PM Skills is a collection of plain-Markdown instructions that teach AI assistants structured methods for handling professional, personal, and life-admin tasks. People use it with Claude, ChatGPT, Gemini, Cursor, Codex, and other supported agents for work such as writing product requirements, reviewing documents, or planning difficult situations.
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.
git clone --depth 1 https://github.com/mohitagw15856/pm-claude-skillsWrote 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/rules/mohitagw15856/pm-claude-skills/ai-disclosure-policy)<a href="https://agentmods.dev/rules/mohitagw15856/pm-claude-skills/ai-disclosure-policy"><img src="https://agentmods.dev/badge/rules/mohitagw15856/pm-claude-skills/ai-disclosure-policy/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/rules/mohitagw15856/pm-claude-skills/ai-disclosure-policy"><img src="https://agentmods.dev/badge/rules/mohitagw15856/pm-claude-skills/ai-disclosure-policy.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 | $0.00111 | $0.01213 |
| Opus 5 | $0.00056 | $0.00607 |
| Sonnet 5 | $0.00022 | $0.00243 |
| Haiku 4.5 | $0.00011 | $0.00121 |
Grade A, and why
ai-disclosure-policy 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 13d 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 — 108 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AI Disclosure Policy Skill
Every company now ships AI-generated content somewhere — support replies, marketing images, chatbot conversations, synthetic voices — and most have no rule for when to say so. Meanwhile transparency regulation is arriving (the EU AI Act's transparency obligations for chatbots, synthetic media, and deepfakes being the headline example, with obligations phasing in through 2026–2027), and the trust cost of an undisclosed AI surface being discovered is higher than the disclosure ever was. This skill produces the policy: what you label, where, in what words — with the honest line that final regulatory judgment belongs to your lawyer, and this document is what makes that conversation short.
What This Skill Produces
- A surface inventory: every place AI-generated content reaches users or the public, with today's disclosure state
- A disclosure matrix: per surface — required (regulatory), expected (platform/industry norm), or chosen (trust) — with the reasoning
- Label copy ready to ship: UI strings, footer lines, image/video marks, chatbot self-identification wording
- The review triggers: what changes (new surface, new market, new regulation phase) forces a policy re-read, and who owns it
Required Inputs
Ask for (if not already provided):
- Where AI output ships today or soon: chatbots, support, marketing content, images/video/voice, code, docs — and which are fully automated vs human-reviewed
- Markets served (EU exposure changes obligations) and industry (regulated sectors add rules)
- Existing policy fragments ([[ai-usage-policy]] covers internal use — this skill covers outward disclosure; link them, don't duplicate)
- Risk posture: minimum-compliance or trust-differentiator
Process
- Inventory before policy. List every AI-touching surface, then the ones the user forgot: auto-generated email, AI-assisted support macros, synthetic voices on calls, generated product imagery, auto-summaries in the product. For each: fully-AI, AI-drafted-human-approved, or AI-assisted — the disclosure answer differs by degree of human control.
- Sort into required / expected / chosen. Required: where a regulation plausibly applies — chatbots that could be mistaken for humans, synthetic media, emotionally targeted content (flag these for counsel; cite the regulation family, not invented article numbers). Expected: platform rules and industry norms (ad platforms, app stores increasingly require labels). Chosen: where labeling is optional but discovery-risk or brand values argue for it. State the reasoning per row — a policy without reasons decays.
- Write labels people won't hate. Honest, short, non-groveling: "AI-assisted, human-reviewed" beats a paragraph of throat-clearing. Chatbots self-identify at conversation start, not in a footer. Human-approved content can say so — the disclosure spectrum has two ends.
- Decide the edge cases explicitly: AI-drafted-human-edited text (the big one — set a threshold and say it), internal content that leaks, user-facing personalization, A/B tests of the labels themselves (don't).
- Wire the triggers. New surface, new market, automation-degree change, regulation phase-in dates → named owner re-reviews. Policy without a re-review trigger is a screenshot, not a policy.
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.
- 13d ago First seen · 108 lines · 111 tokens per session scan A 3999d8ad892f
ai-disclosure-policy is a cursor rule published in the GitHub repository mohitagw15856/pm-claude-skills (1,357 stars, last pushed yesterday), licensed MIT. It adds 111 tokens to every session and 1,213 once invoked, about $0.0006 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 cursor rules, from other repositories
risk-factors
Risk scoring factor definitions and weights for PR review dispatch.
sensitive-paths
Sensitive file path patterns that increase risk score during PR review.
ponytail
Ponytail, lazy senior dev mode. Always pick the simplest solution that works.
angular-20
This rule provides comprehensive best practices and coding standards for Angular development, focusing on modern TypeScript, standalone components, signals, and performance optimizations.
dev-standard
Apache Superset development standards and guidelines for Cursor IDE.
cli-error-handling
CLI command error handling patterns.