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.
npx agentmods add agents/endogenai/dogma/agentic-research-flowsgit clone --depth 1 https://github.com/EndogenAI/dogmaWrote 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.
[](https://agentmods.dev/agents/endogenai/dogma/agentic-research-flows)<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>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.
| Model | Per session | Once 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 |
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.
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.
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.
- 2d ago First seen · 413 lines · 0 tokens per session scan A d8a34e5f386b
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.
Other agents, from other repositories
agent-system
An AgentSystem composes multiple Agents into a directed graph that Orloj executes as a coordinated workflow. The graph defines how messages flow between agents during task execution.
acx-implementer
AgentCortex /implement phase executor. Use when delegating implementation work that must follow agentic-os gates, evidence requirements, and skill injection.
acx-tester
AgentCortex /test phase executor. Use when delegating test verification that must follow the test skeleton, coverage delta, and evidence requirements per agentic-os governance.
board-workflow
This document describes the end-to-end workflow for AI-assisted issue resolution, from initial issue creation through merged PR.
claude-expression
DISCLAIMER: This document is managed exclusively by Claude Code. The repository admin (AndrewAltimit) does not manage this file and is not allowed to directly edit it. Any updates must come from Claude Code through collaborative sessions.
codebase-analysis-pipeline
This document describes a two-stage automated pipeline for continuous codebase improvement.