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 agentmods add skills/planexeorg/planexe/test-napkin-mathnpx skills add PlanExeOrg/PlanExe --skill test-napkin-mathgit clone --depth 1 https://github.com/PlanExeOrg/PlanExeWrote 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/planexeorg/planexe/test-napkin-math)<a href="https://agentmods.dev/skills/planexeorg/planexe/test-napkin-math"><img src="https://agentmods.dev/badge/skills/planexeorg/planexe/test-napkin-math.svg" alt="Measured on agentmods" 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 | $0.00081 | $0.01230 |
| Opus 5 | $0.00041 | $0.00615 |
| Sonnet 5 | $0.00016 | $0.00246 |
| Haiku 4.5 | $0.00008 | $0.00123 |
Grade A, and why
test-napkin-math 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 5d 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 — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Test the napkin_math experiment
Overview
A single-shot smoke check for the napkin_math experiment. The test logic lives in experiments/napkin_math/tests/run_smoke.py; this skill is a thin wrapper that invokes the script, parses its output, and reports a one-line summary.
Covers the Monte Carlo runner (end-to-end, determinism, Bernoulli arithmetic, sensitivity ranking), the strict-schema fail-fast paths (each required field individually), prepare_extract_input.py import sanity, and the compress_report_section pytest suite.
When to Use
- After any edit to:
experiments/napkin_math/run_monte_carlo.pyexperiments/napkin_math/prepare_extract_input.pyexperiments/napkin_math/tests/fixtures/smoke/*worker_plan/worker_plan_internal/parameter_extraction/compress_report_section.py- any system-prompt.txt / SKILL.md under
experiments/napkin_math/.claude/skills/{extract-parameters-from-full,extract-parameters-from-digest,generate-bounds,generate-calculations,run-scenarios,monte-carlo}/that touches the artifact schema
- Before declaring any napkin_math change "done" — even if the change looks self-contained, the schema is tightly coupled across stages
- When the user asks "did I break anything?" or "run the napkin_math tests"
Not for: end-to-end LLM-driven runs of the extract-parameters-from-full skills against real reports (those require an LLM in the loop and are out of scope here).
Workflow
-
Invoke the runner. Requires Python 3.11+ with NumPy and pytest installed:
/opt/homebrew/bin/python3.11 experiments/napkin_math/tests/run_smoke.pyOverride the interpreter with
NAPKIN_TEST_PYTHON=<path>if the default isn't available. -
Read the script's stdout. It prints one section per check with individual
ok/FAILlines, then a final summary:SUMMARY: 7/7 checks passed ALL GREENExit code is
0on full pass,1on any failure. -
Report back to the user. On success: one line ("All 7 napkin_math smoke checks passed."). On failure: list the failing checks with the detail printed by the runner, and point at the specific file or schema field implicated.
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.
- 5d ago First seen · 76 lines · 81 tokens per session scan A 754145feac98
test-napkin-math is a skill published in the GitHub repository PlanExeOrg/PlanExe (398 stars, last pushed 5d ago), licensed MIT. It adds 81 tokens to every session and 1,230 once invoked, about $0.0004 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 skills, from other repositories
session-rag-eval
Run and debug Chatbox session attachment RAG model evaluation with synthetic and real long-file fixtures.
designer_guide
Guidance for creating and editing designs using the designer tool.
lynkr
Universal LLM gateway with intelligent routing, Graphify code intelligence, Distill compression, routing telemetry, Code Mode, and 12+ provider support. 60-80% cost reduction for Claude Code, Cursor, and Codex.
agents_guide
Guidance for delegating focused work to child Agents.
文档协作
引导用户通过结构化的文档共同编写工作流程。当用户想撰写文档、提案、技术规范、决策文档或类似结构化内容时使用。该工作流程帮助用户高效传递上下文，通过迭代优化内容，并验证文档对读者有效。当用户提到写文档、创建提案、起草规范或类似文档任务时触发。.
data_analyst
Analyses datasets with professional rigour — statistical summaries, clear narratives, and well-chosen visualisations.