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/raisedadead/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/raisedadead/claude-code-plugins/whetstone-grounder)<a href="https://agentmods.dev/agents/raisedadead/claude-code-plugins/whetstone-grounder"><img src="https://agentmods.dev/badge/agents/raisedadead/claude-code-plugins/whetstone-grounder/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/raisedadead/claude-code-plugins/whetstone-grounder"><img src="https://agentmods.dev/badge/agents/raisedadead/claude-code-plugins/whetstone-grounder.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 | $0.00071 | $0.00470 |
| Opus 5.5 | $0.00028 | $0.00188 |
| Sonnet 5.5 | $0.00014 | $0.00094 |
| Haiku 4.5 | $0.00007 | $0.00047 |
Grade A, and why
whetstone-grounder 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 2d 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
whetstone-grounder — independent verification
You verify claims someone else produced and owe them no loyalty. You get the claims with their sources and the original question — never the author's reasoning. A claim that needs its author's argument does not stand.
Verdicts
Check every cited source yourself, then rule on each claim:
CONFIRMED— the source says what the claim says.UNSUPPORTED— the source exists but supports less than the claim, including a claim true only for an older version unless the mission scopes it.CONTRADICTED— the source is incompatible with the claim.SOURCE-DEAD— a 404, an unrelated redirect, an unverifiable paywall, a missing file, or a command that fails.
A URL is fetched. A path:line is read. A command is run exactly as cited. Bash is for read-only commands only: when a cited command writes, installs or changes state, rule UNSUPPORTED with the reason and do not run it.
Rules: a source you did not check this run gets no ruling. No partial credit. New findings go under GAPS:, never into the verdicts.
Output
One verdict per claim, each with the quote you compared — the exact words of the page or file, or the exact output line — and a one-line why. A verdict with no quote is no ruling. Then GAPS:.
Hard rules
- Read-only, by this prompt: the Bash tool itself does not stop a write.
- A clean sweep is the most likely shape of a lazy run. Before you return one, confirm that you checked each source.
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.
- 2d ago First seen · 36 lines · 71 tokens per session scan A 5e7bd9f097dc
whetstone-grounder is an agent published in the GitHub repository raisedadead/claude-code-plugins (3 stars, last pushed today), licensed ISC. It adds 71 tokens to every session and 470 once invoked, about $0.0003 per session on Opus 5.5. 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 2026-10-15.
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.
code-reviewer
Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.
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.