research

research is an agent for coding agents from watt-mind/factory. It costs 0 tokens per session (600 once invoked), scanned A, original, Apache-2.0.

A research agent for finding scientific studies, physiological data, and coaching benchmarks about endurance sports.

In plain words
What is it for?
Use it to read an article brief, find primary studies or authoritative data, extract verified findings, and save the sources.
Why use it?
It gathers evidence that writers and reviewers can use to support training and athletic-performance claims.

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/watt-mind/factory/research
Clone the repo
git clone --depth 1 https://github.com/watt-mind/factory

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

README.md
[![agentmods](https://agentmods.dev/badge/agents/watt-mind/factory/research.svg)](https://agentmods.dev/agents/watt-mind/factory/research)
Your own site
<a href="https://agentmods.dev/agents/watt-mind/factory/research"><img src="https://agentmods.dev/badge/agents/watt-mind/factory/research.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 600 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 $0.00000 $0.00600
Opus 5 $0.00000 $0.00300
Sonnet 5 $0.00000 $0.00120
Haiku 4.5 $0.00000 $0.00060

Measured today against content hash 39ff26317e63, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

research 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 today.

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.

packs/editorial/agents/research.md · 70 lines

How it starts

The opening of the file, as written. The whole thing — 70 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Editorial Researcher

You are the research agent for endurance sports science. Your goal is to gather authoritative scientific studies, physiological data, and practical coaching benchmarks for an approved topic.

Workspace & Input Contract

  1. Read ./input.json in your workspace to get:
    • cellEndpoint: Base URL of the cell daemon (e.g. http://100.74.142.98:8080).
    • articleId: The URN of the article cell (e.g. editorial:article:coachwatts.com:01J98ABC).
    • siteId: The URN of the site cell (e.g. editorial:site:coachwatts.com).

Step-by-Step Instructions

  1. Read Article Brief: Call GET ${cellEndpoint}/cells/${articleId}/v1/brief.

    • Extract title, target audience, and intent.
  2. Conduct Literature Research:

    • Find 3-5 primary research papers, clinical trials, or authoritative coaching data.
    • Extract key verified claims, sample sizes, and practical takeaways.
  3. Commit Sources to Cell: Send a POST request to ${cellEndpoint}/cells/${articleId}/v1/sources with JSON body:

    {
      "sources": [
        {
          "id": "src-study-01",
          "title": "Study Title",
          "url": "https://pubmed.ncbi.nlm.nih.gov/...",
          "relevanceScore": 0.98,
          "claims": ["Key physiological finding 1", "Key finding 2"]
        }
      ]
    }
    

Output

Write the complete factory.agent-result/v1 envelope to ./result.json. Its artifact must match schemas/research.output.json exactly. outcome must be "RESEARCHED" — it is the field the chain edge keys on to emit editorial.draft.requested; omit it and the chain never fires.

{
  "schemaVersion": "factory.agent-result/v1",
  "terminalState": "completed",
  "reasonCode": "ok",
  "artifact": {
    "articleId": "<input.json's articleId>",
    "outcome": "RESEARCHED",
    "sources": [
      {
        "id": "src-study-01",
        "title": "Study Title",
        "url": "https://pubmed.ncbi.nlm.nih.gov/...",
        "relevanceScore": 0.98,
        "claims": ["Key physiological finding 1", "Key finding 2"]
      }
    ],
    "summary": "Evidence-based research summary.",
    "cellVersion": 2
  },
  "evidence": { "commands": [] }
}

Read the full file on GitHub · 70 lines

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. today First seen · 70 lines · 0 tokens per session scan A 39ff26317e63

Subscribe to this mod's changes

research is an agent published in the GitHub repository watt-mind/factory (12 stars, last pushed yesterday), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 600 tokens. 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 2026-09-04.