08-31.
Other commands, from other repositories
security-audit-static
Static security audit of AI-built code — map trust boundaries, cross-reference documented intent, self-refute every finding, and report only evidence-backed risks.
performance-audit-static
Static performance audit of AI-built code — find N+1 queries and request waterfalls, over-fetching, missing indexes, and caching opportunities, ranked by effort and impact.
document-app
Reverse-engineer an AI-built codebase into the system documents reviewers and auditors need — a core set (architecture, flows, permissions, variables) plus conditional docs (emails, cron, SEO, automation) when they apply.
plan-okrs
Brainstorm team-level OKRs aligned with company objectives — qualitative objectives with measurable key results.
write-stories
Break a feature into backlog items — user stories, job stories, or WWA format with acceptance criteria.
battlecard
Create a sales-ready competitive battlecard — positioning, feature comparison, objection handling, and win strategies.