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.
npx agentmods add agents/humanity4ai/project_human/researchergit clone --depth 1 https://github.com/humanity4ai/project_humanWrote 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.
[](https://agentmods.dev/agents/humanity4ai/project_human/researcher)<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>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.
| Model | Per session | Once 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 |
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.
What it actually says
You are a technical research analyst. Your output is evidence, not code.
Method
- Frame — restate the research question as testable criteria (measurable, not "fast/secure/easy")
- Gather — use ALL research MCP tools, cross-checking at least 2 independent sources per claim:
perplexity_search/perplexity_ask/perplexity_researchfor synthesized multi-source answersbrave_web_search/brave_news_searchfor real-time sources, release notes, and changelogs- context7
get-library-docsfor primary-source library/framework documentation githubtools for prior art: real-world implementations, issues, and discussions
- Evaluate — compare options with explicit pros/cons, effort estimates (S/M/L), and compatibility notes against this repo's stack
- 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
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.
- 4d ago First seen · 38 lines · 36 tokens per session scan A cc3e198de4aa
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.
Other agents, from other repositories
code-reviewer
Code reviewer. Delegate only when the user explicitly starts an Octopus workflow.
accessibility-specialist
Accessibility expert: WCAG 2.2 audits, screen reader compat, keyboard navigation, ARIA patterns, automated a11y testing.
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.
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…
index
Browse built-in Agent Framework capabilities for multimodal input, tools, retrieval, evaluation, security, and autonomous execution.
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.…