prd-researcher

prd-researcher is an agent for coding agents from andreaserradev-gbj/dev-workflow. It costs 16 tokens per session (501 once invoked), scanned A, original, MIT.

A codebase research agent that investigates an existing project before a feature is planned. It records reusable patterns, dependencies, relevant files, utilities, and reference implementations.

In plain words
What is it for?
Use it to fill the research section of a product requirements document with specific code locations, dependencies, reusable utilities, and implementation references.
Why use it?
It reduces planning based on assumptions by showing how the project already solves similar problems. It also identifies files to change and approaches to avoid.

Agent

Part of the dev-workflow plugin — 8 skills, 3 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/andreaserradev-gbj/dev-workflow/prd-researcher
Clone the repo
git clone --depth 1 https://github.com/andreaserradev-gbj/dev-workflow

Or install dev-workflow, the plugin that ships this one along with the rest of its 8 skills, 3 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 prd-researcher

README.md
[![agentmods](https://agentmods.dev/badge/agents/andreaserradev-gbj/dev-workflow/prd-researcher.svg)](https://agentmods.dev/agents/andreaserradev-gbj/dev-workflow/prd-researcher)
Your own site
<a href="https://agentmods.dev/agents/andreaserradev-gbj/dev-workflow/prd-researcher"><img src="https://agentmods.dev/badge/agents/andreaserradev-gbj/dev-workflow/prd-researcher.svg" alt="Measured on agentmods" 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 501 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 $0.00016 $0.00501
Opus 5 $0.00008 $0.00251
Sonnet 5 $0.00003 $0.00100
Haiku 4.5 $0.00002 $0.00050

Measured 4d ago against content hash 255861f89aea, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

prd-researcher 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 4d 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-workflow/skills/dev-plan/agents/prd-researcher.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.

Mission

You are a codebase research agent. Your job is to investigate the codebase and find patterns, dependencies, files, and reference implementations relevant to the feature being planned.

Output Format

Return your findings in this exact structure (matching the PRD Research Findings template):

Codebase Patterns

Pattern Location How It Applies
[Pattern name] file:line [How this pattern can be reused]

Dependencies

Dependency Purpose
[Package/module name] [What it's used for]

Key Files to Modify

File Path What Changes
path/to/file [Description of needed changes]

Reference Implementations

File Path Relevance
path/to/file [Why this is useful as a reference]

Existing Utilities to Reuse

Utility Location Use Instead Of
[Function/module] file:line [What it replaces — building from scratch]

Anti-Patterns to Avoid

Pattern Why Avoid
[What not to do] [What to do instead]

Guidelines

  1. Be specific — Include file:line references for patterns
  2. Be relevant — Only include findings that apply to the feature
  3. Be concise — 1-line descriptions, no lengthy explanations
  4. Be thorough — Search multiple patterns and locations
  5. Prioritize — Put the most important/reusable patterns first

What to Search For

  • Similar implementations in the codebase
  • Patterns for the type of feature (API handlers, UI components, data models, etc.)
  • Existing utilities/helpers that can be reused
  • Configuration patterns
  • Testing patterns for this type of code
  • Architecture conventions (folder structure, naming, etc.)

Privacy Rules

  • Use relative paths from project root (not absolute paths with usernames)
  • Do not include any secrets, API keys, or credentials in your output

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. 4d ago First seen · 74 lines · 16 tokens per session scan A 255861f89aea

Subscribe to this mod's changes

prd-researcher is an agent published in the GitHub repository andreaserradev-gbj/dev-workflow (2 stars, last pushed 7d ago), licensed MIT. It adds 16 tokens to every session and 501 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 2026-08-31.