agentic-research-flows

agentic-research-flows is an agent for Claude Code from EndogenAI/dogma. It costs 0 tokens per session (9,470 once invoked), scanned A, original, Apache-2.0.

A review of common multi-agent workflow patterns, including one agent coordinating workers, agents checking and improving results, layered memory, and loading context only when needed.

In plain words
What is it for?
Use it to design research workflows, agent coordination, memory layers, evaluation loops, and on-demand context loading.
Why use it?
It helps explain how to structure research agents and identifies gaps such as weak completion criteria, missing long-term memory, and excessive context loaded at startup.

Agent for Claude Code

Written for Claude Code: a Claude Code subagent (agents/*.md). Also seen: reads .claude/ paths; mentions subagents; mentions Claude Code.

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/agentic-research-flows
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 agentic-research-flows

README.md
[![agentmods](https://agentmods.dev/badge/agents/endogenai/dogma/agentic-research-flows.svg)](https://agentmods.dev/agents/endogenai/dogma/agentic-research-flows)
Your own site
<a href="https://agentmods.dev/agents/endogenai/dogma/agentic-research-flows"><img src="https://agentmods.dev/badge/agents/endogenai/dogma/agentic-research-flows.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 9,470 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 5.1 $0.00000 $0.09470
Opus 5 $0.00000 $0.04735
Sonnet 5 $0.00000 $0.01894
Haiku 4.5 $0.00000 $0.00947

Measured 2d ago against content hash d8a34e5f386b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

agentic-research-flows 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 2d 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.

docs/research/agents/agentic-research-flows.md · 413 lines

How it starts

The opening of the file, as written. The whole thing — 413 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agentic Research Flows

Status: Final (addendum 2026-03-06) Research Question: How do multi-agent systems architect context, orchestration, memory, and tool use for effective research — and what patterns can be directly applied to this project? Date: 2026-03-06


Executive Summary

The literature converges on a small set of durable patterns — orchestrator-workers, evaluator-optimizer loops, tiered memory, and lazy context loading — that are well-validated at production scale. Our current fleet design is broadly correct: the self-loop phase gate maps directly to the evaluator-optimizer pattern, our scratchpad satisfies the ephemeral working memory role, and git history covers the immutable audit trail. The primary gaps are (1) no semantic retrieval layer over episodic/experiential memory, (2) agent prompt files that lack explicit completion criteria and example outputs, and (3) a context loading strategy that pays full cost at session start rather than on demand. The most actionable near-term intervention is a skills-manifest script that enables lazy loading of agent metadata — estimated at a significant token reduction with no new dependencies. The longer-term architectural opportunity is an Agentic File System (AFS) layer, but that should be deferred until the local-compute-first baseline is stable.


2. Hypothesis Validation

The central research question — how do multi-agent systems architect context, orchestration, memory, and tool use for effective research? — was validated against five independent source clusters: Anthropic's production multi-agent research system, the Building Effective Agents taxonomy, the ReAct and Generative Agents academic papers, and local-compute tooling evaluations (Ollama, LM Studio, llama.cpp).

H1 — Orchestrator-workers pattern is the dominant production architecture: Confirmed across all Anthropic cookbook agents and the AWS/community agentic systems. Every production research system uses a delegating orchestrator with bounded subagents. No counter-evidence found.

Read the full file on GitHub · 413 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. 2d ago First seen · 413 lines · 0 tokens per session scan A d8a34e5f386b

Subscribe to this mod's changes

agentic-research-flows is an agent published in the GitHub repository EndogenAI/dogma (2 stars, last pushed 12d ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 9,470 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 2026-09-03.