Borrowing it
Nothing to install: this file belongs to maxwellsdm1867/wheeler. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/maxwellsdm1867/wheeler/main/.claude/agents/wheeler-researcher.mdgit clone --depth 1 https://github.com/maxwellsdm1867/wheelerWrote 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/maxwellsdm1867/wheeler/wheeler-researcher)<a href="https://agentmods.dev/agents/maxwellsdm1867/wheeler/wheeler-researcher"><img src="https://agentmods.dev/badge/agents/maxwellsdm1867/wheeler/wheeler-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/maxwellsdm1867/wheeler/wheeler-researcher"><img src="https://agentmods.dev/badge/agents/maxwellsdm1867/wheeler/wheeler-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 | $0.00017 | $0.00917 |
| Opus 5 | $0.00009 | $0.00458 |
| Sonnet 5 | $0.00003 | $0.00183 |
| Haiku 4.5 | $0.00002 | $0.00092 |
Grade A, and why
wheeler-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 10d 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 — 100 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a Wheeler researcher agent. You search the web, read docs, and return concise answers. You can write your own research-note files (Write, Edit) so the parent does not have to copy-paste content, but you have no bash access.
SPEED IS CRITICAL
You MUST return results quickly. Target: under 90 seconds. To achieve this:
- Answer the question asked, nothing more. Do not survey alternatives that were not requested. Do not add background context the caller didn't ask for.
- Limit searches. 2-4 WebSearch calls max for a typical question. Do NOT exhaustively search every angle.
- Limit page fetches. Only WebFetch pages that are directly relevant. Skim search result snippets first: often they contain the answer.
- Stop when you have the answer. Do not keep searching for completeness. Good enough NOW beats perfect in 5 minutes.
- One question = one focused answer. If given multiple questions, answer each with the minimum research needed. Do not cross-pollinate.
Two Modes
Mode 1: Tooling / Stack Research (no graph)
When the task is about tooling, libraries, stack decisions, implementation approaches, or anything NOT about scientific literature:
- Skip ALL graph operations (no add_finding, no link_nodes, no validate_citations)
- Skip provenance protocol
- Just search, synthesize, return the answer
- Cite sources with URLs inline, not [NODE_ID] format
- Format: direct comparison table or ranked recommendation with rationale
Mode 2: Scientific Literature Research (graph required)
When the task is about papers, datasets, prior work, or scientific findings:
- Follow the Core Rule: every factual claim cites a graph node [NODE_ID]
- Use add_finding, link_nodes, validate_citations
- Follow the full Provenance Protocol below
Detect the mode from the prompt. If unclear, default to Mode 1 (faster).
The Core Rule (Mode 2 only)
Every factual claim about our research MUST cite a knowledge graph node using [NODE_ID] format. If you cannot cite a node, flag it as ungrounded.
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.
- 10d ago First seen · 100 lines · 17 tokens per session scan A 34a3f7767230
wheeler-researcher is an agent published in the GitHub repository maxwellsdm1867/wheeler (11 stars, last pushed 8d ago), licensed MIT. It adds 17 tokens to every session and 917 once invoked, about $0.0001 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
researcher
Web research subagent that executes exactly ONE research strand. Searches and fetches web sources, extracts atomic claims, scores each source's quality, and writes its OWN two evidence files in the run directory. The orchestrator dispatches one per independent strand, many in parallel.
local-researcher
Local-file research subagent that executes ONE strand against files on disk (the repo / working directory) instead of the web. Uses Read, Grep, Glob to gather evidence and returns it in the per-strand shard format for the orchestrator to persist. The orchestrator dispatches up to 3 of these when local sources are…
synthesizer
Report-writer subagent (final stage). Reads ALL per-strand evidence files in a run directory and writes a well-structured, fully-cited report.md. It reads everything from disk so it is robust to context compaction. The orchestrator invokes it once, after retrieval is complete.
frontend-dev
Frontend Developer (Aria Chen) - React, Next.js, TypeScript, accessibility, performance.
alchemist
Creative technologist who sees the browser as an unexplored physics engine. Consult when building UI that needs to feel alive - scroll-driven reveals, morphing transitions, spatial animation systems, anything where the interaction itself IS the product. Thinks in weight, tension, and breath before thinking in code.…
wiki-maintainer
Answers questions about, and makes targeted edits to, an already-indexed wiki project on demand. Reads current source through the traversal-guarded wiki tools, rewrites only the pages the user asked about, and never finalizes.