construction-rfi-response

construction-rfi-response is a cursor rule for Cursor from mohitagw15856/pm-claude-skills. It costs 101 tokens per session (1,289 once invoked), scanned A, original, MIT.

A concise response to a construction RFI, or request for information, that answers the question, cites the governing document, and states cost and schedule effects.

In plain words
What is it for?
It is for contractor queries, construction clarification records, variation checks, and maintaining an auditable RFI register.
Why use it?
It prevents a worksite from waiting or proceeding on an unrecorded assumption, while clarifying whether the answer changes the agreed work.

Cursor rule for Cursor

Written for Cursor: a Cursor rule (.mdc).

Good fit It is for contractor queries, construction clarification records, variation checks, and maintaining an auditable RFI register.

Compare 6 cursor rules from other repositories ↓
Install with agentmods
npx agentmods add rules/mohitagw15856/pm-claude-skills/construction-rfi-response
About the project

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.

mohitagw15856/pm-claude-skills · 1,352 stars · on GitHub · mohitagw15856.github.io

Install

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.

Clone the repo
git clone --depth 1 https://github.com/mohitagw15856/pm-claude-skills

Made for: Cursor.

Wrote 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.

agentmods badge for construction-rfi-response

README.md
[![agentmods](https://agentmods.dev/badge/rules/mohitagw15856/pm-claude-skills/construction-rfi-response/github.svg)](https://agentmods.dev/rules/mohitagw15856/pm-claude-skills/construction-rfi-response)
Your own site
<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.

agentmods 80×15 button for construction-rfi-response

Your own site · 80×15
<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>
Per session 101 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,289 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce 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

Measured 8d ago against content hash ecde83885c46, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

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.

exports/cursor/pm-architecture/construction-rfi-response/construction-rfi-response.mdc · 87 lines

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

  1. Answer in the first line. Site reads the first sentence and acts. Context belongs underneath it.
  2. Point at the governing document. A drawing number and revision, or a specification clause. An answer with no reference generates the next RFI.
  3. 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.
  4. 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.
  5. 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.
  6. Distribute to everyone affected. An answer that reaches only the asker creates a second RFI from another trade.
  7. 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.

Read the full file on GitHub · 87 lines

Changes

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.

  1. 8d ago First seen · 87 lines · 101 tokens per session scan A ecde83885c46

Subscribe to this mod's changes

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.