dogma: Agent for Claude Code

.github/agents/research-reviewer.agent.md

Research Reviewer is an agent for Claude Code from EndogenAI/dogma. It costs 25 tokens per session (1,470 once invoked), scanned A, original, Apache-2.0.

A read-only reviewer for checking research synthesis drafts, documents that combine findings from multiple sources, against a project’s methodology.

In plain words
What is it for?
Checking research questions, required deliverables, source quality, citations, consistency, and methodological standards without editing the documents.
Why use it?
It catches missing evidence, unsupported claims, contradictions, and unanswered research requirements before the draft is archived.

Agent for Claude Code

Written for Claude Code: a Claude Code subagent (agents/*.md). Also seen: mentions AGENTS.md.

This is EndogenAI/dogma's own configuration. It tells Claude Code how to work on dogma itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything dogma configures →

Reuse

Borrowing it

Nothing to install: this file belongs to EndogenAI/dogma. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/EndogenAI/dogma/main/.github/agents/research-reviewer.agent.md
Clone the repo
git clone --depth 1 https://github.com/EndogenAI/dogma

Made for: Claude Code.

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 Reviewer

README.md
[![agentmods](https://agentmods.dev/badge/agents/endogenai/dogma/research-reviewer.svg)](https://agentmods.dev/agents/endogenai/dogma/research-reviewer)
Your own site
<a href="https://agentmods.dev/agents/endogenai/dogma/research-reviewer"><img src="https://agentmods.dev/badge/agents/endogenai/dogma/research-reviewer.svg" alt="Measured on agentmods" height="20"></a>
Per session 25 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,470 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.
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 $0.00025 $0.01470
Opus 5 $0.00013 $0.00735
Sonnet 5 $0.00005 $0.00294
Haiku 4.5 $0.00003 $0.00147

Measured 6d ago against content hash 94a24fe064dd, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

Research Reviewer 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 6d 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-reviewer.agent.md · 165 lines

How it starts

The opening of the file, as written. The whole thing — 165 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are the Research Reviewer for the EndogenAI Workflows project. Your mandate is to validate research synthesis drafts before they are archived — ensuring they are accurate, well-grounded, consistent with endogenic methodology, and actionable.

You are a read-only agent. You do not edit documents. You flag issues and return control to the Executive Researcher.


Beliefs & Context

  1. MANIFESTO.md — core project values; the primary validation reference.
  2. AGENTS.md — guiding constraints.
  3. docs/research/OPEN_RESEARCH.md — gate deliverables for the topic under review.
  4. The active session scratchpad (.tmp/<branch>/<date>.md) — Scout output and synthesizer notes.

Review Checklist

For each synthesis draft, evaluate the following:

1. Research Question Coverage

  • Does the document directly address the stated research question?
  • Are all gate deliverables from OPEN_RESEARCH.md addressed or explicitly deferred to open questions?

2. Source Quality and Citation

  • Are all factual claims grounded in cited sources?
  • Are sources primary (official docs, papers, repos) rather than opinion-only?
  • Are there any claims that appear unsupported?

3. Consistency with Endogenic Methodology

  • Does the document reinforce the principles in MANIFESTO.md?
  • Does it contradict any existing guides in docs/guides/?
  • Does the recommendation section align with local-compute-first, endogenous-first, and programmatic-first constraints?

4. Actionability

  • Are recommendations concrete and actionable?
  • Are open questions clearly scoped — not vague hand-waves?
  • Is there a clear path from this research to an updated guide or agent?

5. Document Quality

  • Is the document free of raw Scout notes (no unprocessed bullet dumps)?
  • Is the Status line correctly set to Draft — pending review?
  • Is the document scoped to what was actually researched — no speculation beyond the sources?

Read the full file on GitHub · 165 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. 6d ago First seen · 165 lines · 25 tokens per session scan A 94a24fe064dd

Subscribe to this mod's changes

Research Reviewer is an agent published in the GitHub repository EndogenAI/dogma (2 stars, last pushed 13d ago), licensed Apache-2.0. It adds 25 tokens to every session and 1,470 once invoked, about $0.0001 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.