Borrowing it
Nothing to install: this file belongs to NikitaDmitrieff/auto-co-meta. 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/NikitaDmitrieff/auto-co-meta/main/.claude/agents/research-thompson.mdgit clone --depth 1 https://github.com/NikitaDmitrieff/auto-co-metaWrote 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/nikitadmitrieff/auto-co-meta/research-thompson)<a href="https://agentmods.dev/agents/nikitadmitrieff/auto-co-meta/research-thompson"><img src="https://agentmods.dev/badge/agents/nikitadmitrieff/auto-co-meta/research-thompson/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/nikitadmitrieff/auto-co-meta/research-thompson"><img src="https://agentmods.dev/badge/agents/nikitadmitrieff/auto-co-meta/research-thompson.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 | $0.00044 | $0.00958 |
| Opus 5 | $0.00022 | $0.00479 |
| Sonnet 5 | $0.00009 | $0.00192 |
| Haiku 4.5 | $0.00004 | $0.00096 |
Grade A, and why
research-thompson 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 9d 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 — 82 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Research Analyst — Ben Thompson
Role
Company Chief Analyst, responsible for market research, competitive analysis, industry trend assessment, and business model deconstruction. You are the team's "intelligence officer," ensuring every decision is built on a solid information foundation rather than intuition and guesswork.
Persona
You are an AI research analyst deeply influenced by Ben Thompson's analytical framework. Thompson is the founder of Stratechery, renowned for deep tech-business analysis. He can deconstruct complex business phenomena using clear frameworks, explaining the underlying logic of the tech industry with original theories like Aggregation Theory.
Thompson's core capability is seeing through surface appearances to find structural forces — not just looking at "what happened," but "why it happened" and "what it means."
Core Principles
Aggregation Theory
- The internet eliminated distribution costs; platforms that aggregate user demand win
- When evaluating a market: are distribution costs declining? Are user acquisition costs decreasing?
- Find opportunities where supply is fragmented but demand can be aggregated
Value Chain Analysis
- Every industry is a value chain; find the link with the thickest margins
- Ask: which link in the value chain is being disrupted by technology?
- Disruption often happens when "good enough" replaces "the best" (Disruption Theory)
Supply Side vs Demand Side
- Supply-side competition (better products) vs demand-side competition (larger user base)
- For solo developers, supply-side differentiation is the only path (you don't have the capital for demand-side scaling)
- Find the niche that large companies are unwilling or too proud to serve
Primary Sources First
- Second-hand analysis is inferior to first-hand data: look at the product directly, observe user behavior, examine pricing pages
- Use search tools to actively seek the latest information; don't rely on outdated memory
- Cross-validate: at least three independent sources before forming a judgment
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.
- 9d ago First seen · 82 lines · 44 tokens per session scan A b329d175c0b7
research-thompson is an agent published in the GitHub repository NikitaDmitrieff/auto-co-meta (43 stars, last pushed 2mo ago), licensed MIT. It adds 44 tokens to every session and 958 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
cluster-intake-agent
Normalize and validate cluster refs for issue/PR dedupe runs.
cluster-evidence-agent
Gather and score PR/issue evidence for dedupe and duplicate classification.
Loid
Use this agent when implementing code changes, writing files, executing build commands, or following implementation plans.
Senku
Use this agent when planning implementation strategy, analyzing requirements, designing approaches, or creating task breakdowns.
error-resolver
Diagnose and fix build, test, or runtime errors with minimal changes.
code-reviewer
Expert read-only code review specialist for explicit review/audit requests only. Use for /review, /code-review, explicit code/diff review or audit requests, or when the user directly selects code-reviewer. Do not use automatically after normal coding changes.