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 serejaris/personal-corp-os --skill product-data-auditgit clone --depth 1 https://github.com/serejaris/personal-corp-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/serejaris/personal-corp-os/product-data-audit)<a href="https://agentmods.dev/skills/serejaris/personal-corp-os/product-data-audit"><img src="https://agentmods.dev/badge/skills/serejaris/personal-corp-os/product-data-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/serejaris/personal-corp-os/product-data-audit"><img src="https://agentmods.dev/badge/skills/serejaris/personal-corp-os/product-data-audit.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
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 →
- medium analysis-evasion · line 1 Suspicious Unicode normalization or mixed-script contentFix: Review the flagged content for security risks. Ensure no credentials, secrets, or sensitive data are exposed.
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 | $0.00078 | $0.01580 |
| Opus 5 | $0.00039 | $0.00790 |
| Sonnet 5 | $0.00016 | $0.00316 |
| Haiku 4.5 | $0.00008 | $0.00158 |
Grade A, and why
product-data-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 — 99 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Product & Data Audit
Глубокий аудит продукта/бизнеса: данные, системы, решения, узкие места, контуры внедрения. На выходе — интерактивная HTML-визуализация (12 секций). Markdown-версия — опционально по запросу.
Процесс
digraph audit_flow {
"Определить объект аудита" [shape=box];
"Собрать данные" [shape=box];
"Сгенерировать HTML (12 секций)" [shape=box];
"Открыть в браузере" [shape=box];
"Определить объект аудита" -> "Собрать данные";
"Собрать данные" -> "Сгенерировать HTML (12 секций)";
"Сгенерировать HTML (12 секций)" -> "Открыть в браузере";
}
1. Определить объект аудита
Спросить у пользователя, если неочевидно:
- Аудит одного продукта, линейки или всей экосистемы бренда?
- Какие файлы/системы читать?
workdir = корень git-репозитория текущего проекта. Если неочевидно — спросить у пользователя до шага 2.
2. Собрать данные
Обнаружить и прочитать источники по категориям (конкретные файлы зависят от проекта):
- Архитектура проекта — CLAUDE.md, README, AGENTS.md, .cursor/rules, любые конфиг-файлы агентов
- Канонические данные — файлы с ценами, метриками, офферами, аудиторией (искать по содержимому, не по имени)
- Стратегия и планы — документы с insights, roadmap, OKR, ретро, планы
- Операционные правила — правила в .claude/rules/, playbooks, runbooks
- Рабочие документы — docs/, notes/, analysis/ — всё что есть
- Управление задачами — GitHub Projects/Issues, Linear, Jira (если доступны через CLI)
- Системы и конфиги — боты, CRM, базы, аналитика, мониторинг (конфиги, схемы, .env.example)
- Внешние данные — API-запросы, CLI-команды для свежих метрик (если доступны)
Для каждого источника фиксировать: что внутри, дата snapshot, качество, ограничения.
Обнаружение источников: начать с CLAUDE.md / README.md в корне — они обычно описывают структуру проекта и указывают на канонические файлы. Затем ls + glob по корню для обнаружения остального.
Свежесть данных: если snapshot старше 14 дней — добавить [snapshot: YYYY-MM-DD] рядом с числом. Если старше 30 дней — пометить [УСТАРЕЛО: YYYY-MM-DD].
What ships with it
7 files 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 · 99 lines · 78 tokens per session scan A c61df383002b
product-data-audit is a skill published in the GitHub repository serejaris/personal-corp-os (225 stars, last pushed 15d ago), licensed MIT. It adds 78 tokens to every session and 1,580 once invoked, about $0.0004 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 2026-08-30.
Other skills, from other repositories
manuscript-review
Pre-publication manuscript audit producing a section-level refactoring report with citation hygiene and submission-readiness checks. Triggers on: "review my paper", "check before submission", "is this ready to submit", "pre-pub checklist", "refactor my paper", "check my references", "does the abstract work".
figure-rhetoric
Evaluate whether figures and plots in a manuscript effectively communicate the claims they support. Audits chart-type fit, axis design, visual hierarchy, data density, caption interpretation, perceptual accuracy, and narrative arc across 8 dimensions. Triggers on: "do my figures work", "check my plots", "are my graphs…
humanize
Detects and removes AI-generated writing patterns while preserving meaning and facts. Triggers on: "humanize text", "make this sound human", "remove AI patterns", "rewrite to sound natural", "make this less AI", "de-slop this", "not sound like ChatGPT", "human pass".
manuscript-provenance
Computational provenance audit verifying every number, table, and figure in a manuscript derives from code, not manual entry. Triggers on: "check provenance", "verify reproducibility", "audit my pipeline", "are my numbers from code", "provenance audit". Companion to manuscript-review (prose audit).
code-refiner
Deep code simplification and refactoring preserving behavior across Python, Go, TypeScript, Rust. Targets complexity, anti-patterns, readability debt. Triggers on: "simplify this code", "refactor for clarity", "reduce complexity", "make this more readable", "tech debt cleanup", "too much nesting".
competitive-analyzer
Competitive landscape analysis: Porter's Five Forces, competitor discovery, feature/pricing matrices, positioning maps, moat assessment via WebSearch. Triggers on: "competitive analysis", "competitor comparison", "competitive landscape", "Porter's Five Forces", "market positioning", "moat assessment", "defensibility…