extend

extend is a command for Claude Code from illinigirl/meal-planner-mcp. It costs 15 tokens per session (443 once invoked), scanned A, original, MIT.

A command for extending deliberately simplified parts of a meal-planning codebase, using tests before code changes.

In plain words
What is it for?
Use it to update ingredient parsing, unit conversions, singularization, or configurable pantry staples, then run the project’s tests and code checks.
Why use it?
It provides a consistent way to improve selected areas while preserving rules about units, food classification, and ingredient distinctions.

Command for Claude Code

Written for Claude Code: argument-hint in frontmatter. Also seen: mentions CLAUDE.md.

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.

agentmods
npx agentmods add commands/illinigirl/meal-planner-mcp/extend
Clone the repo
git clone --depth 1 https://github.com/illinigirl/meal-planner-mcp

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 extend

README.md
[![agentmods](https://agentmods.dev/badge/commands/illinigirl/meal-planner-mcp/extend.svg)](https://agentmods.dev/commands/illinigirl/meal-planner-mcp/extend)
Your own site
<a href="https://agentmods.dev/commands/illinigirl/meal-planner-mcp/extend"><img src="https://agentmods.dev/badge/commands/illinigirl/meal-planner-mcp/extend.svg" alt="Measured on agentmods" height="20"></a>
Per session 15 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 443 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00015 $0.00443
Opus 5 $0.00008 $0.00221
Sonnet 5 $0.00003 $0.00089
Haiku 4.5 $0.00002 $0.00044

Measured 5d ago against content hash 45eff70cbf39, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

extend 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 5d 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.

.claude/commands/extend.md · 34 lines

What it actually says

Extend one of this repo's deliberate-simplification seams (see CLAUDE.md → "Deliberate simplifications"). If "$ARGUMENTS" names a seam, do that one; otherwise pick the highest-value seam and say why in one sentence first.

House rules for this repo (don't violate these):

  • Logic goes in a PURE module with a direct test; the MCP/CLI adapters stay thin.
  • Write the FAILING test first, then implement until it's green.
  • No silent unit conversion — same item in different units stays on separate shopping lines.
  • Classification is course-based, not title-based (course is the normalized field; unknown course → treat as a main, never silently drop).
  • Canonicalization preserves real distinctions (red onion ≠ yellow onion).
  • Finish with python -m pytest -q green and ruff check src/mealplanner tests clean.

Seam reference:

  • parseringredients.parse_ingredient: handle 1 (14 oz) can tomatoes, "a pinch", multi-unit lines.
  • units — add an EXPLICIT conversion table (3 tsp → 1 tbsp) applied only on request, never silently.
  • singularize — extend the _SINGULAR rule table or swap in inflect.
  • pantry — make core.PANTRY_STAPLES per-user / configurable.
  • leftovers-b — cook-once-eat-twice via produces/uses recipe tags (roast chicken → chicken soup). The seed already carries roast-chicken + a cooked chicken soup waiting for it. Keep it behind the same plan_week signature.
  • importer — add a Paprika / Mealie / plain-JSON importer behind store.import_*, alongside the Plan to Eat one.
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. 5d ago First seen · 34 lines · 15 tokens per session scan A 45eff70cbf39

Subscribe to this mod's changes

extend is a command published in the GitHub repository illinigirl/meal-planner-mcp (0 stars, last pushed 2mo ago), licensed MIT. It adds 15 tokens to every session and 443 once invoked, about $0.0001 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.