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 impactbrussels/AINativeOS --skill share-of-model-auditgit clone --depth 1 https://github.com/impactbrussels/AINativeOSWrote 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/impactbrussels/ainativeos/share-of-model-audit)<a href="https://agentmods.dev/skills/impactbrussels/ainativeos/share-of-model-audit"><img src="https://agentmods.dev/badge/skills/impactbrussels/ainativeos/share-of-model-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/impactbrussels/ainativeos/share-of-model-audit"><img src="https://agentmods.dev/badge/skills/impactbrussels/ainativeos/share-of-model-audit.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 | $0.00149 | $0.01422 |
| Opus 5 | $0.00075 | $0.00711 |
| Sonnet 5 | $0.00030 | $0.00284 |
| Haiku 4.5 | $0.00015 | $0.00142 |
Grade A, and why
share-of-model-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 11d 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 — 98 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Share-of-Model Audit
Buyers now ask an AI engine before they ask you, and the engine names three companies as proof. If it does not name you, the considered-buying journey starts with your competitor's case study, not yours, and you never see the loss. Share of Model is the percentage of those answers that cite you versus rivals. It is the new top of funnel, and a single reading lies. This skill turns it into a tracked number with a baseline, so you can tell whether your narrative is landing or a competitor is being cited in the rooms you cannot see.
The method
Fixed query set, several engines, a scoring sheet, a tracked trend. Full framework: references/audit-protocol.md, drawn from handbook Chapter 10 and Chapter 12.
Step 1: Design the buyer query set
Write 20 to 50 queries a real buyer types, not the ones that flatter you. Lock the set so months are comparable. Mix the three intents.
| Intent | Example shape | What it tests |
|---|---|---|
| Category | "best tool for [job]" | Do you appear in the top-of-funnel shortlist? |
| Comparison | "[competitor] alternatives", "[X] vs [Y]" | Do you survive the head-to-head? |
| Problem-led | "how do I [solve PROBLEM]" | Do you own the job, not just the category? |
Step 2: Run a fixed engine panel
Run every query through at least three engines; one engine is not a reading. Use a clean session each time so prior chat does not seed the answer.
| Engine | Why include |
|---|---|
| ChatGPT | Largest buyer reach |
| Claude | Different citation behaviour |
| Perplexity | Source-first, names citations explicitly |
Step 3: Score each answer
For every query and engine, record one row. Count citation, not vibes.
| Field | Values |
|---|---|
| Cited me? | yes / no |
| Named first? | yes / no |
| Competitors cited | list of names |
| Outcome | me / rival / neither |
Step 4: Compute the share and the gaps
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 11d ago First seen · 98 lines · 149 tokens per session scan A 61baa6ca8859
share-of-model-audit is a skill published in the GitHub repository impactbrussels/AINativeOS (1 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 149 tokens to every session and 1,422 once invoked, about $0.0007 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 skills, from other repositories
remember
Review reusable project knowledge and decide what belongs in project memory, notepad, or durable docs.
docx-comment-reply
Reply to comments (批注) in Word .docx/.doc files: extract comment context, draft replies, write threaded replies back, and validate OOXML.
explaining-machine-learning-models
Explain trained machine learning models through feature attribution, local explanations, and behavior summaries. Use as an explicit/manual helper once a model already exists, not for training ownership, leakage auditing, or general ML strategy selection.
moai-ref-ui-polish
UI polish and interface-completion reference: the small visual details — concentric border radius, optical alignment, shadow-vs-border, motion easing, typography smoothing, tabular numbers, icon stroke weight, hit areas — that separate polished interfaces from generic ones. Agent-extending skill that amplifies…
config-validator
Validate AIWG configuration files and project setup for correctness and completeness.
aiwg-regenerate-copilot
Regenerate copilot-instructions.md for GitHub Copilot with vendor-specific content only.