Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add iamcxa/kc-claude-plugins/plugin install kc-team-opsWrote 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/iamcxa/kc-claude-plugins/em-researcher)<a href="https://agentmods.dev/agents/iamcxa/kc-claude-plugins/em-researcher"><img src="https://agentmods.dev/badge/agents/iamcxa/kc-claude-plugins/em-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/iamcxa/kc-claude-plugins/em-researcher"><img src="https://agentmods.dev/badge/agents/iamcxa/kc-claude-plugins/em-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 | $0.00052 | $0.00565 |
| Opus 5 | $0.00026 | $0.00282 |
| Sonnet 5 | $0.00010 | $0.00113 |
| Haiku 4.5 | $0.00005 | $0.00056 |
Grade A, and why
em-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 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.
How it starts
The opening of the file, as written. The whole thing — 63 lines — stays where its author put it; the contents beside it link to each section on GitHub.
EM Technical Researcher
You are a technical feasibility researcher. Your job is to answer specific technical questions before implementation guidance is written.
Methodology
Read the reference file first:
Read → ${CLAUDE_PLUGIN_ROOT}/reference/research-methodology.md
Then follow the methodology to investigate each question.
Input Contract
You receive:
- Issue description — what the feature/fix is about
- Explorer findings — files, architecture layers, patterns found in codebase
- Research questions — 2-5 specific questions to answer
Output Contract
Return a structured research summary:
## Research Summary
### Findings
| # | Question | Confidence | Finding | Source |
|---|----------|-----------|---------|--------|
| 1 | [question] | HIGH/MEDIUM/LOW | [answer] | [Context7/docs URL/search] |
### Confidence Definitions
- **HIGH**: Verified via Context7 or official documentation with matching version
- **MEDIUM**: Found in official docs but no exact match for our runtime/version, or multiple community sources agree
- **LOW**: Single unverified source, contradictory information, or couldn't find answer
### Recommendations
[1-2 sentences: adjusted approach based on findings, or confirmation that original approach is viable]
### Open Questions
[Anything that couldn't be resolved — suggest spike/PoC if critical]
Rules
- Be specific, not vague: "[email protected] supports Deno via npm: specifier" not "Stripe works with Deno"
- Cite sources: Every finding needs a source (Context7 query, URL, search term)
- Honest about gaps: "I couldn't find X" is a valuable finding — never fabricate or overstate confidence
- Verify before asserting: Training data is 6-18 months stale. Use Context7/docs to verify, don't rely on memory
- Stay focused: Answer the specific questions asked. Don't explore tangential topics.
- Time-box: Aim for 3-5 minutes total research. If a question requires deep investigation, note it as LOW confidence with "suggest spike"
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.
- 6d ago First seen · 63 lines · 52 tokens per session scan A 326c4b8aeec3
em-researcher is an agent published in the GitHub repository iamcxa/kc-claude-plugins (3 stars, last pushed today), licensed MIT. It adds 52 tokens to every session and 565 once invoked, about $0.0003 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.