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/colinds/forkable-mcp/forkablenpx skills add colinds/forkable-mcp --skill forkablegit clone --depth 1 https://github.com/colinds/forkable-mcpWhat 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 | $0.00053 | $0.01445 |
| Opus 5 | $0.00026 | $0.00723 |
| Sonnet 5 | $0.00011 | $0.00289 |
| Haiku 4.5 | $0.00005 | $0.00145 |
Grade A, and why
forkable 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 2d 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 — 143 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Forkable
Use the forkable MCP tools for account data and meal changes. This skill contains the shared tool,
write, and recovery rules for all Forkable workflows. If the tools are not available, use the
forkable-setup skill.
Find the delivery first
Call list_deliveries before other delivery tools. Use the returned deliveryId; do not derive an
ID from a date. A date can have more than one delivery, so distinguish deliveries by service and club.
Re-list before a write if the conversation has been long or a meal has changed. Piece IDs can change after a replacement.
The default list window begins today and extends 21 days. For past deliveries, supply both from
and to. Forkable normally posts the next week's suggestions on Friday; an empty future range may
mean that the week is not available yet.
The delivery fields are server-reported context. Do not infer a write deadline, capacity decision, company limit, or authoritative charge from them. Forkable decides whether a mutation is allowed.
Read and choose meals
Use these tools in order as appropriate:
recommend_mealsfor Forkable's ranked suggestions.search_itemswhen the user names an ingredient, dish, or cuisine.get_menusto browse a delivery or load one item's modifier details.
Treat recommendations as suggestions rather than policy. Apply the user's stated preferences and show a short set of suitable options with prices and any images returned by the tools.
Menu item IDs can repeat across menus. Keep the menuId with every item. Both set_meal and
set_meal_all require the exact (menuId, itemId) returned by a menu read tool.
Load item details before setting modifiers. Modifier and option names are accepted only when they resolve uniquely; IDs are preferable when names repeat. Preserve an explicitly empty optional selection instead of restoring an old or default choice.
Local preferences
If file access is available, store user-stated food preferences in
~/.forkable-mcp/preferences.md and read it before choosing a meal. This file is an agent
convention, not a Forkable setting.
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.
- 2d ago First seen · 143 lines · 53 tokens per session scan A 8acfccd4c4fb
forkable is a skill published in the GitHub repository colinds/forkable-mcp (2 stars, last pushed 8d ago), licensed MIT. It adds 53 tokens to every session and 1,445 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
xcodebuildmcp-structured-output-review
Use when reviewing XcodeBuildMCP structured output schema changes, schema versioning, manifest outputSchema metadata, and JSON fixture compatibility.
opik-diagnose
Surface the Opik traces worth a developer's attention, ranked by signal — errors, failed tool calls, latency, regressions, and low online-eval scores — plus Diagnostics issues. Reads live/production traces via the SDK (searchtraces and agentinsights) and works with no MCP; uses the MCP issue entity when connected.…
cortex-automate
Set up automation — prospective memory triggers, neuro-symbolic rules, and CLAUDE.md sync. Use when the user says 'remind me when', 'trigger when', 'create a rule', 'auto-remember', 'sync to CLAUDE.md', 'push insights', 'set up trigger', 'when I open this file', 'when this keyword appears', or when you want to…
tabnexus-mcp-evals
Generate, validate, and run isolated Codex-to-TabNexus MCP evaluations with a curated 600-query dataset, executable gold tool labels, safety checks, and best-of-three stability scoring. Use when testing TabNexus MCP tool coverage, Agent behavior, regression quality, destructive-action safety, prompt changes, or a…
compare
Structured comparison of 2+ alternatives with consistent criteria and decision matrix.
maya-shot-export
Pipeline stage — shot-level export: frame ranges, cameras, FBX / Alembic packaging for editorial. Use when packaging shot data for downstream departments. Not for full pipeline publish (maya-pipeline) or scene assembly (maya-scene-assembly).