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/venue-access-check)<a href="https://agentmods.dev/rules/mohitagw15856/pm-claude-skills/venue-access-check"><img src="https://agentmods.dev/badge/rules/mohitagw15856/pm-claude-skills/venue-access-check/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/venue-access-check"><img src="https://agentmods.dev/badge/rules/mohitagw15856/pm-claude-skills/venue-access-check.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 | $0.00117 | $0.01338 |
| Opus 5 | $0.00059 | $0.00669 |
| Sonnet 5 | $0.00023 | $0.00268 |
| Haiku 4.5 | $0.00012 | $0.00134 |
Grade A, and why
venue-access-check 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 8d 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 — 106 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Venue Access Check Skill
"Is it accessible?" is the wrong question — venues answer yes to it reflexively, and the disabled visitor discovers the truth at the door: the "accessible" entrance that's a phone-call-and-wait around the back, the "step-free" route with one step, the toilet that's an accessible sign on a cupboard. This skill replaces the yes/no with the specific questions that surface reality, tailored to your needs, and teaches you to read the answers — because how a venue answers ("let me check and send a photo" vs "yeah should be fine") tells you as much as what they say. It's for personal go/no-go decisions, not a formal WCAG-style audit (that's [[accessibility-audit]]).
What This Skill Produces
- A tailored question list: the specific things to confirm for this venue and your needs — entrance and route, thresholds and widths, the accessible toilet's reality, seating, lighting/noise, hearing loops, level changes, parking/drop-off
- How to read the answers: the reassuring-but-empty replies vs the credible ones, and the follow-ups that catch the "should be fine"
- The photo/evidence ask: how to get pictures or a measurement rather than a promise (the single most reliable move)
- A go / adapt / avoid verdict with the reasoning, plus what to arrange in advance if it's a "go with adaptations"
Required Inputs
Ask for (if not already provided):
- The venue and what for (a meal, a meeting, an overnight, an appointment, an event)
- The specific access needs (wheelchair/mobility aid and transfer ability, sensory needs, fatigue, service animal, dietary-medical) — the questions flex to these
- How much is at stake / how reversible (a casual coffee vs a booked event you can't redo)
- Any info the venue has already given
Framework
- Translate the need into specific, checkable questions. "Accessible?" becomes "Is there a step at the main entrance, and if so is there a genuinely step-free alternative that's staffed at all times?", "What's the clear width of the toilet door?", "Is the accessible toilet used for storage?" (a real and common problem). Specific questions can't be waved away with a reflexive yes.
- Ask for evidence, not assurance. The reliability upgrade: request a photo of the entrance/route/bathroom, or a measurement. A venue that sends one is credible; a venue that can't or won't is a flag. This one move prevents most bad surprises.
- Read the answer's shape. "Let me physically check and get back to you" and specific numbers signal a venue that understands access. "Yeah it should be fine" and "we've never had complaints" signal a venue that doesn't — and "should be fine" has failed more disabled visitors than any other phrase. Teach the follow-up that tests it.
- Verdict with adaptations. Go (confirmed workable), adapt (workable with pre-arrangement — reserve the accessible table, arrange the staffed entrance, bring the ramp), or avoid (the barrier is real and unfixable). For "adapt," list exactly what to arrange and confirm before arriving.
- Have the day-of fallback. Even confirmed access fails sometimes; note the quick check on arrival and the backup (a nearby alternative, the "this isn't as described" line) so a bad answer at the door isn't the end of the plan.
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.
- 8d ago First seen · 106 lines · 117 tokens per session scan A 00d0299e1c6c
venue-access-check is a cursor rule published in the GitHub repository mohitagw15856/pm-claude-skills (1,352 stars, last pushed 4d ago), licensed MIT. It adds 117 tokens to every session and 1,338 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 2026-09-03.
Other cursor rules, from other repositories
cursor
Always-on my-adhd-caveman. Off with "stop adhd-caveman" or "normal mode".
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.
prefer-direct-imports-over-module-mocks
Prefer extracting a testable core over vi.mock / vi.resetModules when unit tests need to reach production logic entangled with config, env, or singletons.