rfp-response-proposal-review

rfp-response-proposal-review is a skill for Claude Code, Codex from pnp/sharepoint-skills. It costs 83 tokens per session (3,144 once invoked), scanned A, original, MIT.

A post-writing audit of a proposal draft against the approved strategy, the buyer's request, and the firm's source material. It produces a report covering strategy alignment, requirement coverage, and whether the content is supported.

In plain words
What is it for?
Use it after proposal drafting to check whether the document follows the response plan, answers the request, and stays grounded in the firm's available information.
Why use it?
A proposal can look complete while missing requirements, drifting from the agreed approach, or making claims without evidence. This review identifies those problems before a human reviewer approves it.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it after proposal drafting to check whether the document follows the response plan, answers the request, and stays grounded in the firm's available information.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/pnp/sharepoint-skills/rfp-response-proposal-review
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.

Any agent
npx skills add pnp/sharepoint-skills --skill rfp-response-proposal-review
Clone the repo
git clone --depth 1 https://github.com/pnp/sharepoint-skills

Made for: Claude Code, Codex.

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 rfp-response-proposal-review

README.md
[![agentmods](https://agentmods.dev/badge/skills/pnp/sharepoint-skills/rfp-response-proposal-review/github.svg)](https://agentmods.dev/skills/pnp/sharepoint-skills/rfp-response-proposal-review)
Your own site
<a href="https://agentmods.dev/skills/pnp/sharepoint-skills/rfp-response-proposal-review"><img src="https://agentmods.dev/badge/skills/pnp/sharepoint-skills/rfp-response-proposal-review/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 rfp-response-proposal-review

Your own site · 80×15
<a href="https://agentmods.dev/skills/pnp/sharepoint-skills/rfp-response-proposal-review"><img src="https://agentmods.dev/badge/skills/pnp/sharepoint-skills/rfp-response-proposal-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 83 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,144 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. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 1 finding, up to high

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • high System Prompt Leakage · line 38
    Skill contains instructions that could directly expose system prompts, internal rules, or hidden instructions to users or external parties.
    Fix: Remove any instructions that reveal, print, or output system prompts or internal rules. System instructions should never be exposed to end users.
How audits are shown
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 $0.00083 $0.03144
Opus 5 $0.00042 $0.01572
Sonnet 5 $0.00017 $0.00629
Haiku 4.5 $0.00008 $0.00314

Measured 11d ago against content hash 82f63738dd5c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

rfp-response-proposal-review 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.

Skills/rfp-response-proposal-review/rfp-response-proposal-review/SKILL.md · 291 lines

How it starts

The opening of the file, as written. The whole thing — 291 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Proposal Review Skill

Firm Profile (REQUIRED — fill in before use)

These values define who your firm is and how it writes. See SETUP.md.

  • FIRM NAME: [FIRM NAME]
  • WHAT THE FIRM DOES: [one sentence]
  • ROLE BOUNDARY: [what the firm will NOT claim to do — leave blank if none]
  • VENDOR STANCE: [vendor-neutral OR resells/implements specific products]
  • SPECIALIZATION: [domains the firm credibly claims]
  • VOICE: [3–5 adjectives]

Purpose

An AI-generated proposal draft may look complete but contain three categories of silent failure: drift from the approved strategy, missed RFP requirements, or content not grounded in the firm's source material. None are obvious from a quick read. This skill audits all three dimensions and produces a structured Review Report telling the human reviewer exactly what to look at — and what has already been verified — before they open the draft.


Critical Output Rules

Do not output the Review Report or audit findings to chat. All findings go into the Review Report Word document saved in Step 6. Chat output is limited to one-line progress updates per step and the final summary.

The Review Report Word document is the only deliverable. Accumulate findings internally, then write the complete report in Step 6.


Prerequisites

  • The generated proposal draft (.docx) must be in the deal's WIP Collaboration Folder subfolder.
  • The Strategy Brief (.docx, Phase 2) must be accessible — approved ToC, strategic themes, tone guidance, section-by-section drafting notes.
  • The RFP Tracker List must be accessible with all columns populated, including Available Content and Source 1/2/3.
  • Write access to the deal's WIP Collaboration Folder subfolder.

Step 1 — Load All Inputs

Load and read the following before any checks.

Proposal Draft — read in full. Note:

  • The actual section structure and headings present
  • Text marked as placeholder ([PLACEHOLDER, [TBD, [INSERT, [MISSING, or similar)
  • Sections notably thin (less than one substantive paragraph)
  • Specific factual claims, statistics, or named outcomes that require source grounding

Read the full file on GitHub · 291 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. 11d ago First seen · 291 lines · 83 tokens per session scan A 82f63738dd5c

Subscribe to this mod's changes

rfp-response-proposal-review is a skill published in the GitHub repository pnp/sharepoint-skills (116 stars, last pushed 2d ago), licensed MIT. It adds 83 tokens to every session and 3,144 once invoked, about $0.0004 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.