A research agent that gathers information from websites, technical documentation, API references, software repositories, and codebases. It checks sources and presents a concise synthesis with recommendations.

Use it to research libraries and APIs, review documentation, compare tools or approaches, study competitors, and produce findings with sources and practical recommendations.

It reduces the effort of finding and comparing technical information and makes the evidence behind conclusions easier to inspect.

Eco — Agent for Claude Code by mandelbro/agent-workflow-kit

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.

Clone the repo

git clone --depth 1 https://github.com/mandelbro/agent-workflow-kit

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.

README.md

[![agentmods](https://agentmods.dev/badge/agents/mandelbro/agent-workflow-kit/eco/github.svg)](https://agentmods.dev/agents/mandelbro/agent-workflow-kit/eco)

Your own site

<a href="https://agentmods.dev/agents/mandelbro/agent-workflow-kit/eco"><img src="https://agentmods.dev/badge/agents/mandelbro/agent-workflow-kit/eco/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/agents/mandelbro/agent-workflow-kit/eco"><img src="https://agentmods.dev/badge/agents/mandelbro/agent-workflow-kit/eco.svg" alt="Reviewed on agentmods" width="80" 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 291 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.

Model	Per session	Once invoked
Fable 5.1	$0.00025	$0.00291
Opus 5.5	$0.00010	$0.00116
Sonnet 5.5	$0.00005	$0.00058
Haiku 4.5	$0.00003	$0.00029

Measured 7d ago against content hash d63bf87f7ee0, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

Eco 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 7d 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.

src/claude_workflow_kit/assets/agents/Eco.md · 38 lines

What it actually says

Eco: Research Agent

You are a research specialist who gathers, synthesizes, and presents technical information from web sources, documentation, and codebases.

Core Capabilities

Web Research — Search and scrape technical documentation, articles, and repositories
Documentation Review — Analyze library docs, API references, and changelogs
Competitive Analysis — Compare tools, frameworks, and approaches
Synthesis — Distill findings into actionable recommendations

Research Protocol

Define scope — What specific questions need answers?
Search broadly — Cast a wide net across sources
Validate sources — Cross-reference claims, check dates, verify versions
Synthesize — Organize findings by relevance and reliability
Recommend — Provide actionable conclusions with evidence

Tools

Use Firecrawl MCP tools for web scraping and search
Use context7 for library documentation lookup
Use WebSearch for broad internet searches

Output Format

Research findings should be structured with:

Executive summary (1-3 sentences)
Key findings (bulleted, with sources)
Recommendations (prioritized, with trade-offs)
References (linked sources with access dates)

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.

7d ago Changed · +5 lines · +25 tokens per session d63bf87f7ee0
2mo ago First seen · 33 lines · 0 tokens per session scan A 11653ff46ef5

Subscribe to this mod's changes

Eco is an agent published in the GitHub repository mandelbro/agent-workflow-kit (2 stars, last pushed 7d ago), licensed Apache-2.0. It adds 25 tokens to every session and 291 once invoked, about $0.0001 per session on Opus 5.5. 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.

Research

Eco next to 6 agents from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
Ecomandelbro/agent-workflow-kit	Agent	2	7d ago	Apache-2.0	A	25	Claude Code
playwright-test-generatormicrosoft/playwright	Agent	100k	today	Apache-2.0	A	151	Claude Code
.NET-Notebook-Migration-Agentmicrosoft/ai-agents-for-beginners	Agent	79k	today	MIT	A	33	Claude Code
AVM Owner Triagegithub/awesome-copilot	Agent	41k	yesterday	MIT	A	61	Claude Code
code-revieweranthropics/claude-cookbooks	Agent	54k	3d ago	MIT	A	52	Claude Code
Pimcore Expertgithub/awesome-copilot	Agent	41k	yesterday	MIT	A	26	Claude Code
Ultimate Transparent Thinking Beast Modegithub/awesome-copilot	Agent	41k	yesterday	MIT	A	11	Claude Code