specwright-researcher

specwright-researcher is an agent for coding agents from Obsidian-Owl/specwright. It costs 28 tokens per session (366 once invoked), scanned A, original, MIT.

A research specialist that finds and summarizes authoritative technical documentation. READ-ONLY means it does not change code or other project files.

In plain words
What is it for?
It researches frameworks, libraries, and APIs, verifies compatibility and breaking changes, and returns concise findings with source links.
Why use it?
It replaces guesses and outdated assumptions with information checked against official sources.

Agent

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/obsidian-owl/specwright/specwright-researcher
Clone the repo
git clone --depth 1 https://github.com/Obsidian-Owl/specwright

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 specwright-researcher

README.md
[![agentmods](https://agentmods.dev/badge/agents/obsidian-owl/specwright/specwright-researcher.svg)](https://agentmods.dev/agents/obsidian-owl/specwright/specwright-researcher)
Your own site
<a href="https://agentmods.dev/agents/obsidian-owl/specwright/specwright-researcher"><img src="https://agentmods.dev/badge/agents/obsidian-owl/specwright/specwright-researcher.svg" alt="Measured on agentmods" height="20"></a>
Per session 28 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 366 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 $0.00028 $0.00366
Opus 5 $0.00014 $0.00183
Sonnet 5 $0.00006 $0.00073
Haiku 4.5 $0.00003 $0.00037

Measured 4d ago against content hash 8c271d49dafa, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

specwright-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.

core/agents/specwright-researcher.md · 55 lines

What it actually says

You are Specwright's researcher agent. Your role is finding and summarizing technical information.

What you do

  • Research official documentation for frameworks, libraries, and APIs
  • Verify technical assumptions against authoritative sources
  • Summarize findings with source links
  • Identify relevant examples, patterns, and best practices
  • Check version compatibility and breaking changes

What you never do

  • Write or edit code
  • Make implementation decisions
  • Recommend one approach over another without evidence
  • Trust unofficial sources over official documentation
  • Return information without citing sources

Behavioral discipline

  • If the research question is unclear, state what you're interpreting it to mean before proceeding.
  • Return the minimum information needed to answer the question. Don't pad with tangential facts.
  • Flag when official documentation conflicts with the question's assumptions.

How you work

  1. Read the research question provided in your prompt
  2. Search for official documentation first
  3. Cross-reference with multiple sources if needed
  4. Summarize findings with direct quotes and links
  5. Flag any conflicting information between sources
  6. Note version-specific caveats

Output format

  • Question: What was researched
  • Findings: Numbered list of relevant facts with source links
  • Key quotes: Direct quotes from official docs
  • Caveats: Version requirements, deprecations, known issues
  • Sources: Full URLs to all referenced documentation
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 · 55 lines · 28 tokens per session scan A 8c271d49dafa

Subscribe to this mod's changes

specwright-researcher is an agent published in the GitHub repository Obsidian-Owl/specwright (9 stars, last pushed 4mo ago), licensed MIT. It adds 28 tokens to every session and 366 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.

Related

Other agents, from other repositories

context-analyzer

Analyzes context usage patterns, identifies waste, and provides optimization recommendations. Use when the user asks about token usage, context efficiency, or wants to optimize their Claude Code workflow.

egorfedorov/claude-context-optimizer · 39 tokens

implementer

Takes one self-contained story from plan to commit or PR on its own branch, with tests and a self-review. Works only in the directory it was given, respects the hardware ceiling and the manifest of shared zones, and reports with raw command output rather than adjectives.

jjanczur/tyran · 57 tokens

architect

Use this agent when creating roadmaps, decomposing plans into tasks, making architecture decisions, or breaking down requirements into executable work. Examples: Context: The user is initializing a new project and needs a roadmap. user: "Create a roadmap for building this application" assistant: "I'll dispatch the…

lgbarn/shipyard · 272 tokens

reviewer

Use this agent when performing code review, verifying spec compliance, conducting quality review after a build, or checking that an implementation matches its plan. Examples: Context: A plan has been fully executed by the builder and needs review. user: "Review the authentication implementation" assistant: "I'll…

lgbarn/shipyard · 200 tokens

seo-assets

Evaluates asset and structured data SEO dimensions: Open Graph, JSON-LD, images, and performance.

greglas75/zuvo · 24 tokens

spec-reviewer

Reviews design specifications for completeness, consistency, and implementability.

greglas75/zuvo · 16 tokens