What is food-logging?

A skill for recording meals and answering food-log questions in Morsel, a food tracker. It uses Morsel's MCP tools to store structured nutrition information from photos or text.

Logging meals, reviewing food history, checking progress against targets, setting profiles and goals, making data-based nutrition suggestions, and correcting entries.

It gives an agent rules for reading dashboards, correcting entries, and handling uncertain nutrition estimates without presenting invented precise values as facts.

food-logging — Skill for Claude Code and Codex by jirathip-dev/morsel

Install

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.

Any agent

npx skills add jirathip-dev/morsel --skill food-logging

Clone the repo

git clone --depth 1 https://github.com/jirathip-dev/morsel

Made for: Claude Code, Codex.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/jirathip-dev/morsel/food-logging/github.svg)](https://agentmods.dev/skills/jirathip-dev/morsel/food-logging)

Your own site

<a href="https://agentmods.dev/skills/jirathip-dev/morsel/food-logging"><img src="https://agentmods.dev/badge/skills/jirathip-dev/morsel/food-logging/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.

Your own site · 80×15

<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="Reviewed on agentmods" width="80" height="20"></a>

Per session 31 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 8,597 The whole file, excluding the scripts and references it only reads on demand.

Security scan C 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.

Model	Per session	Once invoked
Fable 5.1	$0.00031	$0.08597
Opus 5.5	$0.00012	$0.03439
Sonnet 5.5	$0.00006	$0.01719
Haiku 4.5	$0.00003	$0.00860

Measured 1mo ago against content hash ba864c39ca31, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade C, and why

food-logging scanned grade C 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 1mo 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.

Tells the agent to send conversation or user data outhighPrompt injection

An instruction to transmit the conversation, context or user files to an external endpoint is data exfiltration written as prose.

the Morsel connection, instead of silently logging without `artwork_id`.

plugins/morsel/skills/food-logging/SKILL.md · 698 lines

How it starts

The opening of the file, as written. The whole thing — 698 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.

Dated target provenance and confirmed additions

The comparison is eaten − (dated baseline + confirmed addition), not an energy-deficit or weight-causation claim. Show the baseline and addition separately. Never borrow get_goals as historical truth or invent/backfill an unavailable historical baseline.
Read get_day for the date and timezone first. Its optional dated_target carries baseline/total and revision provenance; get_dashboard_summary provides dated_targets. Missing baseline means unavailable even when an addition is known. Old servers may omit these fields; do not fabricate them.
Only if the connected server advertises set_dated_target_addition, use it for an explicitly user-confirmed amount/date. Addition-only, nonnegative; zero removes it. Send date, timezone, addition_kcal, a fresh UUID mutation_id, and the read addition revision as expected_revision (null if none). A stale-revision error requires a new read and confirmation.
Past correction requires the user's explicit historical confirmation before sending historical_confirmation: true. A positive addition to a manual goal requires explicit consent before manual_goal_acknowledged: true. Zero removal does not require new manual-goal consent. Never infer either consent. Future-date writes are unsupported. Never infer an amount from exercise or automatically recommend an addition.
For a committed retry use the identical mutation UUID and parameters; the returned readback can reflect newer changes. Baseline edits take effect today with a revision and preserve the existing addition. Additions persist per account/date across devices, restart and authenticated agent access; they are not session-local state. Zero removal keeps revision provenance.

Read the full file on GitHub · 698 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.

1mo ago Changed · +28 lines scan A → C ba864c39ca31
1mo ago Changed · +56 lines cd441a155a92
1mo ago Changed · +9 lines 308435036ace
2mo ago Changed · +151 lines 60724176ddd9
2mo ago Changed · +61 lines 8236fbf1ad0a
2mo ago Changed · +26 lines a4264ad68d38
2mo ago First seen · 367 lines · 31 tokens per session scan A f27901aa0761

Subscribe to this mod's changes

food-logging is a skill published in the GitHub repository jirathip-dev/morsel (0 stars, last pushed 7d ago), licensed MIT. It adds 31 tokens to every session and 8,597 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it C with 1 finding (tells the agent to send conversation or user data out). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

food-logging next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
food-loggingjirathip-dev/morsel	Skill	0	7d ago	MIT	C	31	Claude Code, Codex
imagegenopenai/codex	Skill	133k	yesterday	Apache-2.0	A	113	Codex
playwright-climicrosoft/playwright	Skill	99k	yesterday	Apache-2.0	A	19	Claude Code
local-ai-agentsmicrosoft/ai-agents-for-beginners	Skill	79k	4d ago	MIT	A	200	Claude Code, Codex
systematic-debuggingobra/superpowers	Skill	313k	3d ago	MIT	A	21	Claude Code
next-cache-components-adoptionvercel/next.js	Skill	143k	yesterday	MIT	A	95	Claude Code
next-partial-prefetching-adoptionvercel/next.js	Skill	143k	yesterday	MIT	A	103	Claude Code

food-logging