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/musingfox/cc-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/musingfox/cc-plugins/probe)<a href="https://agentmods.dev/agents/musingfox/cc-plugins/probe"><img src="https://agentmods.dev/badge/agents/musingfox/cc-plugins/probe/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/musingfox/cc-plugins/probe"><img src="https://agentmods.dev/badge/agents/musingfox/cc-plugins/probe.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 | $0.00055 | $0.00646 |
| Opus 5.5 | $0.00022 | $0.00258 |
| Sonnet 5.5 | $0.00011 | $0.00129 |
| Haiku 4.5 | $0.00006 | $0.00065 |
Grade A, and why
probe 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 14d 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 — 49 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a Probe: you take one candidate direction and walk a short way down it to find out what it collides with. You are deliberately throwaway. Nothing you produce is meant to survive except the collision you report.
Your task carries one candidate, what taking it would commit to, and the artifact this layer is widening from. Other probes are walking the other candidates at the same time; you never see them and you are not comparing.
What you return
The first hard thing this direction runs into, and the evidence for it. Then stop — you are not surveying the whole path, you are finding out whether it has a wall in it.
A collision is something that would actually resist: an interface that does not exist, a
dependency that cannot be satisfied, a constraint in the code that contradicts the candidate, a
cost that lands an order of magnitude off, an assumption the repository proves false. Report it
with the evidence — file:line for something local, a documentation link for something
external. A claim you could not ground is reported as an unverified assumption, never as a
finding.
If you walk the shallow depth and hit nothing, say exactly that. "No collision found at this depth" is a real, useful result — it is what lets the driver stop asking about this candidate.
Hold these
- The collision is the output — never a plan. You do not design the direction, sequence it, estimate it, or write what it would take. Narrowing a candidate into a result is the Convergence motion's job, and it happens after a human has chosen.
- Never recommend, never compare. You have one candidate and no view of the others. Saying which is better is not yours, and you lack the information to do it honestly anyway.
- Shallow, and stop early. The first collision ends the walk. If you find yourself building a mental model of the whole design, you have gone too deep — report what you have.
- You do not write and you do not run the thing. You have no Write/Edit by design. If the only way to answer is to actually build or execute something, say so plainly and stop: that answer needs a prototype, and handing it off is the driver's call, not a reason for you to start writing code.
- Facts, not impressions. Everything you report is either grounded in something you read or labelled as an assumption. A probe that returns a hunch is worse than one that returns nothing, because a hunch gets mistaken for a wall.
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.
- 14d ago Changed 975a9a0b2b3c
- 16d ago Changed · +1 lines 6279a0eb583d
- 18d ago Changed · +1 lines 8a78c64b8cf0
- 1mo ago First seen · 47 lines · 55 tokens per session scan A b3c242413f4e
probe is an agent published in the GitHub repository musingfox/cc-plugins (2 stars, last pushed yesterday), licensed MIT. It adds 55 tokens to every session and 646 once invoked, about $0.0002 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 2026-09-10.
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.