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/mechanic-quote-decoder)<a href="https://agentmods.dev/rules/mohitagw15856/pm-claude-skills/mechanic-quote-decoder"><img src="https://agentmods.dev/badge/rules/mohitagw15856/pm-claude-skills/mechanic-quote-decoder/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/mechanic-quote-decoder"><img src="https://agentmods.dev/badge/rules/mohitagw15856/pm-claude-skills/mechanic-quote-decoder.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 | $0.00129 | $0.01542 |
| Opus 5 | $0.00064 | $0.00771 |
| Sonnet 5 | $0.00026 | $0.00308 |
| Haiku 4.5 | $0.00013 | $0.00154 |
Grade A, and why
mechanic-quote-decoder 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 — 134 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Mechanic Quote Decoder Skill
Most garages are honest; the padding problem is structural anyway: you can't see the car, you can't judge the diagnosis, and the quote arrives by phone with a "while it's up on the lift" rider. The defense isn't mechanical knowledge — it's interrogation structure: which lines trace to the symptom you brought the car in with, which are discoveries (legitimate but separately decidable), which are maintenance upsells wearing urgency, and the magic question that dissolves soft lines: "which of these are safety-critical today, and which can wait until the next service?" Honest garages answer that cleanly. The answer's shape tells you which kind you're dealing with.
What This Skill Produces
- A line-by-line decode of the quote: symptom-linked / legitimate discovery / maintenance-due / soft upsell — with the reasoning per line and the 🔴🟡🟢 urgency read as claimed vs as evidenced
- The callback questions, scripted: the safety-critical-today question, the "can I see/keep the old part?" line, the failed-vs- worn distinction ("is it broken, or wearing?"), labor-hours clarity
- A sort: authorize now / decline politely / defer to next service / second-opinion — with the decline scripts that keep the relationship
- The second-opinion math: when the quote size justifies the cost and hassle of another garage's eyes, and how to ask for one without war
- Price-sanity flags: parts findable at retail (the OEM-vs- pattern-part question asked, not assumed), labor hours vs book-time norms — framed as questions to ask, never as asserted local prices
Required Inputs
Ask for (if not already provided):
- The quote/invoice text or the phone-call version as remembered, with every line and price
- The original symptom: what the car was brought in FOR, in the user's words
- The car (make/model/year/mileage) and its service history roughness
- The relationship: trusted long-term garage, or first visit? (The prior changes the read — and the scripts)
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 · 134 lines · 129 tokens per session scan A ddb3ceca03f2
mechanic-quote-decoder is a cursor rule published in the GitHub repository mohitagw15856/pm-claude-skills (1,352 stars, last pushed 3d ago), licensed MIT. It adds 129 tokens to every session and 1,542 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
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.
control-plane-descriptors
Control plane descriptor and instance implementation patterns.