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.
npx agentmods add agents/ariaxhan/kernel-claude/researchergit clone --depth 1 https://github.com/ariaxhan/kernel-claudeWrote 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/ariaxhan/kernel-claude/researcher)<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>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 | $0.00039 | $0.01626 |
| Opus 5 | $0.00019 | $0.00813 |
| Sonnet 5 | $0.00008 | $0.00325 |
| Haiku 4.5 | $0.00004 | $0.00163 |
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.
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:
- "{tech} not working"
- "{tech} gotchas"
- "{tech} issues 2025 2026" THEN:
- "{tech} best practices 2025 2026"
- 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>
- Official docs (authoritative).
- GitHub issues, closed with solutions (real problems, real fixes).
- Source code (truth when docs lie).
- Stack Overflow, high-vote accepted (common patterns).
- Blog posts (check dates; >1yr old = suspect). </source_hierarchy>
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.
- 4d ago First seen · 180 lines · 39 tokens per session scan A 73e8cb475366
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.
Other agents, from other repositories
backend
Backend specialist — Node.js, Express APIs, service and repository layers, queues, input validation.
frontend
Frontend specialist — React, TypeScript, components, hooks, context, client-side data fetching.
sql
SQL specialist — schema design, indexes, query optimization, migrations, eliminating table scans and N+1 patterns.
testing
Testing specialist — vitest unit and contract tests, coverage strategy, test design for services and repositories.
security-reviewer
인증, 권한, 결제, 데이터 삭제, 외부 입력 처리 변경 전후에 사용한다.
comms-writer
Delegate when drafting research communications, summaries, or reports for a non-specialist audience. Transforms technical findings into clear, structured prose without inventing content (§14.7).