em-researcher

em-researcher is an agent for Claude Code from iamcxa/kc-claude-plugins. It costs 52 tokens per session (565 once invoked), scanned A, original, MIT.

A research agent for checking whether libraries, versions, and APIs can support a proposed software change. It gathers evidence from documentation and other technical sources and reports confidence for each finding.

In plain words
What is it for?
Use it to answer focused compatibility and API questions during engineering triage and to provide source-backed recommendations.
Why use it?
It helps resolve technical uncertainty before implementation guidance is written, reducing decisions based on unsupported assumptions about dependencies or APIs.

Agent for Claude Code

Written for Claude Code: ${CLAUDE_PLUGIN_ROOT} variable. Also seen: model in frontmatter.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the kc-team-ops plugin — 8 skills, 3 agents shipped together

Good fit Use it to answer focused compatibility and API questions during engineering triage and to provide source-backed recommendations.

Compare 6 agents from other repositories ↓
Install

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.

Claude Code
/plugin marketplace add iamcxa/kc-claude-plugins
Claude Code
/plugin install kc-team-ops

Made for: Claude Code.

Or install kc-team-ops, the plugin that ships this one along with the rest of its 8 skills, 3 agents.

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 em-researcher

README.md
[![agentmods](https://agentmods.dev/badge/agents/iamcxa/kc-claude-plugins/em-researcher/github.svg)](https://agentmods.dev/agents/iamcxa/kc-claude-plugins/em-researcher)
Your own site
<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.

agentmods 80×15 button for em-researcher

Your own site · 80×15
<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>
Per session 52 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 565 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.

ModelPer sessionOnce 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

Measured 6d ago against content hash 326c4b8aeec3, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

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.

kc-team-ops/agents/em-researcher.md · 63 lines

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"

Read the full file on GitHub · 63 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. 6d ago First seen · 63 lines · 52 tokens per session scan A 326c4b8aeec3

Subscribe to this mod's changes

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.