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 SoMic520/Hemusci-Skills --skill soil-third-survey-reportgit clone --depth 1 https://github.com/SoMic520/Hemusci-SkillsWrote 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/somic520/hemusci-skills/soil-third-survey-report)<a href="https://agentmods.dev/skills/somic520/hemusci-skills/soil-third-survey-report"><img src="https://agentmods.dev/badge/skills/somic520/hemusci-skills/soil-third-survey-report/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/somic520/hemusci-skills/soil-third-survey-report"><img src="https://agentmods.dev/badge/skills/somic520/hemusci-skills/soil-third-survey-report.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 | $0.00202 | $0.04649 |
| Opus 5 | $0.00101 | $0.02325 |
| Sonnet 5 | $0.00040 | $0.00930 |
| Haiku 4.5 | $0.00020 | $0.00465 |
Grade A, and why
soil-third-survey-report 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 12d 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.
The source is not reproduced here
No licence file
A repository with no LICENSE is all rights reserved by default, so the body is not copied here. The metadata, the measurements and the link are.
What ships with it
15 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.
- agents/openai.yaml 437 B
- references/data-tables-figures.md 10 KB
- references/docx-redline-workflow.md 13 KB
- references/domain-and-acceptance.md 12 KB
- references/formal-language.md 16 KB
- references/guide-third-part-writing-tasks.md 16 KB
- references/model-portability.md 7.9 KB
- references/province-city-county-levels.md 14 KB
- references/report-format-requirements.md 22 KB
- references/soil-attribute-classification-nyt4980-2025.md 13 KB
- references/structure-and-paragraphs.md 9.8 KB
- scripts/ensure_libreoffice.ps1 8.3 KB runs code
- scripts/scan_report_text.py 32 KB runs code
- scripts/test_scan_report_text.py 8.8 KB runs code
- scripts/validate_skill.ps1 2.2 KB runs code
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.
- 12d ago First seen · 218 lines · 202 tokens per session scan A 3b625bc1eb92
soil-third-survey-report is a skill published in the GitHub repository SoMic520/Hemusci-Skills (7 stars, last pushed 25d ago), with no licence file. It adds 202 tokens to every session and 4,649 once invoked, about $0.0010 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
scientific-writing
Core skill for the deep research and writing tool.
research-essay
Develop a research idea into a literature-grounded, standalone HTML essay with verified full texts, reproducible analysis, and a tutorial narrative. Use for requests to develop or situate an idea in the literature and write it up, or to revise an existing essay after new evidence, analysis, or reader feedback. Also…
write-reader-first-papers
Rewrite, restructure, translate, or audit academic manuscripts so first-time readers can identify the problem, contribution, evidence, value, and limitations without decoding internal jargon or formulaic prose. Use for English or Chinese papers, abstracts, introductions, methods, results, conclusions, highlights…
scientific-paper-writer
Full-lifecycle scientific paper writing assistant. Fetches live journal guidelines, AI authorship policy, word limits, citation format, and LaTeX template for any journal before writing. Audits every draft for 25 AI writing patterns. Verifies every citation via web search. Produces publication-ready prose for Nature…
wit
Apply WIT (Writing Is Thinking) as a human–LLM collaborative scientific reasoning skill for scientific question formulation, finding-driven research planning, next-experiment selection, Results or Discussion review, claim–evidence and reviewer stress tests, manuscript logic audits, deadline closure, and researcher…
paper-workshop
CRUCIBLE: a Claude-only adversarial expert workshop that stress-tests a scientific paper and then, opt-in, rebuilds it. ACT I (TRIBUNAL): from the paper PDF (plus a few public cited works it fetches), a topic-adapted fleet of expert referee subagents (every contested claim argued from at least two COMPETING…