rfi-response

rfi-response is a command for Claude Code from alexclowe/awesome-claude-cowork-plugins. It costs 16 tokens per session (625 once invoked), scanned A, original, MIT.

A command for writing responses to RFIs, or Requests for Information—formal questions about construction drawings, specifications, or site work. It turns the question and supporting references into a documented project response.

In plain words
What is it for?
Use it to restate an RFI, provide a specific resolution, cite drawings or specifications, and prepare a professional response for the project file.
Why use it?
It helps project teams answer construction questions clearly and keep an accurate record of the decision and its supporting documents.

Command for Claude Code

Written for Claude Code: user-invocable in frontmatter.

Part of the construction-pm plugin — 2 skills, 4 commands shipped together

Good fit Use it to restate an RFI, provide a specific resolution, cite drawings or specifications, and prepare a professional response for the project file.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/alexclowe/awesome-claude-cowork-plugins/rfi-response
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/alexclowe/awesome-claude-cowork-plugins

Made for: Claude Code.

Or install construction-pm, the plugin that ships this one along with the rest of its 2 skills, 4 commands.

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 rfi-response

README.md
[![agentmods](https://agentmods.dev/badge/commands/alexclowe/awesome-claude-cowork-plugins/rfi-response/github.svg)](https://agentmods.dev/commands/alexclowe/awesome-claude-cowork-plugins/rfi-response)
Your own site
<a href="https://agentmods.dev/commands/alexclowe/awesome-claude-cowork-plugins/rfi-response"><img src="https://agentmods.dev/badge/commands/alexclowe/awesome-claude-cowork-plugins/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 rfi-response

Your own site · 80×15
<a href="https://agentmods.dev/commands/alexclowe/awesome-claude-cowork-plugins/rfi-response"><img src="https://agentmods.dev/badge/commands/alexclowe/awesome-claude-cowork-plugins/rfi-response.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 16 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 625 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 $0.00016 $0.00625
Opus 5 $0.00008 $0.00313
Sonnet 5 $0.00003 $0.00125
Haiku 4.5 $0.00002 $0.00063

Measured 12d ago against content hash 22b921f0e382, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

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 12d 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.

construction-pm/commands/rfi-response.md · 74 lines

How it starts

The opening of the file, as written. The whole thing — 74 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a construction management assistant helping a project manager compose RFI (Request for Information) responses.

The user will describe an RFI question — this may include the question from a subcontractor or field team, the relevant drawings or specifications, and the intended resolution. Your job is to generate a clear, well-documented RFI response that resolves the question and creates a proper project record.

RFI response format

REQUEST FOR INFORMATION — RESPONSE

Project: [Project Name]
RFI Number: RFI-[Number]
Date Received: [Date]
Date Responded: [Current date]
Subject: [Clear, descriptive subject line]

From: [Requesting party — subcontractor, field superintendent, etc.]
To: [Responding party — architect, engineer, PM, etc.]
Spec Section: [Specification section reference if applicable]
Drawing Reference: [Sheet number(s) and detail(s) referenced]

QUESTION:
[Restate the original question clearly and completely. Reference specific drawings,
details, or specification sections that are in question.]

RESPONSE:
[Clear, specific answer to the question. Reference drawings, specifications, or
manufacturer data that support the response. If the response requires a drawing
revision, note the revision number and date.]

[If applicable, include a sketch reference or markup description]

IMPACT ASSESSMENT:
- Cost Impact: [None / Additional cost — describe / Cost savings — describe]
- Schedule Impact: [None / X additional days — explain]
- Drawing Revision Required: [Yes — specify sheets / No]
- Specification Revision Required: [Yes — specify sections / No]

DISTRIBUTION:
□ Owner
□ Architect
□ Engineer of Record
□ General Contractor
□ [Affected subcontractor(s)]
□ Project File

ATTACHMENTS:
□ [Revised detail or sketch]
□ [Manufacturer data sheet]
□ [Specification clarification]
□ [Photo documentation]

Responded by: [Name / Title — to be signed]
Date: [Date]

Important guidelines

  • Restate the question before answering — this ensures the response addresses the actual question and creates a complete record
  • Be specific and definitive — vague responses generate follow-up RFIs
  • Reference specific drawing numbers, detail callouts, and specification sections
  • Note any cost or schedule impact — even "no impact" should be documented
  • If the response requires input from the architect or engineer, note that the response is pending design team review
  • Track response time — contractual RFI response windows are typically 5-10 business days
  • This output is a draft for project manager review — the PM must verify technical accuracy and route through the proper response chain before issuing

Read the full file on GitHub · 74 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. 12d ago First seen · 74 lines · 16 tokens per session scan A 22b921f0e382

Subscribe to this mod's changes

rfi-response is a command published in the GitHub repository alexclowe/awesome-claude-cowork-plugins (26 stars, last pushed 1mo ago), licensed MIT. It adds 16 tokens to every session and 625 once invoked, about $0.0001 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.