researcher

researcher is an agent for coding agents from ariaxhan/kernel-claude. It costs 39 tokens per session (1,626 once invoked), scanned A, original, MIT.

A research agent that investigates existing solutions, software packages, common problems, and recommended practices before implementation begins.

In plain words
What is it for?
Use it to research unfamiliar technologies, compare packages or integrations, find documented pitfalls, and record findings before coding.
Why use it?
It helps avoid choosing unsuitable tools, repeating known mistakes, or building something that already exists.

Agent

Part of the kernel plugin — 28 skills, 13 agents, 9 hooks shipped together

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.

agentmods
npx agentmods add agents/ariaxhan/kernel-claude/researcher
Clone the repo
git clone --depth 1 https://github.com/ariaxhan/kernel-claude

Or install kernel, the plugin that ships this one along with the rest of its 28 skills, 13 agents, 9 hooks.

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 researcher

README.md
[![agentmods](https://agentmods.dev/badge/agents/ariaxhan/kernel-claude/researcher.svg)](https://agentmods.dev/agents/ariaxhan/kernel-claude/researcher)
Your own site
<a href="https://agentmods.dev/agents/ariaxhan/kernel-claude/researcher"><img src="https://agentmods.dev/badge/agents/ariaxhan/kernel-claude/researcher.svg" alt="Measured on agentmods" height="20"></a>
Per session 39 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,626 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00039 $0.01626
Opus 5 $0.00019 $0.00813
Sonnet 5 $0.00008 $0.00325
Haiku 4.5 $0.00004 $0.00163

Measured 4d ago against content hash 73e8cb475366, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

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 4d 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.

agents/researcher.md · 180 lines

How it starts

The opening of the file, as written. The whole thing — 180 lines — stays where its author put it; the contents beside it link to each section on GitHub.

investment: research_time: 10-20% of task payoff: prevents 80% of bugs skip_research: reinvent wheels, repeat mistakes

<on_start> agentdb inject-context researcher </on_start>

<skill_load> MANDATORY before searching: Read skills/build/SKILL.md (solution exploration, pitfalls-first). Reference: skills/build/reference/build-research.md. Reference: _meta/research/ai-code-anti-patterns.md </skill_load>

<startup_reads> Existing research in _meta/research/: don't duplicate prior work. Patterns from AgentDB: known tech preferences, past evaluations. Contract (if exists): what specific questions need answering. </startup_reads>

anti_pattern_search_first:

  1. "{tech} not working"
  2. "{tech} gotchas"
  3. "{tech} issues 2025 2026" THEN:
  4. "{tech} best practices 2025 2026"
  5. official docs

<ask_user> Use AskUserQuestion when: multiple viable packages/approaches found with similar tradeoffs Ask: "Found {N} viable options: {list}. Preference, or should I pick simplest?" Options: pick simplest, I prefer {option}, show full comparison </ask_user>

<source_hierarchy>

  1. Official docs (authoritative).
  2. GitHub issues, closed with solutions (real problems, real fixes).
  3. Source code (truth when docs lie).
  4. Stack Overflow, high-vote accepted (common patterns).
  5. Blog posts (check dates; >1yr old = suspect). </source_hierarchy>

Read the full file on GitHub · 180 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. 4d ago First seen · 180 lines · 39 tokens per session scan A 73e8cb475366

Subscribe to this mod's changes

researcher is an agent published in the GitHub repository ariaxhan/kernel-claude (12 stars, last pushed today), licensed MIT. It adds 39 tokens to every session and 1,626 once invoked, about $0.0002 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 2026-08-30.