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 skills/jirathip-dev/morsel/food-loggingnpx skills add jirathip-dev/morsel --skill food-logginggit clone --depth 1 https://github.com/jirathip-dev/morselWrote 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/jirathip-dev/morsel/food-logging)<a href="https://agentmods.dev/skills/jirathip-dev/morsel/food-logging"><img src="https://agentmods.dev/badge/skills/jirathip-dev/morsel/food-logging.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 5.1 | $0.00031 | $0.05031 |
| Opus 5 | $0.00015 | $0.02516 |
| Sonnet 5 | $0.00006 | $0.01006 |
| Haiku 4.5 | $0.00003 | $0.00503 |
Grade A, and why
food-logging 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 yesterday.
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 — 454 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Food logging (Morsel)
Use Morsel's MCP tools to record food, read the dashboard data, and correct entries. The current assistant analyzes an uploaded image; Morsel stores the structured result. There is no in-app chat or in-app AI.
The Morsel MCP server must be connected and the user authenticated before calling tools; writes are scoped to that account.
Scope and invariants
Use this skill for meal logging, food-history readback, profile and goal setup, nutrition recommendations based on the user's data, and corrections. Do not use it for clinical or medical diet advice.
Use it when the user sends a food photo or meal description, asks what they ate or how a day/week is tracking, asks whether they hit a target or what to eat to fit it, or asks to fix an entry.
Always follow these rules:
- Do not invent precise macros. Call
search_foodfor exact catalog values when possible; otherwise make an honest estimate, use a lowerconfidence, and explain the uncertainty in the item'snotes. - Macro fields sent to
log_mealare totals for the whole item as eaten, not per unit.quantityandunitare descriptive; the server never multiplies macros by them.search_foodvalues are per itsserving_sizeandserving_unit, so scale them yourself before logging (for example, 250 g at 130 kcal per 100 g becomesquantity: 250,unit: "g",calories_kcal: 325). If either serving field is absent, the serving basis is unknown: seek clarification or, if proceeding, use an explicitly noted lower-confidence estimate; never treat the returned macros as one serving. - One uploaded photo is one
log_mealcall containing one or moreitems[]. - Never log twice. To reread or correct existing data, use
get_day,update_meal_item, ordelete_meal_log. v0.1 has no tool that adds a new item to an existing meal: if a forgotten food was part of the same sitting, confirm before deleting that meal and re-logging its complete item list once; if it was a separate meal, log it separately. Never create a second log for the same sitting. - Choose the unit honestly:
gfor weighed food,mlfor measured liquid,servingfor a plate or portion,piecefor countable food, andcupfor a cup measure.unitcannot be changed byupdate_meal_item, so get it right on the first call. sourceis assigned by the server; never send it. A photo URL makes the server usephoto_vision, a barcode without a photo makes it usebarcode, and otherwise it usesmanual.- For “how am I doing” or target questions, compare the day's eaten calories
with the effective goal from
get_day(orget_goalswhen a standalone target is needed) and report the signed difference (eaten minus goal) as under, on target, or over. The effective goal is TDEE-based and activity-inclusive — activity is already factored in — so progress is eaten vs goal.get_energy_burnedmay be read for context and shown as a separate activity note; it is never subtracted from the goal. eaten_atmeans when the meal happened, not when the photo was uploaded. If it is unknown, omit it and let the server use now.- Morsel v0.1 stores a caller-supplied HTTPS
image_urlas a reference; it does not upload or fetch image bytes. Never fabricate a URL.
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.
- yesterday Changed · +61 lines 8236fbf1ad0a
- 2d ago Changed · +26 lines a4264ad68d38
- 5d ago First seen · 367 lines · 31 tokens per session scan A f27901aa0761
food-logging is a skill published in the GitHub repository jirathip-dev/morsel (0 stars, last pushed yesterday), licensed MIT. It adds 31 tokens to every session and 5,031 once invoked, about $0.0002 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…