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/construction-rfi-response)<a href="https://agentmods.dev/rules/mohitagw15856/pm-claude-skills/construction-rfi-response"><img src="https://agentmods.dev/badge/rules/mohitagw15856/pm-claude-skills/construction-rfi-response/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/construction-rfi-response"><img src="https://agentmods.dev/badge/rules/mohitagw15856/pm-claude-skills/construction-rfi-response.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 | $0.00101 | $0.01289 |
| Opus 5 | $0.00051 | $0.00645 |
| Sonnet 5 | $0.00020 | $0.00258 |
| Haiku 4.5 | $0.00010 | $0.00129 |
Grade A, and why
construction-rfi-response 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 — 87 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Construction RFI Response
An RFI is a clock. Site is either waiting or proceeding on an assumption, and both are expensive. The answer that works is short, points at the document that governs, and says plainly whether this is a clarification or a change — because the argument that follows is almost always about that distinction, and it is far cheaper to settle in the response than in the final account.
What This Skill Produces
- A direct answer — the actual resolution, in the first line
- The governing reference — the drawing, specification clause, or schedule that supports it
- Cost and programme implication — stated explicitly, including when there is none
- Instruction status — whether this is a clarification of existing information or a variation requiring a formal instruction
- The distribution list — who else is affected and must receive it
- The register entry — the fields that keep the RFI log usable and the response auditable
Required Inputs
Ask for these if not provided:
- The RFI — the question as asked, its number, date received, and the response date required
- What is actually being asked — sometimes different from what was written; clarify before answering
- The governing documents — the drawings, specification, and schedules that bear on the question
- The status on site — whether work is stopped, proceeding, or about to be covered up
- Who else is affected — other trades, the client, and any consultant whose design is touched
Framework: Answer First, Reference Second, Implication Third
- Answer in the first line. Site reads the first sentence and acts. Context belongs underneath it.
- Point at the governing document. A drawing number and revision, or a specification clause. An answer with no reference generates the next RFI.
- Say whether this is a change. Clarification of existing information, or a variation? This single field is where most final-account disputes originate, and it costs nothing to state now.
- State the cost and time implication even when it is nil. 'No cost or programme implication' is a valuable sentence, and its absence is read as an admission.
- Answer what was actually asked. If the question is ambiguous, resolve the ambiguity by phone and record the clarification — do not answer a question you invented.
- Distribute to everyone affected. An answer that reaches only the asker creates a second RFI from another trade.
- Watch the clock. If you cannot answer in full by the required date, issue a holding response with a date — silence is what causes the delay claim.
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 · 87 lines · 101 tokens per session scan A ecde83885c46
construction-rfi-response is a cursor rule published in the GitHub repository mohitagw15856/pm-claude-skills (1,352 stars, last pushed 3d ago), licensed MIT. It adds 101 tokens to every session and 1,289 once invoked, about $0.0005 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
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.