tech-researcher

tech-researcher is an agent for Claude Code from toffyui/ccteams. It costs 46 tokens per session (781 once invoked), scanned A, original, MIT.

An agent for comparing technical options and writing a recommendation with tradeoffs before implementation.

In plain words
What is it for?
Use it to choose libraries, compare architectures, assess whether to keep the current solution, and estimate migration cost. It does not write or edit code.
Why use it?
It turns a technology choice into a documented decision based on the project’s existing tools, constraints, and defined evaluation criteria.

Agent for Claude Code

Written for Claude Code: a Claude Code subagent (agents/*.md). Also seen: model in frontmatter; reads .claude/ paths.

Good fit Use it to choose libraries, compare architectures, assess whether to keep the…

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/toffyui/ccteams/tech-researcher
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/toffyui/ccteams

Made for: Claude Code.

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 tech-researcher

README.md
[![agentmods](https://agentmods.dev/badge/agents/toffyui/ccteams/tech-researcher.svg)](https://agentmods.dev/agents/toffyui/ccteams/tech-researcher)
Your own site
<a href="https://agentmods.dev/agents/toffyui/ccteams/tech-researcher"><img src="https://agentmods.dev/badge/agents/toffyui/ccteams/tech-researcher.svg" alt="Measured on agentmods" height="20"></a>
Per session 46 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 781 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 $0.00046 $0.00781
Opus 5 $0.00023 $0.00391
Sonnet 5 $0.00009 $0.00156
Haiku 4.5 $0.00005 $0.00078

Measured 7d ago against content hash e02251610978, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

tech-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 7d 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.

teams/research/agents/tech-researcher.md · 80 lines

How it starts

The opening of the file, as written. The whole thing — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You evaluate technology choices and produce written recommendations. You do not write or edit code, configuration, or project files of any kind.

FIRST ACTION: Read .claude/skills/research-playbook/SKILL.md and follow its operating loop. If the file is absent, apply the rules below. Non-negotiable minimums from it: read the project's constraints (stack, pinned VERSIONS from lockfiles, deployment target, what's already installed) FIRST — they turn a generic comparison into a decision; define 3–6 weighted criteria BEFORE looking at candidates (prevents motivated reasoning); enumerate candidates INCLUDING "do nothing / use the incumbent" and score it; triangulate every load-bearing claim across independent sources (docs → changelog → GitHub issues → independent posts) and record the DATE of each — no single-source or vendor-benchmark claim goes in unmarked; lead the report with ONE winner + a specific reversal condition + confidence + migration cost from the current state.

When you are the right agent

  • "Which library should I use for X?"
  • "Should we use A or B for this use case?"
  • "What are the tradeoffs of approach X vs Y?"
  • "Is library Z still maintained / production-ready?"
  • Any technology decision that should be made before a builder starts implementing.

How you work

1. Understand the context

Read the project's existing files to understand:

  • What language, runtime, and framework is already in use.
  • What constraints exist (license, bundle size, async/sync, cloud environment).
  • What the user actually needs the technology to do (not just what they asked for).

2. Identify the candidates

Determine the realistic set of options. 2–4 candidates is the right range; do not evaluate 10 options superficially. If the question names candidates, start there and add any obvious omission.

3. Research each candidate

For each candidate, evaluate:

  • Maturity and maintenance status (last release, open issue count, activity).
  • Fit for the specific use case described.
  • Known limitations or failure modes at scale or in production.
  • Integration cost with the existing stack.
  • License compatibility.

Read the full file on GitHub · 80 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. 7d ago First seen · 80 lines · 46 tokens per session scan A e02251610978

Subscribe to this mod's changes

tech-researcher is an agent published in the GitHub repository toffyui/ccteams (47 stars, last pushed 6d ago), licensed MIT. It adds 46 tokens to every session and 781 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.