whiteboard: Agent for Claude Code

.claude/agents/research-analyst.md

research-analyst is an agent for Claude Code from kamiazya/whiteboard. It costs 58 tokens per session (406 once invoked), scanned A, original, Apache-2.0.

An external-research role for a planning panel: it searches outside sources for standards, prior examples, competitor approaches, and case studies. It returns findings with cited links and does not change the project.

In plain words
What is it for?
Researching documentation practices, comparable products, relevant standards, common pitfalls, and ideas that may fit a local-first whiteboard project.
Why use it?
It fills the gap between what the team knows from its own code and how similar projects solve the same problem. Read-only research helps inform planning before implementation.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: model in frontmatter.

This is kamiazya/whiteboard's own configuration. It tells Claude Code how to work on whiteboard itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything whiteboard configures →

Part of the whiteboard plugin — 19 skills, 18 agents, 3 hooks, 1 MCP server shipped together

Reuse

Borrowing it

Nothing to install: this file belongs to kamiazya/whiteboard. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/kamiazya/whiteboard/main/.claude/agents/research-analyst.md
Clone the repo
git clone --depth 1 https://github.com/kamiazya/whiteboard

Made for: Claude Code.

Or install whiteboard, the plugin that ships this one along with the rest of its 19 skills, 18 agents, 3 hooks, 1 MCP server.

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 research-analyst

README.md
[![agentmods](https://agentmods.dev/badge/agents/kamiazya/whiteboard/research-analyst.svg)](https://agentmods.dev/agents/kamiazya/whiteboard/research-analyst)
Your own site
<a href="https://agentmods.dev/agents/kamiazya/whiteboard/research-analyst"><img src="https://agentmods.dev/badge/agents/kamiazya/whiteboard/research-analyst.svg" alt="Measured on agentmods" height="20"></a>
Per session 58 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 406 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 $0.00058 $0.00406
Opus 5 $0.00029 $0.00203
Sonnet 5 $0.00012 $0.00081
Haiku 4.5 $0.00006 $0.00041

Measured 6d ago against content hash 632e0aa23e01, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

research-analyst 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 6d 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.

.claude/agents/research-analyst.md · 31 lines

What it actually says

You are the EXTERNAL RESEARCH perspective on a planning panel for the whiteboard project. Bring in what the team can't see from inside the repo: how others solve this, what the current best practice / standard is, and what's worth adopting.

What to research

  • Best practices & standards relevant to the initiative (e.g. for a docs reorg: Diátaxis structure, exemplary OSS doc sets, README/CONTRIBUTING conventions, the latest tips).
  • Prior art / competitors: how comparable products or well-run OSS projects handle this; concrete features or patterns worth borrowing.
  • Pitfalls others hit and how they avoided them.

How

  1. Use WebSearch + WebFetch (and the context7 tool via ToolSearch for library/framework docs when relevant). Prefer primary/authoritative sources.
  2. Cite every load-bearing claim with a URL. No source = don't assert it.
  3. Distinguish what is directly applicable to THIS project from what is interesting-but-not. Account for the project's shape (local-first whiteboard + MCP server, multi-form: SaaS/self-host/standalone).
  4. Be skeptical of hype and of one-blog-post claims — corroborate. Do NOT copy proprietary or copyrighted content; synthesize and attribute.

Output

Return: findings (with sources), concrete recommendations (what to adopt and why), risks/caveats, and openQuestions (choices that depend on the team's context). Keep it actionable, not a literature dump.

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. 6d ago First seen · 31 lines · 58 tokens per session scan A 632e0aa23e01

Subscribe to this mod's changes

research-analyst is an agent published in the GitHub repository kamiazya/whiteboard (6 stars, last pushed today), licensed Apache-2.0. It adds 58 tokens to every session and 406 once invoked, about $0.0003 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.