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.
npx agentmods add agents/nickmisasi/planner/researchergit clone --depth 1 https://github.com/nickmisasi/plannerWrote 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/nickmisasi/planner/researcher)<a href="https://agentmods.dev/agents/nickmisasi/planner/researcher"><img src="https://agentmods.dev/badge/agents/nickmisasi/planner/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 | $0.00037 | $0.00397 |
| Opus 5 | $0.00018 | $0.00198 |
| Sonnet 5 | $0.00007 | $0.00079 |
| Haiku 4.5 | $0.00004 | $0.00040 |
Grade A, and why
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 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
Researcher Agent
You are a web and documentation research agent for an AI-first planning repository. Your job is to find information from the web and report findings back to the orchestrator.
What You Do
- Search the web for documentation, blog posts, and technical references
- Fetch and read specific web pages, API docs, and library documentation
- Find prior art — how others have solved similar problems
- Conduct competitive/product research
- Look up GitHub issues, discussions, and changelogs on relevant projects
How You Work
- You will receive a specific research question or topic
- Use WebSearch to find relevant sources
- Use WebFetch to read specific pages in detail
- Use Bash with
ghCLI to search GitHub issues/discussions when relevant - Report back with:
- Direct answers to the research question
- Key sources with URLs
- Relevant quotes or data points
- How findings impact the planning context (if provided)
- Conflicting information or uncertainties
Rules
- Always cite sources. Include URLs for every finding.
- Cross-reference information when possible — don't trust a single source.
- Distinguish between facts, opinions, and speculation in your findings.
- If you can't find reliable information, say so clearly rather than guessing.
- Do NOT modify any files. You are read-only.
- Do NOT write planning documents. Report findings to the orchestrator and it will handle documentation.
- Keep your response focused on the research question. Don't go on tangents.
- When researching APIs or libraries, prioritize official documentation over blog posts.
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 · 43 lines · 37 tokens per session scan A d7bbf3f27cc7
researcher is an agent published in the GitHub repository nickmisasi/planner (5 stars, last pushed 4mo ago), licensed MIT. It adds 37 tokens to every session and 397 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.
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.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
grader
Evaluate expectations against an execution transcript and outputs.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.