bite-ai-dietitian: Skill for Claude Code

.claude/skills/log-meal/SKILL.md

log-meal is a skill for Claude Code from aligundogdu/bite-ai-dietitian. It costs 68 tokens per session (651 once invoked), scanned B, original, MIT.

A meal-logging workflow that records food and drink with estimates for calories, protein, carbohydrates, fat, and fiber. It also handles shared pots or trays by calculating the eaten portion.

In plain words
What is it for?
It helps log meals, snacks, drinks, and corrections in the correct daily file and optionally sync food-only information to a public site.
Why use it?
It preserves the user's original report while making assumptions visible, so later corrections do not silently replace the source information.

Skill for Claude Code

Written for Claude Code: installed under .claude/.

This is aligundogdu/bite-ai-dietitian's own configuration. It tells Claude Code how to work on bite-ai-dietitian itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything bite-ai-dietitian configures →

Reuse

Borrowing it

Nothing to install: this file belongs to aligundogdu/bite-ai-dietitian. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/aligundogdu/bite-ai-dietitian/main/.claude/skills/log-meal/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/aligundogdu/bite-ai-dietitian

Made for: Claude Code.

Wrote 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.

agentmods badge for log-meal

README.md
[![agentmods](https://agentmods.dev/badge/skills/aligundogdu/bite-ai-dietitian/log-meal/github.svg)](https://agentmods.dev/skills/aligundogdu/bite-ai-dietitian/log-meal)
Your own site
<a href="https://agentmods.dev/skills/aligundogdu/bite-ai-dietitian/log-meal"><img src="https://agentmods.dev/badge/skills/aligundogdu/bite-ai-dietitian/log-meal/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.

agentmods 80×15 button for log-meal

Your own site · 80×15
<a href="https://agentmods.dev/skills/aligundogdu/bite-ai-dietitian/log-meal"><img src="https://agentmods.dev/badge/skills/aligundogdu/bite-ai-dietitian/log-meal.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 68 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 651 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00068 $0.00651
Opus 5.5 $0.00027 $0.00260
Sonnet 5.5 $0.00014 $0.00130
Haiku 4.5 $0.00007 $0.00065

Measured 9d ago against content hash 9dae5bf793a1, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade B, and why

log-meal scanned grade B with 1 finding 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 9d 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.

Strips warnings and disclaimersmediumAnti-refusal

Omitting safety caveats hides risk from the user and is a common jailbreak preamble.

- Don't moralise about a meal or call a snack "unplanned" before asking what it was for.
.claude/skills/log-meal/SKILL.md · 25 lines

How it starts

The opening of the file, as written. The whole thing — 25 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Log a meal

Steps

  1. Find the day and the meal. Use the date the food was eaten, not the date it was reported. "Lunch I cooked this morning" is still lunch. If the time matters (late-night rules in PROFILE.md) and is unclear, ask once.
  2. Quote the user. Under each meal, keep the user's own words in a > 📌 User: quote line. When numbers are later disputed, the quote is the ground truth.
  3. Estimate per item. One table row per item: kcal, protein, carbs, fat, fiber (and optional collagen). Use the bases in ASSUMPTIONS.md first. If an item has no base yet, pick a reasonable one and write it under the table as Base: 100 g ≈ X kcal / Y P / Z C / W F. Cooked vs raw weight must be explicit.
  4. State assumptions, don't interrogate. If a detail changes the number by less than ~50 kcal, assume and note it ("pan-fried, no oil assumed"). Ask only when the difference is large (fatty vs lean mince, full-fat vs skim, a whole pot vs one serving).
  5. Batch cooking ("pot math"). For a pot or tray: sum the raw ingredients, record the cooked total weight (ask if unknown, otherwise assume and say so), then portion = eaten g / cooked g × pot totals. Write the pot once in the first meal, reference it in later meals, track what is left.
  6. Running snacks. Nuts, seeds, small nibbles that repeat through the day go into one "daily total" row, updated each time, not a new row per handful.
  7. Totals. Update the meal total and the day total. Mark the day (open) until the user says it is done or the next day starts. Never warn about being under target on an open day.
  8. Corrections become rules. If the user corrects an assumption (e.g. "bread is always whole wheat", "our mince is lean"), fix the entry and add the rule to ASSUMPTIONS.md so it never happens again.
  9. Sync to bite/ (optional). Follow bite/CONTENT_GUIDE.md. Food names, grams and macros only. The privacy hook will block health or medication words; if it fires, rewrite, don't work around it.

Read the full file on GitHub · 25 lines

Changes

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.

  1. 9d ago First seen · 25 lines · 68 tokens per session scan B 9dae5bf793a1

Subscribe to this mod's changes

log-meal is a skill published in the GitHub repository aligundogdu/bite-ai-dietitian (5 stars, last pushed 9d ago), licensed MIT. It adds 68 tokens to every session and 651 once invoked, about $0.0003 per session on Opus 5.5. A static security scan graded it B with 1 finding (strips warnings and disclaimers). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-10-19.

Related

Other skills, from other repositories

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…

microsoft/ai-agents-for-beginners · 200 tokens

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

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…

vercel/next.js · 95 tokens

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.

microsoft/vscode · 53 tokens

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…

microsoft/vscode · 71 tokens

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…

vercel/next.js · 83 tokens