agentmods.dev

save-plan

save-plan is a skill for Claude Code from RamonBedin/mcp-game-deck. It costs 31 tokens per session (713 once invoked), scanned A, original, MIT.

A tool for saving a conversation plan as a file in a project’s GameDeck plans folder.

In plain words
What is it for?
Use it to name and save the latest plan or plan text, after choosing where its content should come from.
Why use it?
It preserves a plan so it can be reused later instead of remaining only in the conversation.

Skill for Claude Code

Written for Claude Code: user-invocable in frontmatter. Also seen: names the AskUserQuestion tool.

Part of the mcp-game-deck plugin — 24 skills, 10 agents shipped together

not rated 6repo 2mo ago A scan 31 tokens original MIT

Good fit Use it to name and save the latest plan or plan text, after choosing where its content should come from.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/ramonbedin/mcp-game-deck/save-plan
View source ↗ RamonBedin/mcp-game-deck
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 RamonBedin/mcp-game-deck --skill save-plan
Clone the repo
git clone --depth 1 https://github.com/RamonBedin/mcp-game-deck

Made for: Claude Code.

Or install mcp-game-deck, the plugin that ships this one along with the rest of its 24 skills, 10 agents.

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 save-plan

README.md
[![agentmods](https://agentmods.dev/badge/skills/ramonbedin/mcp-game-deck/save-plan.svg)](https://agentmods.dev/skills/ramonbedin/mcp-game-deck/save-plan)
Your own site
<a href="https://agentmods.dev/skills/ramonbedin/mcp-game-deck/save-plan"><img src="https://agentmods.dev/badge/skills/ramonbedin/mcp-game-deck/save-plan.svg" alt="Measured on agentmods" 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 713 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. 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 $0.00031 $0.00713
Opus 5 $0.00015 $0.00357
Sonnet 5 $0.00006 $0.00143
Haiku 4.5 $0.00003 $0.00071

Measured 8d ago against content hash 81b93fe2d16c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

save-plan 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 8d 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.

Plugin~/skills/save-plan/SKILL.md · 76 lines

What it actually says

When this skill is invoked:

  1. Parse the plan name from the user's message. If they wrote /save-plan setup-2d-scene, the name is setup-2d-scene. If no argument was provided, ask via AskUserQuestion:

    • "What should this plan be called?" (free-text)

  2. Validate the name: lowercase ASCII letters, digits, and hyphens only; must start with a letter or digit; 1–64 characters. If invalid, explain why and re-ask via AskUserQuestion in the same turn.

  3. Ask the user where to get the plan content via AskUserQuestion. Use this exact question and these three options:

    Question: "Where should I get the plan content for <name>?"

    Option A — label: "Use the plan from our conversation" description: "I just shared a plan above and want to save that one."

    Option B — label: "I'll paste the plan content" description: "Provide the plan as free text in the answer."

    Option C — label: "Cancel" description: "Don't save anything."

    If the user picks A: look at the most recent assistant message in this conversation that resembles a plan (markdown headers, numbered sections, structured outline, etc.) and use its full body verbatim. If there's no clear plan candidate in recent history, re-ask with only options B and C.

    If the user picks B: use whatever they provide as the "Other (specify)" free text as the plan body verbatim.

    If the user picks C: respond "Cancelled." and stop.

  4. Compose a one-line description (≤80 characters) summarizing the plan. Goes into the YAML frontmatter so the Plans tab list can show it next to the name.

  5. Resolve the auto-suffixed filename at ProjectSettings/GameDeck/plans/<name>.md (relative to cwd, which is UNITY_PROJECT_PATH). Use the Glob tool to check existence:

    • First try <name>.md
    • If it exists, try <name>-2.md, <name>-3.md, ..., up to <name>-99.md
    • Pick the first slot that doesn't exist. If all 99 are taken, tell the user to delete some plans with that prefix first and stop.

  6. Write the file using the Write tool. The body must be:

    ---
description: <one-line summary from step 4>
---

<plan body from step 3, verbatim>

    Don't reformat the plan body — preserve whatever structure it had.

  7. Confirm to the user with the actual filename used:

    • No collision: "Saved as <name>.md."
    • With suffix: "Saved as <name>-N.md (a plan named <name> already existed, so I bumped the suffix)."
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. 8d ago First seen · 76 lines · 31 tokens per session scan A 81b93fe2d16c

Subscribe to this mod's changes

save-plan is a skill published in the GitHub repository RamonBedin/mcp-game-deck (6 stars, last pushed 2mo ago), licensed MIT. It adds 31 tokens to every session and 713 once invoked, about $0.0002 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.

Planning
Related

Other skills, from other repositories

systematic-debugging

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

obra/superpowers · 21 tokens

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

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

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…

vercel/next.js · 103 tokens

chronicle

Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…

microsoft/vscode · 72 tokens