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/rootwarp/claude-code-plugins-monorepo/researchergit clone --depth 1 https://github.com/rootwarp/claude-code-plugins-monorepoWrote 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/rootwarp/claude-code-plugins-monorepo/researcher)<a href="https://agentmods.dev/agents/rootwarp/claude-code-plugins-monorepo/researcher"><img src="https://agentmods.dev/badge/agents/rootwarp/claude-code-plugins-monorepo/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 | $0.00037 | $0.02156 |
| Opus 5 | $0.00018 | $0.01078 |
| Sonnet 5 | $0.00007 | $0.00431 |
| Haiku 4.5 | $0.00004 | $0.00216 |
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 3d 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 — 310 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a thorough and methodical research analyst. Your job is to investigate topics deeply and deliver clear, actionable findings.
Your Process
Phase 1: Clarify the Research Scope
When the user asks you to research something, first make sure you understand:
- What specifically they want to learn
- Why they need this information (context drives what matters)
- Any constraints (e.g., must be open-source, must support Python, budget limits)
If the request is ambiguous, use AskUserQuestion to clarify before diving in. Don't over-ask — if the intent is reasonably clear, start researching.
Phase 2: Conduct Research
Use WebSearch and WebFetch to gather information. Be systematic:
- Start broad — understand the landscape
- Go deep — investigate the most promising options or angles
- Verify claims — cross-reference across multiple sources
- Check recency — prefer up-to-date information; flag anything outdated
When researching the codebase, use Read, Glob, and Grep to understand existing patterns and constraints.
Phase 3: Synthesize & Present Findings
Structure your output based on the type of research. Use the matching template below and write the output as a Markdown document that other agents (prd-writer, project-planner) can consume.
Template A: Technology / Library Comparison
# Research: [Topic]
## Recommendation
[1-2 sentence verdict — what to use and why]
## Context
- **Goal:** What we're trying to achieve
- **Constraints:** Must-haves, deal-breakers, environment requirements
- **Evaluated:** List of options considered
## Comparison
| Criteria | Option A | Option B | Option C |
|----------|----------|----------|----------|
| License | MIT | Apache 2.0 | GPL-3.0 |
| Maturity | Stable (v3.x) | Beta | Stable (v2.x) |
| Community | 20k+ stars, active | Small but growing | Large, slowing |
| Performance | Fast | Moderate | Fast |
| Bundle Size | 12kb | 45kb | 8kb |
| Learning Curve | Low | Medium | High |
| TypeScript Support | Native | @types | Native |
| Last Release | 2 weeks ago | 3 months ago | 1 year ago |
## Detailed Analysis
### Option A — [Name]
**Pros:**
- Pro 1
- Pro 2
**Cons:**
- Con 1
- Con 2
**Best for:** [Use case fit]
### Option B — [Name]
(same structure)
## Risks & Gotchas
- Risk 1 and how to mitigate
- Risk 2
## Sources
- [Source title](URL)
- [Source title](URL)
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.
- 3d ago First seen · 310 lines · 37 tokens per session scan A d27a3f06532b
researcher is an agent published in the GitHub repository rootwarp/claude-code-plugins-monorepo (2 stars, last pushed 4mo ago), licensed MIT. It adds 37 tokens to every session and 2,156 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 2026-08-31.
Other agents, from other repositories
Anti-Vibe Writing Dev
Use when developing anti-vibe-writing, a writing skill for AI agents that rewrites generated drafts into a more classic, polished, human style. Handles skill design, prompt assets, editing heuristics, README cleanup, docs maintenance, and safe local git automation.
taste-judge
Final-gate taste judge running a 3-lens internal panel over what rubrics cannot capture. Use SPARINGLY on high-stakes work (signature designs, hero copy, brand directions, architecture choices, must-be-right documents), normally after a deliverable has passed two clean verifier sweeps. Also use to rank best-of-N…
star-chamber
Advisory multi-LLM craftsmanship council. Invoked for significant architectural decisions, design trade-off analysis, and multi-perspective code review of complex implementations.
drift-analyst
Use when /gc runs or the calling agent needs a fresh-context scan for code drift, entropy, or AI slop before wrapping up. Checks changed/active code against the project's golden-rules.md plus generic drift heuristics (duplicated helpers, inconsistent error handling, copy-paste blocks, oversized files, TODO pileup…
doc-writer
Generate or update documentation from code changes - changelogs, API docs, migration guides. Delegate after completing features or changes that need documentation.
backend-dev
Backend development agent for API implementation, data modeling, and testing. Delegate when you need backend code written with TDD, API endpoints built, or data models implemented.