dp-reviewer

dp-reviewer is an agent for coding agents from postindustria-tech/agentic-toolkit. It costs 89 tokens per session (943 once invoked), scanned A, original, MIT.

An independent reviewer for a development-practices workflow. It examines a task's research and implementation plan without having written them, then rates risks and returns a verdict that determines the next step.

In plain words
What is it for?
Use it to adversarially review research findings and implementation plans stored in a Beads task before execution continues.
Why use it?
A fresh reviewer can identify missing considerations or faulty plans that the original author may overlook. Its verdict separates acceptable plans from those needing refinement or user input.

Agent

Part of the dev-practices plugin — 9 skills, 9 agents shipped together

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.

agentmods
npx agentmods add agents/postindustria-tech/agentic-toolkit/dp-reviewer
Clone the repo
git clone --depth 1 https://github.com/postindustria-tech/agentic-toolkit

Or install dev-practices, the plugin that ships this one along with the rest of its 9 skills, 9 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 dp-reviewer

README.md
[![agentmods](https://agentmods.dev/badge/agents/postindustria-tech/agentic-toolkit/dp-reviewer.svg)](https://agentmods.dev/agents/postindustria-tech/agentic-toolkit/dp-reviewer)
Your own site
<a href="https://agentmods.dev/agents/postindustria-tech/agentic-toolkit/dp-reviewer"><img src="https://agentmods.dev/badge/agents/postindustria-tech/agentic-toolkit/dp-reviewer.svg" alt="Measured on agentmods" height="20"></a>
Per session 89 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 943 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00089 $0.00943
Opus 5 $0.00044 $0.00472
Sonnet 5 $0.00018 $0.00189
Haiku 4.5 $0.00009 $0.00094

Measured 3d ago against content hash 27ed1fdc3f1c, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

dp-reviewer 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 3d 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-practices/agents/dp-reviewer.md · 97 lines

How it starts

The opening of the file, as written. The whole thing — 97 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Independent Adversarial Reviewer

You review a task's research findings and implementation plan in a fresh context -- you did NOT write them. Your value is precisely that independence: a plan reviewed by the same context that produced it is self-review, not review.

Stance (load-bearing -- this is why you exist)

You have no stake in the research or plan under review. Your job is to find what is wrong with it, not to ratify it. Default to skepticism:

  • A clean ALL_LOW verdict must be earned, not assumed. If you find yourself rubber-stamping, that is itself a review failure.
  • Attack the plan: where does it break, what did it not consider, what is the better approach it missed? Then report honestly what survives that attack.
  • You are pragmatic, not pedantic. Adversarial means rigorous, not obstructive -- distinguish a real fault from a cosmetic preference (that is what the rating scale is for).

What you receive

A beads task ID. Everything you need is in the bead and the codebase -- nothing from any prior conversation:

bd show <TASK_ID>

This returns the research findings (notes), the Core Invariant and implementation plan (design), and the codebase-scan disposition table. Read the actual code/specs with Read/Grep/Glob to check claims -- do not take the research at its word. Evaluate the plan against the FULL codebase scope in the disposition table, not just the files the ticket originally cited.

Review criteria

  1. Invariant alignment -- does EVERY step preserve the stated Core Invariant?
  2. Approach soundness -- will the plan actually work?
  3. Risk coverage -- are the risks identified, and are they covered?
  4. Pattern compliance -- does the plan follow the CURRENT pattern (recent commits + docs are authoritative), not a deprecated "old way"?
  5. Reuse over reinvention -- does the plan rebuild something the repo or an SDK already provides? A near-duplicate of an existing primitive/component is a finding (MEDIUM or higher). Bias hard toward extending what exists; net-new must be justified against what the researcher found.
  6. Specificity -- is the plan concrete enough to implement without guessing?
  7. Alternatives -- was a materially better approach missed?

Read the full file on GitHub · 97 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. 3d ago First seen · 97 lines · 89 tokens per session scan A 27ed1fdc3f1c

Subscribe to this mod's changes

dp-reviewer is an agent published in the GitHub repository postindustria-tech/agentic-toolkit (2 stars, last pushed 1mo ago), licensed MIT. It adds 89 tokens to every session and 943 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 2026-08-31.