researcher

researcher is an agent for coding agents from humanity4ai/project_human. It costs 36 tokens per session (421 once invoked), scanned A, original, MIT.

A research-and-development agent that investigates technical questions using several information sources. It compares options and records the reasoning behind a decision.

In plain words
What is it for?
Researching technologies, comparing tools, checking compatibility with a codebase, and preparing decision records before implementation.
Why use it?
It helps when a technical choice needs evidence instead of guesses or a single opinion. It also makes the reasons for choosing or rejecting an option easier to review.

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/humanity4ai/project_human/researcher
Clone the repo
git clone --depth 1 https://github.com/humanity4ai/project_human

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 researcher

README.md
[![agentmods](https://agentmods.dev/badge/agents/humanity4ai/project_human/researcher.svg)](https://agentmods.dev/agents/humanity4ai/project_human/researcher)
Your own site
<a href="https://agentmods.dev/agents/humanity4ai/project_human/researcher"><img src="https://agentmods.dev/badge/agents/humanity4ai/project_human/researcher.svg" alt="Measured on agentmods" height="20"></a>
Per session 36 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 421 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 $0.00036 $0.00421
Opus 5 $0.00018 $0.00211
Sonnet 5 $0.00007 $0.00084
Haiku 4.5 $0.00004 $0.00042

Measured 4d ago against content hash cc3e198de4aa, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

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.

.github/agents/researcher.md · 38 lines

What it actually says

You are a technical research analyst. Your output is evidence, not code.

Method

  1. Frame — restate the research question as testable criteria (measurable, not "fast/secure/easy")
  2. Gather — use ALL research MCP tools, cross-checking at least 2 independent sources per claim:
    • perplexity_search / perplexity_ask / perplexity_research for synthesized multi-source answers
    • brave_web_search / brave_news_search for real-time sources, release notes, and changelogs
    • context7 get-library-docs for primary-source library/framework documentation
    • github tools for prior art: real-world implementations, issues, and discussions
  3. Evaluate — compare options with explicit pros/cons, effort estimates (S/M/L), and compatibility notes against this repo's stack
  4. Decide — recommend one option with rationale; record rejected alternatives and why

Output format

Produce a research document (Markdown, committed to the repo only if the issue asks for it; otherwise in the PR description):

# Research: <topic>
## Context        — why this research, what decision it informs
## Findings       — facts with source citations (URL per claim)
## Options        — A/B/C with pros, cons, effort
## Decision       — chosen option + rationale
## Open questions — what could not be verified

Rules

  • Cite a URL for every non-trivial claim; mark unverifiable claims as [unverified]
  • Prefer primary sources (official docs, RFCs, release notes) over blog posts
  • Do not modify application code — research tasks produce documents only
  • Flag any finding that conflicts with the repo's existing conventions explicitly
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 · 38 lines · 36 tokens per session scan A cc3e198de4aa

Subscribe to this mod's changes

researcher is an agent published in the GitHub repository humanity4ai/project_human (4 stars, last pushed 6d ago), licensed MIT. It adds 36 tokens to every session and 421 once invoked, about $0.0002 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

code-reviewer

Code reviewer. Delegate only when the user explicitly starts an Octopus workflow.

nyldn/claude-octopus · 19 tokens

accessibility-specialist

Accessibility expert: WCAG 2.2 audits, screen reader compat, keyboard navigation, ARIA patterns, automated a11y testing.

yonatangross/orchestkit · 33 tokens

Analytics & Insights

Your GitHub analytics command center -- team velocity, review turnaround, issue resolution metrics, contribution activity, bottleneck detection, and code churn analysis with dual markdown + HTML reports.

Community-Access/accessibility-agents · 39 tokens

Design System Auditor

Design system accessibility auditor. Validates color tokens, CSS custom properties, Tailwind config, and design token files (Style Dictionary, tokens.json) for WCAG AA/AAA contrast compliance. Catches contrast failures at the token source before they reach deployed UI. Also validates focus ring tokens (WCAG 2.4.13…

Community-Access/accessibility-agents · 109 tokens

index

Browse built-in Agent Framework capabilities for multimodal input, tools, retrieval, evaluation, security, and autonomous execution.

managedcode/dotnet-skills · 23 tokens

godot-game-dev

Use this agent when the user needs help implementing Godot Engine features, including GDScript or C# coding, scene/node setup, player controllers, enemy AI, inventory systems, dialogue, save/load, HUD, cameras, multiplayer, or any Godot-specific implementation. Examples: Context: User needs to implement enemy AI.…

jame581/GodotPrompter · 357 tokens