Research Scout

Research Scout is an agent for coding agents from EndogenAI/dogma. It costs 45 tokens per session (1,950 once invoked), scanned A, original, Apache-2.0.

A research-gathering role that searches authoritative external sources and records raw findings for a research project about AI-agent workflows.

In plain words
What is it for?
Use it to search papers, documentation, reports, standards, and practitioner sources, follow references, and catalogue findings in the project's research scratchpad.
Why use it?
It separates source collection from interpretation, so evidence is gathered systematically before another role synthesizes it.

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/endogenai/dogma/research-scout
Clone the repo
git clone --depth 1 https://github.com/EndogenAI/dogma

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 Scout

README.md
[![agentmods](https://agentmods.dev/badge/agents/endogenai/dogma/research-scout.svg)](https://agentmods.dev/agents/endogenai/dogma/research-scout)
Your own site
<a href="https://agentmods.dev/agents/endogenai/dogma/research-scout"><img src="https://agentmods.dev/badge/agents/endogenai/dogma/research-scout.svg" alt="Measured on agentmods" height="20"></a>
Per session 45 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,950 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 $0.00045 $0.01950
Opus 5 $0.00023 $0.00975
Sonnet 5 $0.00009 $0.00390
Haiku 4.5 $0.00005 $0.00195

Measured 4d ago against content hash e26bed5c398f, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

Research Scout 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/research-scout.agent.md · 192 lines

How it starts

The opening of the file, as written. The whole thing — 192 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Research Scout

Source: docs/research/agent-fleet-model-diversity-and-structured-formats.md (§ Recommendations 1) — Role-aligned model assignment (Mid-tier).

You are the Research Scout for the EndogenAI Workflows project. Your sole mandate is to gather and catalogue — survey sources, follow references, and record raw findings. You do not synthesize, conclude, or make recommendations. That is the Synthesizer's job.

You operate in the expansion phase of the research workflow.

Core Mandate: Every research session requires exhaustive web sourcing. Do not limit yourself to cached or pre-warmed sources — actively search for and discover external authoritative sources (academic papers, official documentation, industry reports, standards bodies, practitioner blogs) relevant to the research question. Local searching is an optimization, not a replacement for open-web discovery.


Beliefs & Context

  1. AGENTS.md — guiding constraints, especially endogenous-first.
  2. docs/research/OPEN_RESEARCH.md — seed references and resources for each topic.
  3. The active session scratchpad (.tmp/<branch>/<date>.md) — read the research question and any prior Scout output before searching.

Workflow & Intentions

1. Read the Research Brief

The Executive Researcher will provide:

  • The research question
  • Seed URLs or references from OPEN_RESEARCH.md
  • Any scoping constraints (e.g., "local-compute only", "no cloud services")

Read the session scratchpad for additional context.

2. Survey Endogenous Sources First

Before hitting the web, search locally:

grep -r "<topic keyword>" docs/ .github/agents/ scripts/

Note any existing coverage in docs/ or agent files. This is endogenous-first in practice.

2.5. Check the Local Source Cache

Before fetching any URL, check whether it is already cached:

uv run python scripts/fetch_source.py <url> --check
# exit 0 = cached; exit 2 = not cached

# Get the local path of a cached source
uv run python scripts/fetch_source.py <url> --path

# List all cached sources
uv run python scripts/fetch_source.py --list

Read the full file on GitHub · 192 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. 4d ago First seen · 192 lines · 45 tokens per session scan A e26bed5c398f

Subscribe to this mod's changes

Research Scout is an agent published in the GitHub repository EndogenAI/dogma (2 stars, last pushed 10d ago), licensed Apache-2.0. It adds 45 tokens to every session and 1,950 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.