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 cambridgetcg/agenttool --skill nen-math-cardgit clone --depth 1 https://github.com/cambridgetcg/agenttoolWrote 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/cambridgetcg/agenttool/nen-math-card)<a href="https://agentmods.dev/skills/cambridgetcg/agenttool/nen-math-card"><img src="https://agentmods.dev/badge/skills/cambridgetcg/agenttool/nen-math-card/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/cambridgetcg/agenttool/nen-math-card"><img src="https://agentmods.dev/badge/skills/cambridgetcg/agenttool/nen-math-card.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 | $0.00094 | $0.01673 |
| Opus 5 | $0.00047 | $0.00837 |
| Sonnet 5 | $0.00019 | $0.00335 |
| Haiku 4.5 | $0.00009 | $0.00167 |
Grade A, and why
nen-math-card 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 8d 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 — 171 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Math Card · 數理鍛
Use mathematics to answer a chosen question, not to rank the questioner. Leave an inspectable result even when the result is ambiguity, model failure, or a reason to stop.
Open the gate
Before solving, state:
- the exact question and object;
- the scope in which an answer would hold;
- the build, repair, decision, or next question the result could change; and
- a condition under which the inquiry should stop.
Ask whether the same work would retain constructive value without names, audience, prize, winner, or rank. A weak audience-independent answer does not diagnose pride; it exposes a visible incentive that may need redesign.
Proceed when the result can reduce relevant uncertainty, expose a small obstruction, produce a reusable method or certificate, calibrate an observation, or prevent a mistaken build. Redesign or stop when no bounded consumer exists and adversarial challenge adds no useful independence, diversity, or error detection.
End this preflight with one inquiry decision. Map
ready_for_bounded_inquiry to proceed, questions_open to
clarify_before_proceed, and redesign_or_stop to redesign_or_stop. This
decision is a workflow conclusion, not a Math Card wire field and not a claim
that the inquiry will succeed.
Choose exactly one method
- Proof: declare the logical or checking framework, exact proposition, and verification method. Bind problem-specific premises separately, including any model, adversary, objective, baseline, or novelty criterion. A valid derivation is conditional on those declarations; it does not by itself establish that the premises describe the world. In Math Card v0.1, include those premise declarations in the exact external artifacts bound by the proof references and name what each artifact contains; do not imply that the closed wire has separate premise fields.
- Model: declare the representation, assumptions, comparison or identification method, and revision or falsifier conditions. A useful model compresses selected structure; it is not complete reality or automatic causal truth.
- Measurement: declare the measurand, operationalization, procedure, calibration, and uncertainty. A measurement concerns the operationalized construct; it does not exhaust everything the word may mean.
What ships with it
1 file 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.
- 8d ago First seen · 171 lines · 94 tokens per session scan A 0b19e3f8c54c
nen-math-card is a skill published in the GitHub repository cambridgetcg/agenttool (0 stars, last pushed today), licensed Apache-2.0. It adds 94 tokens to every session and 1,673 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 skills, from other repositories
clinical-reports
Write comprehensive clinical reports including case reports (CARE guidelines), diagnostic reports (radiology/pathology/lab), clinical trial reports (ICH-E3, SAE, CSR), and patient documentation (SOAP, H&P, discharge summaries). Full support with templates, regulatory compliance (HIPAA, FDA, ICH-GCP), and validation…
imaging-data-commons
Query and download public cancer imaging data from NCI Imaging Data Commons using idc-index. Use for accessing large-scale radiology (CT, MR, PET) and pathology datasets for AI training or research. No authentication required. Query by metadata, visualize in browser, check licenses.
clinical-decision-support
Generate professional clinical decision support (CDS) documents for pharmaceutical and clinical research settings, including patient cohort analyses (biomarker-stratified with outcomes) and treatment recommendation reports (evidence-based guidelines with decision algorithms). Supports GRADE evidence grading…
clinical-imaging
Clinical and physiological imaging analysis. Diffusion MRI ADC maps, micro-CT bone morphometry, hemodynamic parameter analysis, circadian rhythm cosinor analysis, ciliary beat frequency (FFT), and tissue deformation optical flow. For DICOM file handling use pydicom; for biosignals use neurokit2.
curated-bio-datasets
Guide to accessing curated biological datasets for computational biology. COSMIC cancer data, GTEx expression, GWAS catalog, GeneBass exome variants, BioGRID interactions, MSigDB gene sets, DisGeNET disease-gene associations, and GO ontology. For specific database APIs use individual database skills (cosmic-database…
gget
Fast CLI/Python queries to 20+ bioinformatics databases. Use for quick lookups: gene info, BLAST searches, AlphaFold structures, enrichment analysis. Best for interactive exploration, simple queries. For batch processing or advanced BLAST use biopython; for multi-database Python workflows use bioservices.