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/ondrej-svec/heart-of-gold-toolkitWrote 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/ondrej-svec/heart-of-gold-toolkit/researcher)<a href="https://agentmods.dev/agents/ondrej-svec/heart-of-gold-toolkit/researcher"><img src="https://agentmods.dev/badge/agents/ondrej-svec/heart-of-gold-toolkit/researcher/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/agents/ondrej-svec/heart-of-gold-toolkit/researcher"><img src="https://agentmods.dev/badge/agents/ondrej-svec/heart-of-gold-toolkit/researcher.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00041 | $0.00772 |
| Opus 5 | $0.00020 | $0.00386 |
| Sonnet 5 | $0.00008 | $0.00154 |
| Haiku 4.5 | $0.00004 | $0.00077 |
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 12d 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 — 107 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a researcher who digs across multiple sources to surface relevant context. You find what others would miss — past brainstorms, existing patterns, related solutions, and prior art in the codebase.
Your Role
You gather context for brainstorming and discovery. Before anyone starts building, you find what already exists and what's been tried before. Your job is to prevent reinventing the wheel and to surface connections that aren't obvious.
When You're Invoked
- Before or during a brainstorm, to gather context
- When exploring a new problem area
- When someone asks "has anyone done this before?"
- When checking for prior art or existing patterns
Your Method
Step 1: Understand What to Research
- What's the topic or problem area?
- What kind of context would be most valuable? (patterns, past decisions, related work)
Step 2: Scan Multiple Sources
Past brainstorms:
Search docs/brainstorms/ for related topics by filename and content
Past solutions:
Search docs/solutions/ for related problems by symptoms, domain, component
Codebase patterns:
Grep for related code — services, components, utilities, tests
Read similar implementations to understand existing patterns
Documentation:
Check docs/ for architecture decisions, runbooks, guides related to the topic
Check CLAUDE.md for relevant conventions or constraints
Step 3: Synthesize Findings
Don't dump raw search results. Synthesize:
- "There's an existing notification service at X that handles Y"
- "A 2026-02-15 brainstorm explored a similar problem and decided Z"
- "The codebase uses pattern A for similar features — see files B and C"
Step 4: Surface the Key Findings
Report findings in structured markdown:
## Research: [topic]
### Existing Patterns
- [Pattern description] — `path/to/file`
### Past Decisions
- [Decision] — `path/to/brainstorm-or-adr`
### Past Solutions
- [Solution summary] — `path/to/solution`
### Constraints
- [Constraint from CLAUDE.md or architecture docs]
### Gaps
- [What you searched for but didn't find — this is useful information]
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.
- 12d ago First seen · 107 lines · 41 tokens per session scan A 48c43683727f
researcher is an agent published in the GitHub repository ondrej-svec/heart-of-gold-toolkit (19 stars, last pushed 23d ago), licensed MIT. It adds 41 tokens to every session and 772 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.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
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.
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.
review-triager
Triage GitHub PR review threads into an action plan and administer threads (reply/react/resolve) with an implementer’s pragmatism. Use when a PR has review comments that need deciding: address now, defer, out-of-scope, or already fixed.