researcher-tech

researcher-tech is an agent for Claude Code from Hayes-Zhang/deep-research. It costs 32 tokens per session (1,541 once invoked), scanned A, original, MIT.

A research role focused on the technical design of software systems, including technology choices, APIs, open-source projects, frameworks, and performance. It produces findings that another team member can combine into a larger research report.

In plain words
What is it for?
Use it to compare technology stacks and frameworks, examine API designs, find reusable open-source projects, and identify likely performance bottlenecks.
Why use it?
It reduces the work of comparing implementation options and finding technical evidence. It also gives architecture questions a dedicated review instead of mixing them with product or user research.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: model in frontmatter; reads .claude/ paths.

Part of the deep-research plugin — 1 command, 8 agents shipped together

Good fit Use it to compare technology stacks and frameworks, examine API designs, find reusable open-source projects, and identify likely performance bottlenecks.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/hayes-zhang/deep-research/researcher-tech
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.

Clone the repo
git clone --depth 1 https://github.com/Hayes-Zhang/deep-research

Made for: Claude Code.

Or install deep-research, the plugin that ships this one along with the rest of its 1 command, 8 agents.

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-tech

README.md
[![agentmods](https://agentmods.dev/badge/agents/hayes-zhang/deep-research/researcher-tech/github.svg)](https://agentmods.dev/agents/hayes-zhang/deep-research/researcher-tech)
Your own site
<a href="https://agentmods.dev/agents/hayes-zhang/deep-research/researcher-tech"><img src="https://agentmods.dev/badge/agents/hayes-zhang/deep-research/researcher-tech/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.

agentmods 80×15 button for researcher-tech

Your own site · 80×15
<a href="https://agentmods.dev/agents/hayes-zhang/deep-research/researcher-tech"><img src="https://agentmods.dev/badge/agents/hayes-zhang/deep-research/researcher-tech.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 32 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,541 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00032 $0.01541
Opus 5 $0.00016 $0.00771
Sonnet 5 $0.00006 $0.00308
Haiku 4.5 $0.00003 $0.00154

Measured 9d ago against content hash 7be5f0f1b674, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

researcher-tech 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.

agents/researcher-tech.md · 169 lines

How it starts

The opening of the file, as written. The whole thing — 169 lines — stays where its author put it; the contents beside it link to each section on GitHub.

🔵 Technical Architecture Researcher

You are a senior software architect and technical researcher. Your job is to investigate the given topic from the technical implementation & architecture angle and produce evidence-backed findings the team lead can synthesize with six other perspectives.

Output language: Match the user's question. If they asked in Chinese, write your report in Chinese; if in English, write in English. The choice is theirs, not yours.

Core responsibilities

  • Architecture choices — What tech stack(s) make sense? What are the architectural options?
  • API design patterns — What are the relevant API design best practices?
  • Open-source implementations — What open-source projects can be referenced or directly used?
  • Framework / library comparisons — Trade-offs between options
  • Performance considerations — Where are the bottlenecks? How to optimize?

Search strategy

Default: prioritize English sources. Signal density for architecture, open-source ecosystems, framework discussions, and benchmarks is substantially higher in English than in any other language.

Primary sources (always start here)

  1. GitHub — open-source implementations, trending projects, star/usage signals
  2. Stack Overflow — technical discussions, common-issue resolutions
  3. Official docs & engineering blogs — first-hand authoritative material
  4. High-quality technical writing — dev.to, Medium, InfoQ (English), individual engineer blogs (e.g., Simon Willison, Will Larson)
  5. Conference talks — KubeCon, StrangeLoop, QCon, RustConf, JSConf — recorded and slides

Supplement with Chinese sources only when

  • The question is explicitly about Chinese-origin frameworks / tools (e.g., 国产数据库 TiDB, MegEngine, PaddlePaddle, 字节跳动 ByConity)
  • You need primary Chinese technical material (Chinese engineering team's first-hand writing on their own product)
  • A Chinese team has open-sourced something with no English equivalent

Then go to: 字节跳动技术团队 / 阿里云开发者 / 腾讯技术 / 美团技术 official blogs, InfoQ 中文 (when covering original Chinese content), 掘金 (when authored by the original engineer). Skip translation aggregators.

Read the full file on GitHub · 169 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. 9d ago First seen · 169 lines · 32 tokens per session scan A 7be5f0f1b674

Subscribe to this mod's changes

researcher-tech is an agent published in the GitHub repository Hayes-Zhang/deep-research (4 stars, last pushed 3mo ago), licensed MIT. It adds 32 tokens to every session and 1,541 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.

Related

Other agents, from other repositories

plan-creation-eng-lead

Engineering and Delivery Lead for implementation planning. Produces work breakdown structures, effort estimates, dependency graphs, milestones, parallel opportunities, and risk registers. Use when you need structured delivery planning for any implementation topic.

QBall-Inc/the-bulwark · 48 tokens

product-ideation-segment-analyzer

Identifies target user segments, develops detailed personas using Jobs-to-be-Done framework, estimates willingness to pay, and refines TAM/SAM/SOM by segment. Reads competitive analysis output from logs/. Use when the orchestrator needs target user segment profiles from competitive data.

QBall-Inc/the-bulwark · 63 tokens

product-ideation-market-researcher

Researches market size, growth trends, key players, regulatory landscape, and technology enablers for a product idea using web sources. Produces evidence-based market assessment with TAM/SAM/SOM estimates. Use when the orchestrator needs market landscape data for a product idea.

QBall-Inc/the-bulwark · 64 tokens

skill-eval-grader

Artifact-based grader for subjective skill evaluations. Reads evidence files (generated SKILL.md, templates, run traces) against a rubric and returns PASS/FAIL with structured reasoning. Used by grade.ts for fuzzy assertions where deterministic checks cannot apply.

QBall-Inc/the-bulwark · 53 tokens

csharp-reviewer

C#-specific code reviewer. Audits for .NET patterns, async/await correctness, LINQ efficiency, IDisposable compliance, and security vulnerabilities.

KevinZai/commander · 35 tokens

implementer

Feature-sized coding work where the decisions live inside the task - multi-file changes, refactors, end-to-end implementation from a spec. Used by senior-fable mode for the code the lead specifies but does not type. Not for mechanical edits with an obvious diff, and not for open-ended investigation.

AndyShaman/senior-fable · 63 tokens