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 LooseWireDev/mealforge --skill meal-planninggit clone --depth 1 https://github.com/LooseWireDev/mealforgeWrote 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/loosewiredev/mealforge/meal-planning)<a href="https://agentmods.dev/skills/loosewiredev/mealforge/meal-planning"><img src="https://agentmods.dev/badge/skills/loosewiredev/mealforge/meal-planning/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/loosewiredev/mealforge/meal-planning"><img src="https://agentmods.dev/badge/skills/loosewiredev/mealforge/meal-planning.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 | $0.00065 | $0.01489 |
| Opus 5 | $0.00032 | $0.00745 |
| Sonnet 5 | $0.00013 | $0.00298 |
| Haiku 4.5 | $0.00006 | $0.00149 |
Grade A, and why
meal-planning 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 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.
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 — 74 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Meal planning with mealforge
Plan meals collaboratively in chat, then publish the finalized plan to the mealforge app. A plan is any set of 1+ meals — a full week of dinners, a weekend of brunches, breakfast-lunch-dinner-snacks, or one special meal. Each meal is typed breakfast, lunch, dinner, or snack. Planning is conversation — as much back-and-forth as it takes. Publishing is a command — it happens exactly once, only when the user says so, and always via the two-step flow: save each recipe with create_recipe, then assemble the plan with push_meal_plan using recipeIds only.
The plan lifecycle
Plans move through three states, and the household cooks from exactly one active plan at a time:
- upcoming — pushed but not started; plans queue here.
- active — the plan being cooked from right now. Its grocery list is the one in the app. A brand-new push becomes active automatically only when nothing else is active.
- completed — cooked through; browsable history.
Lifecycle moves are user commands, not your judgment calls: complete_meal_plan when they say they're done ("we finished the week", "wrap up this plan"), activate_meal_plan when they pick what's next. Activation fails while another plan is active — complete that one first (confirm with the user).
When to use
- The user wants to plan meals ("let's plan next week", "plan me three breakfasts", "meal plan time")
- The user revises a pushed plan ("swap the salmon", "add a couple of snacks to the plan")
- The user tells you to push/send the plan to mealforge
- The user wants to switch plans, finish a plan, or bring back a favorite plan
How to apply
1. Gather context before proposing anything
get_active_meal_planandlist_meal_plans(limit 6) — see what's cooking now and what was cooked recently; don't repeat recent meals unless asked. Each meal'scookedAt(null = not cooked yet) is the household's check-off, so you can answer "what's left to cook this week?".- If the user wants something they've had before ("one of our favorites", "that carnitas"), find it with
list_favoritesorsearch_recipes, confirm withget_recipe, and remember its recipeId — reuse the id at push time instead of recreating the recipe. - For "one of our favorite plans", use
list_meal_planswithfavoritesOnly: trueand rebuild from its recipeIds.
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.
- 9d ago First seen · 74 lines · 65 tokens per session scan A 0f3a0691e67a
meal-planning is a skill published in the GitHub repository LooseWireDev/mealforge (1 stars, last pushed 1mo ago), licensed MIT. It adds 65 tokens to every session and 1,489 once invoked, about $0.0003 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
i18n Completeness Audit
Comprehensive audit of internationalization — translation key parity, hardcoded strings, date/number/currency formatting, email translations, metadata translations, and locale routing. Use when asked to audit i18n, translations, localization, internationalization, or multilingual support.
adhoc-flow
Workflow for the rest of tasks: lightweight documentation, build, track, synchronize, etc.
olares-search
Olares search via olares-cli search — the Desktop global search over Drive files, Sync (Seafile) libraries, Google Drive, Dropbox, Wise/Knowledge, and installed applications, with paging and JSON output. On Olares 1.12.7+ one search drive (alias search files) covers all four file sources. Use for Olares search…
cortex-profile
View and manage your cognitive profile — how you think, work patterns, blind spots, and cross-domain connections. Use when the user says 'show my profile', 'how do I work', 'what are my patterns', 'cognitive style', 'blind spots', 'methodology', or at the start of a session to load context. Also use 'rebuild profile'…
add-mechanic
Add game mechanics with correct GDScript 4.x patterns -- movement, health, inventory, save/load.
speak
Provides concise spoken alerts and digests through the mcp-tts MCP server. It should be selected proactively for significant AI and DevOps transitions: a substantial plan is ready, a long build/test/deploy/release/monitoring phase changes state, a major task completes, a terminal blocker or exhausted retry budget…