research-intelligence

research-intelligence is a skill for Claude Code, Codex from AlekseiUL/hermes-researcher-agent. It costs 41 tokens per session (2,830 once invoked), scanned A, original, MIT.

A public-source research workflow for gathering and evaluating evidence about tools, projects, vendors, products, papers, and market signals.

In plain words
What is it for?
Use it for public research, tool comparisons, GitHub and community checks, official documentation reviews, competitor analysis, and decision briefs.
Why use it?
It separates confirmed facts, weak signals, hypotheses, and interpretation so decisions are based on appropriately graded evidence.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is python3 tools/evidence_lineage_check.py examples/research-run-source-lineage.json --json.

Good fit Use it for public research, tool comparisons, GitHub and community checks, official documentation reviews, competitor analysis, and decision briefs.

Compare 6 skills from other repositories ↓
Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo
git clone --depth 1 https://github.com/AlekseiUL/hermes-researcher-agent
agentmods
npx agentmods add skills/alekseiul/hermes-researcher-agent/research-intelligence

Made for: Claude Code, Codex.

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-intelligence

README.md
[![agentmods](https://agentmods.dev/badge/skills/alekseiul/hermes-researcher-agent/research-intelligence/github.svg)](https://agentmods.dev/skills/alekseiul/hermes-researcher-agent/research-intelligence)
Your own site
<a href="https://agentmods.dev/skills/alekseiul/hermes-researcher-agent/research-intelligence"><img src="https://agentmods.dev/badge/skills/alekseiul/hermes-researcher-agent/research-intelligence/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for research-intelligence

Your own site · 80×15
<a href="https://agentmods.dev/skills/alekseiul/hermes-researcher-agent/research-intelligence"><img src="https://agentmods.dev/badge/skills/alekseiul/hermes-researcher-agent/research-intelligence.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 41 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,830 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. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00041 $0.02830
Opus 5 $0.00020 $0.01415
Sonnet 5 $0.00008 $0.00566
Haiku 4.5 $0.00004 $0.00283

Measured 7d ago against content hash 5174cef9f29d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

research-intelligence 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 7d 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.

skills/research-intelligence/SKILL.md · 283 lines

How it starts

The opening of the file, as written. The whole thing — 283 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Research Intelligence

Overview

This skill turns a Hermes agent into a careful public-source researcher. It is optimized for comparing tools, vendors, repositories, products, papers, market signals, community pain, and public claims.

The operating rule is simple: collect enough evidence for the decision, not enough links to look busy. Facts, weak signals, hypotheses, and interpretation must be kept separate when the answer affects money, risk, implementation, reputation, or public claims.

When to Use

Use for:

  • tool, repository, model, vendor, or product comparison;
  • public GitHub/project traction checks;
  • official docs/changelog/release research;
  • community pain and adoption scouting;
  • public OSINT-style due diligence on companies, products, or public claims;
  • research briefs for implementation, purchase, positioning, or watch/reject decisions;
  • recurring watchlist design, but only when the user explicitly asks for monitoring.

Do not use for:

  • private-account scraping;
  • bypassing login walls, paywalls, CAPTCHAs, or access controls;
  • collecting secrets, credentials, private exports, or personal data;
  • legal/medical/financial conclusions without qualified review;
  • public posting, registration, payment, joining, following, liking, DMing, or emailing without explicit approval.

Core Research Loop

  1. Frame the decision. Name the user decision: adopt, buy, compare, reject, watch, implement, contact, investigate, or hand off.
  2. Choose the mode. Use references/research-modes.md to select quick_fact, deep_research, repo_tool, community_pain, live_visual, or monitoring_design.
  3. Build the source ladder. Pick source classes before searching.
  4. Ingest documents when needed. For public PDFs, DOCX, PPTX, spreadsheets, HTML, EPUB, or inspected trusted document bundles, create a Markdown analysis copy with markitdown-document-ingestion before summarizing.
  5. Collect dated facts. Include timestamps for volatile data like stars, downloads, prices, package versions, and community metrics.
  6. Group source lineages. Copies, syndications, mirrors, and posts repeating one announcement count as one evidence lineage until independent reporting or data is shown.
  7. Triangulate important claims. Decision-relevant claims need primary or structured evidence plus another independent lineage when safely available.
  8. Seek a counterexample. Check failure terms, negative cases, limitations, and evidence that could change the decision.
  9. Classify signal strength. Use fact / claim / weak signal / hypothesis / interpretation.
  10. Browser-check the shortlist. Use a real browser, DOM extraction, or vision for dynamic/social/visual pages when live state matters.
  11. Run the evidence gate. Fix gaps or label limitations before final answer.
  12. Return the next move. A good brief ends with a practical action.

Read the full file on GitHub · 283 lines

Files

What ships with it

3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 7d ago Changed · +57 lines 5174cef9f29d
  2. 12d ago First seen · 226 lines · 41 tokens per session scan A e6223b9a5577

Subscribe to this mod's changes

research-intelligence is a skill published in the GitHub repository AlekseiUL/hermes-researcher-agent (57 stars, last pushed 7d ago), licensed MIT. It adds 41 tokens to every session and 2,830 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 2026-08-30.

Related

Other skills, from other repositories

humanize-automation

Human-like mouse, keyboard and scroll behavior for behavioral bot bypass.

uphiago/recon-skills · 18 tokens

hermes-tweet

Use Xquik in Hermes Agent for public X research, monitoring, thread summaries, creator discovery & approved actions. Not affiliated with X Corp. Use when the user requests X data or a named action. Trigger with "search X", "monitor X", "post tweet", or "X trends".

Xquik-dev/hermes-tweet · 65 tokens

browser-harness-authoring

Use when mapping a repeatable website workflow into a verified Hermes skill so later runs can follow known steps instead of rediscovering the site. Surveys browser compatibility, semantic targets, failure modes, recovery paths, decision gates, and expiry using dummy data and no irreversible submissions.

AtlasOmnia/hermes-custom-pack · 60 tokens

obsidian-memory-architecture

Use when designing, setting up, or maintaining an Obsidian vault as Hermes Agent's durable knowledge layer. Routes facts, conversation history, documents, procedures, and daily logs to the correct Hermes or vault system without duplicating everything into the prompt.

AtlasOmnia/hermes-custom-pack · 56 tokens

hermes-diagnostic-review

Use when running a read-only diagnostic review of recent Hermes sessions to find recurring mistakes, failed tool calls, and repeated fixes, then propose suggestion-only improvements and reusable skills. Human-gated; never auto-applies.

AtlasOmnia/hermes-custom-pack · 49 tokens

holix-cron

Schedule recurring agent tasks via Holix built-in gateway cron (not crontab or custom scripts).

javded-itres/Holix · 25 tokens