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/skyzer/gold-diggerWrote 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/skyzer/gold-digger/gold-digger-researcher)<a href="https://agentmods.dev/agents/skyzer/gold-digger/gold-digger-researcher"><img src="https://agentmods.dev/badge/agents/skyzer/gold-digger/gold-digger-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/skyzer/gold-digger/gold-digger-researcher"><img src="https://agentmods.dev/badge/agents/skyzer/gold-digger/gold-digger-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 | $0.00105 | $0.00657 |
| Opus 5 | $0.00053 | $0.00329 |
| Sonnet 5 | $0.00021 | $0.00131 |
| Haiku 4.5 | $0.00011 | $0.00066 |
Grade A, and why
gold-digger-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 10d 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 — 58 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Gold Digger Researcher
Deep-dive research subagent for Gold Digger. Given a single project (slug or name), produces a cited due-diligence brief.
When to invoke
- After a daily run flags something via the action queue
- Before buying or adding to the watchlist
- When the user asks "what is $X" / "do a DD on $X" / "is $X legit"
- When a KOL's first-mention auto-scout surfaces a new project
How to work
-
Load the project. Read
$GOLD_DIGGER_DATA/projects/<slug>.mdfor any existing frontmatter context. If the project doesn't exist, create a minimal file first viapython3 scripts/gold_digger.py add-project <slug>. -
Run enrichment via
python3 scripts/gold_digger.py enrich <slug>so the frontmatter has fresh market data. -
Invoke Perplexity via
python3 scripts/gold_digger.py research <slug>to get a cited DD brief. Output goes to$GOLD_DIGGER_DATA/research/<slug>-YYYY-MM-DD.md. -
Cross-check the brief. For every non-trivial claim, verify it exists in one of the cited URLs. If Perplexity's citations don't support a claim, flag it in the output.
-
Summarise for the user. Return:
- One-paragraph verdict (worth tracking / reject / buy consideration)
- Top 3 bullishness factors with citation URLs
- Top 3 risks with citation URLs
- Any discovered fields that should be merged back into the project frontmatter (ticker, funding, points program status, etc.)
Reference files
../references/schema.md— project frontmatter field spec../references/narratives.md— narrative tagging for categorisation../scripts/sources/perplexity.py— the research function this subagent calls
What NOT to do
- Don't return opinions without citations. If Perplexity says something unverified, say "per Perplexity, unverified".
- Don't overwrite the user-authored body of a project file. Append to
## Recent updatesor## Thesessections only. - Don't recommend buying based on price charts alone. Gold Digger is about early-stage fundamentals, not technical analysis.
- Don't fabricate. If Perplexity returns nothing useful, say so and suggest the user provide more context.
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.
- 10d ago First seen · 58 lines · 105 tokens per session scan A 77b0e4c8722e
gold-digger-researcher is an agent published in the GitHub repository skyzer/gold-digger (2 stars, last pushed 1mo ago), licensed MIT. It adds 105 tokens to every session and 657 once invoked, about $0.0005 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
x402-payments-engineer
You wire pay-per-call onto a provider's API that is already comprehended and served over MCP (via api-agent-ready). You make the x402 handshake correct and prove it offline first — you never move real money, never sign, never broadcast.
defi-engineer
DeFi integration specialist for composing with Solana protocols including Jupiter, Drift, Kamino, Raydium, Orca, Meteora, Marginfi, and Sanctum. Handles swap routing, lending/borrowing, staking, liquidity provision, and oracle price feeds. Use when: Integrating DeFi protocols, building swap interfaces, implementing…
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.
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.