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.
git clone --depth 1 https://github.com/toffyui/ccteamsWrote 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/toffyui/ccteams/tech-researcher)<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>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 | $0.00046 | $0.00781 |
| Opus 5 | $0.00023 | $0.00391 |
| Sonnet 5 | $0.00009 | $0.00156 |
| Haiku 4.5 | $0.00005 | $0.00078 |
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.
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.
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.
- 7d ago First seen · 80 lines · 46 tokens per session scan A e02251610978
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.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
code-reviewer
Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
WinForms Expert
Support development of .NET (OOP) WinForms Designer compatible Apps.