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.
npx skills add getcrew44/crew44 --skill pol-probegit clone --depth 1 https://github.com/getcrew44/crew44Wrote 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/skills/getcrew44/crew44/pol-probe)<a href="https://agentmods.dev/skills/getcrew44/crew44/pol-probe"><img src="https://agentmods.dev/badge/skills/getcrew44/crew44/pol-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/skills/getcrew44/crew44/pol-probe"><img src="https://agentmods.dev/badge/skills/getcrew44/crew44/pol-probe.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 4 findings, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Agent Snooping · line 202 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
- medium Agent Snooping · line 203 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
- medium Agent Snooping · line 204 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
- medium Agent Snooping · line 205 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
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 | $0.00028 | $0.02352 |
| Opus 5.5 | $0.00011 | $0.00941 |
| Sonnet 5.5 | $0.00006 | $0.00470 |
| Haiku 4.5 | $0.00003 | $0.00235 |
Grade A, and why
pol-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 1mo 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 — 218 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Purpose
Define and document a Proof of Life (PoL) probe—a lightweight, disposable validation artifact designed to surface harsh truths before expensive development. Use this when you need to eliminate a specific risk or test a narrow hypothesis without building production-quality software. PoL probes are reconnaissance missions, not MVPs—they're meant to be deleted, not scaled.
This framework prevents prototype theater (expensive demos that impress stakeholders but teach nothing) and forces you to match validation method to actual learning goal.
Key Concepts
What is a PoL Probe?
A Proof of Life (PoL) probe is a deliberate, disposable validation experiment designed to answer one specific question as cheaply and quickly as possible. It's not a product, not an MVP, not a pilot—it's a targeted truth-seeking mission.
Origin: Coined by Dean Peters (Productside), building on Marty Cagan's 2014 work on prototype flavors and Jeff Patton's principle: "The most expensive way to test your idea is to build production-quality software."
The 5 Essential Characteristics
Every PoL probe must satisfy these criteria:
| Characteristic | What It Means | Why It Matters |
|---|---|---|
| Lightweight | Minimal resource investment (hours/days, not weeks) | If it's expensive, you'll avoid killing it when the data says to |
| Disposable | Explicitly planned for deletion, not scaling | Prevents sunk-cost fallacy and scope creep |
| Narrow Scope | Tests one specific hypothesis or risk | Broad experiments yield ambiguous results |
| Brutally Honest | Surfaces harsh truths, not vanity metrics | Polite data is useless data |
| Tiny & Focused | Reconnaissance missions, never MVPs | Small surface area = faster learning cycles |
Anti-Pattern: If your "prototype" feels too polished to delete, it's not a PoL probe—it's prototype theater.
PoL Probe vs. MVP
| Dimension | PoL Probe | MVP |
|---|---|---|
| Purpose | De-risk decisions through narrow hypothesis testing | Justify ideas or defend roadmap direction |
| Scope | Single question, single risk | Smallest shippable product increment |
| Lifespan | Hours to days, then deleted | Weeks to months, then iterated |
| Audience | Internal team + narrow user sample | Real customers in production |
| Fidelity | Just enough illusion to catch signals | Production-quality (or close) |
| Outcome | Learn what doesn't work | Learn what does work (and ship it) |
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 1mo ago First seen · 218 lines · 28 tokens per session scan A 2506abaf32b5
pol-probe is a skill published in the GitHub repository getcrew44/crew44 (356 stars, last pushed 4mo ago), licensed MIT. It adds 28 tokens to every session and 2,352 once invoked, about $0.0001 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 2026-08-30.
Other skills, from other repositories
eval-dataset-design
A guide to creating reliable test sets for AI agents. Each evaluation task includes the request, the simulated user's behaviour, a reset starting state, and a success check that can be independently verified.
memory-system
A guide to giving an AI agent persistent, user-specific memory across conversations. It covers what to remember, how to store it, how to update or compress it, and when to use memory instead of a shared knowledge base.
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.
verify
Exercise the real app/API/CLI and collect observable evidence; tests alone do not count as end-to-end verification.
writing
A writing guide for turning verified facts and calculations into finished text for a specific audience. It follows the requested language, structure, and length.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.