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 spyrae/kronos-agent-os --skill food-advisorgit clone --depth 1 https://github.com/spyrae/kronos-agent-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/skills/spyrae/kronos-agent-os/food-advisor)<a href="https://agentmods.dev/skills/spyrae/kronos-agent-os/food-advisor"><img src="https://agentmods.dev/badge/skills/spyrae/kronos-agent-os/food-advisor/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/spyrae/kronos-agent-os/food-advisor"><img src="https://agentmods.dev/badge/skills/spyrae/kronos-agent-os/food-advisor.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00018 | $0.00371 |
| Opus 5.5 | $0.00007 | $0.00148 |
| Sonnet 5.5 | $0.00004 | $0.00074 |
| Haiku 4.5 | $0.00002 | $0.00037 |
Grade A, and why
food-advisor 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 2mo 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.
What it actually says
Food Advisor
Trigger
Use when the user asks to count calories, estimate macros, log a meal, compare food options, or summarize food notes.
Protocol
- Parse the meal into explicit items, portions, and preparation assumptions.
- Estimate calories and macros only when enough information is present. Use a
range or
lowconfidence when portions are vague. - If the user asks to log the meal and a food/calorie database is configured,
write a compact entry with:
- entry title;
- date;
- meal type;
- items/portions;
- calories;
- protein, carbs, fat;
- confidence;
- assumptions/notes.
- If no database/tool is available, return the same data as a markdown row the user can paste manually.
- For daily summaries, separate observed totals from estimates and list high-impact uncertainty first.
Output
- Estimate — kcal and macros, preferably as a range when uncertain.
- Assumptions — portions, cooking method, and source of uncertainty.
- Log row — compact structured fields for the calorie tracker.
- Next question — only ask for missing portion details that materially change the estimate.
Safety
- This is an informational tracker, not medical advice.
- Do not prescribe diets, diagnose conditions, or set aggressive calorie targets. Suggest a qualified clinician/dietitian for medical goals, eating-disorder concerns, pregnancy, diabetes, kidney disease, or other clinical contexts.
- Do not shame the user or moralize food choices.
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.
- 2mo ago First seen · 51 lines · 18 tokens per session scan A 1b16eefc975b
food-advisor is a skill published in the GitHub repository spyrae/kronos-agent-os (66 stars, last pushed 15d ago), licensed MIT. It adds 18 tokens to every session and 371 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.
food-advisor compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| food-advisorspyrae/kronos-agent-os | Skill | 66 | 15d ago | MIT | A | 18 | Claude Code, Codex |
| tmuxthe-open-agent/openagent | Skill | 5.7k | 5d ago | Apache-2.0 | A | 22 | Claude Code, Codex |
| python-lib-analyzershibing624/agentica | Skill | 360 | yesterday | Apache-2.0 | A | 23 | Claude Code |
| cronshibing624/agentica | Skill | 360 | yesterday | Apache-2.0 | A | 52 | Claude Code, Codex |
| apple-remindersthe-open-agent/openagent | Skill | 5.7k | 5d ago | Apache-2.0 | A | 34 | Claude Code, Codex |
| gogthe-open-agent/openagent | Skill | 5.7k | 5d ago | Apache-2.0 | A | 20 | Claude Code, Codex |
| slackthe-open-agent/openagent | Skill | 5.7k | 5d ago | Apache-2.0 | A | 37 | Claude Code, Codex |