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/rp1-run/rp1Wrote 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/agents/rp1-run/rp1/blueprint-auditor)<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.
<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>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 | $0.00018 | $0.01778 |
| Opus 5 | $0.00009 | $0.00889 |
| Sonnet 5 | $0.00004 | $0.00356 |
| Haiku 4.5 | $0.00002 | $0.00178 |
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.
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
- PRD_NAME must be non-empty
- MODE must be
auditoraction - 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:
- Title: First
#heading - Overview: Content under
## Overviewor 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 PRDmatching PRD_NAME - Evidence: Feature ID + "complete"
Tier 2: Active Feature Evidence
- Glob
{FEATURES_DIR}/*/requirements.md - Search for
Parent PRDmatching PRD_NAME - Check
feature_verify*.mdexistence -> complete/in_progress
Tier 3: Codebase Evidence (when Tier 1+2 insufficient)
- Grep codebase for phase keywords
- Record files + confidence
S6 Classification
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.
- 9d ago First seen · 254 lines · 18 tokens per session scan A b9fa265ccc04
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.
Other agents, from other repositories
adversarial-reviewer
Reviews adversarial-authoring drafts.
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.
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.
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.
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.
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.