blueprint-auditor

blueprint-auditor is an agent for Claude Code from rp1-run/rp1. It costs 18 tokens per session (1,778 once invoked), scanned A, original, Apache-2.0.

A tool for checking product-requirement documents against evidence of what has been implemented. A PRD is a document describing a product or feature’s requirements; this tool can audit the match or carry out selected follow-up actions.

In plain words
What is it for?
Use it to audit PRDs, extract their phases and requirements, compare them with implementation records, and perform supported disposition actions in action mode.
Why use it?
It helps reveal which planned features are complete, missing, or need a decision. It also checks that the named PRD exists before continuing.

Agent for Claude Code

Written for Claude Code: arguments in frontmatter. Also seen: model in frontmatter; positional $N argument.

Part of the rp1-dev plugin — 23 skills, 36 agents shipped together

Good fit Use it to audit PRDs, extract their phases and requirements, compare them with implementation records, and perform supported disposition actions in action mode.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/rp1-run/rp1/blueprint-auditor
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/rp1-run/rp1

Made for: Claude Code.

Or install rp1-dev, the plugin that ships this one along with the rest of its 23 skills, 36 agents.

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 blueprint-auditor

README.md
[![agentmods](https://agentmods.dev/badge/agents/rp1-run/rp1/blueprint-auditor/github.svg)](https://agentmods.dev/agents/rp1-run/rp1/blueprint-auditor)
Your own site
<a href="https://agentmods.dev/agents/rp1-run/rp1/blueprint-auditor"><img src="https://agentmods.dev/badge/agents/rp1-run/rp1/blueprint-auditor/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 blueprint-auditor

Your own site · 80×15
<a href="https://agentmods.dev/agents/rp1-run/rp1/blueprint-auditor"><img src="https://agentmods.dev/badge/agents/rp1-run/rp1/blueprint-auditor.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 18 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,778 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 $0.00018 $0.01778
Opus 5 $0.00009 $0.00889
Sonnet 5 $0.00004 $0.00356
Haiku 4.5 $0.00002 $0.00178

Measured 9d ago against content hash b9fa265ccc04, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

blueprint-auditor 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 9d 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.

plugins/dev/agents/blueprint-auditor.md · 254 lines

How it starts

The opening of the file, as written. The whole thing — 254 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Blueprint Auditor

You are BlueprintAuditorGPT - audits PRD documents against implementation evidence and executes disposition actions.

$1 <prd_name>$2</prd_name> <user_choice>$3</user_choice> <scope_input>$4</scope_input> <kb_root>{{KB_ROOT from prompt}}</kb_root> <work_root>{{WORK_ROOT from prompt}}</work_root>

S1 Validation

  1. PRD_NAME must be non-empty
  2. MODE must be audit or action
  3. Check PRD exists at {WORK_ROOT}/prds/{PRD_NAME}.md

On PRD not found:

  • List available PRDs via glob {WORK_ROOT}/prds/*.md
  • Return error JSON and STOP:
{"type":"error","message":"PRD '{PRD_NAME}' not found.","available_prds":["prd1","prd2"]}

S2 Paths

PRD_PATH = {WORK_ROOT}/prds/{PRD_NAME}.md
FEATURES_DIR = {WORK_ROOT}/features/
FEATURES_ARCHIVE_DIR = {WORK_ROOT}/archives/features/

S3 Mode Branch

  • audit: Continue to S4
  • action: Skip to S8

AUDIT MODE (S4-S7)

S4 PRD Loading & Phase Extraction

Read PRD file and extract:

  1. Title: First # heading
  2. Overview: Content under ## Overview or first paragraph

Phase Extraction (priority order):

Priority Section Extract As
1 ## Milestones / ## Phases Milestone items
2 ## Requirements FR/NFR items
3 ## Scope In-scope items
4 Fallback PRD title as single phase

Capture per phase: id, title, description

S5 Evidence Gathering

For each phase, gather evidence in tier order:

Tier 1: Archive Evidence

  • Glob {FEATURES_ARCHIVE_DIR}/*/requirements.md
  • Search for Parent PRD matching PRD_NAME
  • Evidence: Feature ID + "complete"

Tier 2: Active Feature Evidence

  • Glob {FEATURES_DIR}/*/requirements.md
  • Search for Parent PRD matching PRD_NAME
  • Check feature_verify*.md existence -> complete/in_progress

Tier 3: Codebase Evidence (when Tier 1+2 insufficient)

  • Grep codebase for phase keywords
  • Record files + confidence

S6 Classification

Read the full file on GitHub · 254 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. 9d ago First seen · 254 lines · 18 tokens per session scan A b9fa265ccc04

Subscribe to this mod's changes

blueprint-auditor is an agent published in the GitHub repository rp1-run/rp1 (38 stars, last pushed 2d ago), licensed Apache-2.0. It adds 18 tokens to every session and 1,778 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.

Related

Other agents, from other repositories

adversarial-reviewer

Reviews adversarial-authoring drafts.

intent-driven-dev/intent-driven-template · 7 tokens

skill-creator

Generates or modifies optimized skill files. In creation mode, builds from raw user knowledge. In modification mode, applies targeted changes to existing skills while preserving unchanged content. Use when creating new skills or updating existing ones.

shinpr/rashomon · 47 tokens

validator

Read-only adversarial validator. Spawned by scout to verify research findings against the actual code. Challenges assumptions, confirms or refutes claims, and reports CONFIRMED/CONTESTED/UNVERIFIED. Cannot modify files or run commands — enforced by tool restrictions.

justinjdev/fellowship · 56 tokens

dev-agent-ux-designer

Read-only. Turns the architect's specification into an intentional, coherent UI/UX design system -- information architecture, navigation, layouts, typography, color, component hierarchy, and every UI state (loading/empty/error/success). Avoids generic AI-slop interfaces. Never implements application code.

Surjal/dev-agent · 58 tokens

ai-slop-cleaner

Clean AI-generated code anti-patterns — redundant comments, one-use abstractions, over-engineering, template slop — via behavior-preserving edits verified by compile/lint.

RaNDoM6913/claude-code-superkit · 40 tokens

behavioral-nudge-engine

Behavioral psychology specialist for retention, habit loops, and notification cadence. Designs nudges that increase user engagement without burning them out. Use when building reminders, streak mechanics, onboarding sequences, or social-app retention features.

RaNDoM6913/claude-code-superkit · 48 tokens