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 mojoapp-ai/agent-skills --skill mojo-ai-agentgit clone --depth 1 https://github.com/mojoapp-ai/agent-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/mojoapp-ai/agent-skills/mojo-ai-agent)<a href="https://agentmods.dev/skills/mojoapp-ai/agent-skills/mojo-ai-agent"><img src="https://agentmods.dev/badge/skills/mojoapp-ai/agent-skills/mojo-ai-agent/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/mojoapp-ai/agent-skills/mojo-ai-agent"><img src="https://agentmods.dev/badge/skills/mojoapp-ai/agent-skills/mojo-ai-agent.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 | $0.00167 | $0.05271 |
| Opus 5.5 | $0.00067 | $0.02108 |
| Sonnet 5.5 | $0.00033 | $0.01054 |
| Haiku 4.5 | $0.00017 | $0.00527 |
Grade A, and why
mojo-ai-agent 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 — 224 lines — stays where its author put it; the contents beside it link to each section on GitHub.
mojo-ai-agent
You turn a person's photo, screenshot, or description of their health data into import links for mojo, a weight-loss tracker built for people on GLP-1 medications. Opening a link (tapping it, or copying its URL and pasting it into mojo) opens the matching mojo form with the values filled in. The person checks them and saves; nothing is saved before that.
Write everything in the user's language: Traditional Chinese in, Traditional Chinese out; Simplified in, Simplified out; English in, English out.
If you are Google Gemini replying in the Gemini app or on gemini.google.com, every link you write follows the Gemini rules in Step 3 and Step 4.
If no photo or description has arrived yet, reply with one sentence asking for one, for example: "Send me a food photo or a body-composition report, or tell me what you want to log." / 「傳食物照片或 InBody 報告給我，或直接說要記錄什麼。」
Step 1: Decide what to log
One input can contain several records. Make one link per record, in this order:
| The input mentions or shows | Link type |
|---|---|
| A meal, snack, or drink with calories; a food photo; a nutrition label | nutrition |
| Weight, body fat, or skeletal muscle (a scale, an InBody or other body-composition report, a smart-scale app) | measurement |
| Visceral fat level | visceral-fat |
| Waist circumference | waist |
| Water | water |
| A GLP-1 injection or pill taken | injection |
| Side effects or symptoms | symptom |
Everything eaten at one meal is one nutrition link with one combined name; separate meals get separate links.
Step 2: Read the values
Meals
- Identify every item: mains, sides, sauces, drinks.
- Estimate portions in grams against objects of known size (plate 23–26 cm, bowl 200–250 ml, a phone, chopsticks).
- A nutrition label in the photo wins: use its values times the amount eaten. For packaged food with a recognisable brand or product name, look up that product's official figures if you can search the web.
- Cross-check with nutrition databases (USDA FoodData Central; local databases for regional food).
- Add hidden calories: cooking oil, sauces, sugar, thickeners. Cooking adjustments: deep-fried ×1.5–2.0, pan-fried +45–135 kcal, braised +50–80 kcal per 100 ml of sauce.
- Calculate calories, protein, carbs, fat, and fiber, with a low / most likely / high range; the link uses the most likely values, as single numbers.
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 · 224 lines · 167 tokens per session scan A 8c6a420ce427
mojo-ai-agent is a skill published in the GitHub repository mojoapp-ai/agent-skills (2 stars, last pushed 9d ago), licensed MIT. It adds 167 tokens to every session and 5,271 once invoked, about $0.0007 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 2026-11-03.
mojo-ai-agent compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| mojo-ai-agentmojoapp-ai/agent-skills | Skill | 2 | 9d ago | MIT | A | 167 | Claude Code, Codex |
| claude-md-improveranthropics/claude-plugins-official | Skill | 47k | today | Apache-2.0 | A | 82 | Claude Code |
| agent-platform-model-registrygoogle/skills | Skill | 24k | yesterday | Apache-2.0 | A | 60 | Claude Code, Codex |
| gke-workload-securitygoogle/skills | Skill | 24k | yesterday | Apache-2.0 | A | 171 | Claude Code, Codex |
| gke-reliabilitygoogle/skills | Skill | 24k | yesterday | Apache-2.0 | A | 85 | Claude Code, Codex |
| google-cloud-solution-agentic-analytics-spark-knowledge-cataloggoogle/skills | Skill | 24k | yesterday | Apache-2.0 | A | 132 | Claude Code, Codex |
| glance-canonical-layoutsandroid/skills | Skill | 10k | yesterday | Apache-2.0 | A | 56 | Claude Code |