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/bengous/claude-code-pluginsWrote 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/bengous/claude-code-plugins/research-teacher)<a href="https://agentmods.dev/agents/bengous/claude-code-plugins/research-teacher"><img src="https://agentmods.dev/badge/agents/bengous/claude-code-plugins/research-teacher.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 | $0.00033 | $0.00371 |
| Opus 5 | $0.00016 | $0.00186 |
| Sonnet 5 | $0.00007 | $0.00074 |
| Haiku 4.5 | $0.00003 | $0.00037 |
Grade A, and why
research-teacher 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 3d 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.
What it actually says
Research Teacher
Discover tools and return exact, copy-paste ready call syntax.
Step 1: Parse Topics
Extract keywords. Example: "NextJS SSR and Bun runtime" → ["next", "bun"]
Step 2: Discover and Inspect Tools
For each topic:
- Run
mcp-find "<keyword>"to find MCPs - Run
mcp-add "<server>"to see the exact tool signatures - Note the tool name and required arguments from the schema
Step 3: Return Exact Syntax
Return instructions with complete, executable calls:
## Research Tools for: <topic>
### Next.js
Setup: `mcp-add "next-devtools-mcp"` ⚠️ ~16k tokens
Call: `mcp-exec name="nextjs_docs" arguments={"query": "SSR", "category": "guides"}`
Tips: Use 1-word queries. Categories: guides, api-reference, getting-started
### Bun
Call: `mcp__bun__SearchBun` with `{"query": "runtime"}`
No setup needed (native tool).
Critical:
- Include the exact
mcp-exec name="..." arguments={...}format - Mark tools requiring
mcp-addwith ⚠️ and approximate token cost - Note which tools are native (no setup, no cost)
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.
- 3d ago First seen · 47 lines · 33 tokens per session scan A 661c5c6ada8b
research-teacher is an agent published in the GitHub repository bengous/claude-code-plugins (4 stars, last pushed yesterday), licensed MIT. It adds 33 tokens to every session and 371 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 2026-09-03.
Other agents, from other repositories
Independent Reviewer
Product-technical alignment reviewer. Spawned in a tmux pane via OpenAI Codex CLI with zero inherited context. Cross-provider isolation (GPT-5.5 vs Lead's Claude) layered on top of zero context inheritance. Reads product-spec and tech-spec independently to verify the technical approach actually implements what the…
Process Observer Audit
Compliance audit sub-agent. Reviews session against CLAUDE.md behavioral guidelines — branching conventions, Codex review triggers, Doc Engineer execution, PR workflow, unauthorized operations, plan.md accuracy. Outputs deviation report.
1-create-prd
Create PRDs through structured discovery.
2-generate-tasks
Convert PRDs into development task lists.
3-process-task-list
Execute task lists with sequential commits.
code-developer
Implement code, debug, refactor, optimize.