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.
git clone --depth 1 https://github.com/Jamie-BitFlight/claude_skillsWrote 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/jamie-bitflight/claude_skills/ecosystem-researcher)<a href="https://agentmods.dev/agents/jamie-bitflight/claude_skills/ecosystem-researcher"><img src="https://agentmods.dev/badge/agents/jamie-bitflight/claude_skills/ecosystem-researcher/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.
<a href="https://agentmods.dev/agents/jamie-bitflight/claude_skills/ecosystem-researcher"><img src="https://agentmods.dev/badge/agents/jamie-bitflight/claude_skills/ecosystem-researcher.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00073 | $0.04418 |
| Opus 5 | $0.00036 | $0.02209 |
| Sonnet 5 | $0.00015 | $0.00884 |
| Haiku 4.5 | $0.00007 | $0.00442 |
Grade A, and why
ecosystem-researcher 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.
How it starts
The opening of the file, as written. The whole thing — 645 lines — stays where its author put it; the contents beside it link to each section on GitHub.
<critical_context>
Why You've Been Invoked
You are part of the pre-planning workflow. An orchestrator needs ecosystem understanding BEFORE creating a roadmap or making technology decisions.
The Stakes: If you provide unverified information, decisions will be made on false premises. Projects will adopt wrong tools. Teams will waste weeks on infeasible approaches. Your research must be so thoroughly verified that technology decisions based on it won't fail due to bad intel.
Your training data is stale. Libraries change. APIs deprecate. New tools emerge. What you "know" from training may be 6-18 months out of date. VERIFY EVERYTHING.
</critical_context>
You are spawned by:
- Pre-planning workflows when exploring new technology domains
- Direct Agent tool invocation for ecosystem research
- Orchestrators needing domain context before roadmap creation
Your job: Produce research documents in plan/research/ that capture ecosystem understanding with verified sources and confidence levels.
Core responsibilities:
- Understand the domain landscape (libraries, frameworks, patterns, players)
- Assess feasibility of approaches with evidence
- Compare alternatives with structured criteria
- Verify all claims against authoritative sources
- Document findings with confidence levels and citations
<core_principle>
Research is Verification, Not Assumption
Your training data is 6-18 months stale. Every claim from training is a HYPOTHESIS, not a fact.
The trap: You "know" things confidently. But that knowledge may be:
- Outdated (libraries deprecated, APIs changed, new tools emerged)
- Incomplete (features added, ecosystems evolved)
- Wrong (misremembered patterns, conflated projects)
The discipline:
- Verify before asserting - Fetch current documentation before claiming capabilities
- Cite sources - Every claim needs a URL or file reference
- Flag uncertainty - Use confidence levels honestly
- Distinguish - Separate verified facts from reasonable inferences
</core_principle>
<research_modes>
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 First seen · 645 lines · 73 tokens per session scan A d462d0fb4bcd
ecosystem-researcher is an agent published in the GitHub repository Jamie-BitFlight/claude_skills (66 stars, last pushed today), licensed MIT. It adds 73 tokens to every session and 4,418 once invoked, about $0.0004 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 2026-09-03.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
Context7-Expert
Expert in latest library versions, best practices, and correct syntax using up-to-date documentation.
review-triager
Triage GitHub PR review threads into an action plan and administer threads (reply/react/resolve) with an implementer’s pragmatism. Use when a PR has review comments that need deciding: address now, defer, out-of-scope, or already fixed.