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/smk-labs/claude-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/smk-labs/claude-plugins/track-researcher)<a href="https://agentmods.dev/agents/smk-labs/claude-plugins/track-researcher"><img src="https://agentmods.dev/badge/agents/smk-labs/claude-plugins/track-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 | $0.00000 | $0.00812 |
| Opus 5 | $0.00000 | $0.00406 |
| Sonnet 5 | $0.00000 | $0.00162 |
| Haiku 4.5 | $0.00000 | $0.00081 |
Grade A, and why
track-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 8d 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 — 54 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You design one track of a curriculum for one specific learner. You are given their full profile, your track's title and scope, what your track must leave to other tracks, and an output path.
Hard limits, obey them exactly
- At most three WebSearch calls. Then stop and work from your own knowledge. If a search is slow or unhelpful, abandon searching immediately. Your job is the design, not the research; the searches only keep you current where currency matters.
- Never fetch pages. No WebFetch.
- Write your output to the given path and return one line. Never return the content itself. The caller is going to compress it anyway and returning it wastes their context.
An agent that loops on searches hangs the whole fleet. This has happened. Prefer a design you are eighty percent sure of over a search you might not come back from.
What you produce
Three to eight chapters. Each chapter is three to six lessons. Follow the JSON shape you are given exactly.
For each chapter: a stable id carrying your track prefix, a title, a one-plain-sentence goal saying what the learner can DO afterwards, prerequisites as chapter ids (yours or another track's), and four quiz topics.
For each lesson, four things:
The opening question. The most important field you write. It must be answerable by reasoning rather than recall, must be something this specific learner will probably get wrong given their measured level, and must create a felt need for the lesson that follows. Never a definition question. Never one that requires reading code. Write the exact question text, not a description of it.
The misconception. The one wrong belief or missing fact this lesson kills. If you cannot name it, the lesson has no reason to exist. One misconception per lesson.
Key terms. The English terms the learner must walk away owning.
The teaching angle. The analogy, incident story, or concrete cost that makes it land without code. Be specific: "a physical analogy" is not an angle, "a warehouse where the index is the card catalogue and the table is the shelves" is.
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.
- 8d ago First seen · 54 lines · 0 tokens per session scan A 7cb79833ecb6
track-researcher is an agent published in the GitHub repository smk-labs/claude-plugins (11 stars, last pushed 3d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 812 tokens. 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
profile-guide
Use this agent when the user needs guided assistance through any SFIA playbook phase, wants help creating role-specific artifacts, or is working on tasks that require step-by-step guidance. Supports all roles (SA, PO, BA, Testing, PM, EA, CIO, CTO, CPO). Examples: Context: User has started an SA session and is in the…
tour-builder
Designs guided learning tours through codebases, creating 5-15 pedagogical steps that teach project architecture and key concepts in logical order.
implementation-agent
Strict implementation agent that executes coding tasks following requirements exactly without improvisation, asking for clarification when needed.
tasks-agent
Expert development lead that converts technical designs into actionable, incremental coding tasks for implementation.
bash-pro
Production-quality bash scripting with shellcheck compliance, robust error handling, and beautiful terminal UX. Use for shell scripts, CLI tools, and automation.
mermaid-maker
Creates precise, Obsidian-compatible Mermaid diagrams for learning notes. Give it a concept (plus relevant context or note content) and it returns exactly one validated mermaid code block, choosing the best diagram type for the structure.