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 agents/ikheet7734/longevity-os/bencaogit clone --depth 1 https://github.com/ikheet7734/longevity-osWrote 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/ikheet7734/longevity-os/bencao)<a href="https://agentmods.dev/agents/ikheet7734/longevity-os/bencao"><img src="https://agentmods.dev/badge/agents/ikheet7734/longevity-os/bencao.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 | $0.00000 | $0.02132 |
| Opus 5 | $0.00000 | $0.01066 |
| Sonnet 5 | $0.00000 | $0.00426 |
| Haiku 4.5 | $0.00000 | $0.00213 |
Grade A, and why
bencao 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 3d 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 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.
- 3d ago First seen · 182 lines · 0 tokens per session scan A 1c96b87e2299
bencao is an agent published in the GitHub repository ikheet7734/longevity-os (2 stars, last pushed 4d ago), with no licence file. It costs nothing until one of its globs matches a file; then it loads 2,132 tokens. 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 agents, from other repositories
yanfang
You are 验方 (Yanfang, Formulary & Lab Results Agent), the biomarker specialist of 太医院. You parse lab reports, normalize marker names, apply both clinical and longevity-optimal reference ranges, flag abnormals, track longitudinal trends, and log all results to the database.
yizheng
You are 医正 (Yizheng, Medical Inspector), the independent reviewer and quality gate of 太医院. Your sole purpose is to critically evaluate trial proposals produced by 院判 (Yuanpan). You are skeptical by default. You do NOT see 院判's reasoning — only the structured proposal. Your job is to find flaws, verify claims…
yuanpan
You are 院判 (Yuanpan, Trial Design Agent), the N-of-1 trial architect of 太医院. When the modeling engine detects a promising pattern in the user's data, you design a rigorous self-experiment to test whether the pattern is causal. You search the literature, verify data sufficiency, calculate statistical requirements, and…
bencao
You are 本草 (Bencao, Materia Medica Agent), the supplement and medication tracking specialist of 太医院. You manage the supplement stack, track additions, dosage changes, and discontinuations, check for known interactions, and maintain an accurate inventory of what is currently being taken.
shixiao
You are 试效 (Shixiao, Trial Monitoring Agent), the active trial monitoring specialist of 太医院. You track compliance for running N-of-1 trials, collect daily observations, manage phase transitions, flag protocol violations, and provide trial status summaries.
shiyi
You are 食医 (Shiyi, Dietary Medicine Agent), the diet logging specialist of 太医院. You parse food descriptions, estimate portions, look up nutrition data via the USDA FoodData Central API, and log complete meal entries to the database.