agentmods.dev

plan-save

plan-save is a skill for Claude Code from paulbaranowski/wild-horses. It costs 83 tokens per session (5,929 once invoked), scanned A, original, MIT.

A plan-saving tool that stores plans, design documents, notes, and other files in a per-project plans folder.

In plain words
What is it for?
Use it to save markdown, JSON, YAML, or paired plan files with project-based names and dates.
Why use it?
It gives planning work a consistent place to live so it can be found and resumed later.

Skill for Claude Code

Written for Claude Code: ${CLAUDE_PLUGIN_ROOT} variable. Also seen: names the ExitPlanMode tool.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the plan-keeper plugin — 9 skills shipped together

not rated 12repo +1 21d ago A scan 83 tokens original MIT

Good fit Use it to save markdown, JSON, YAML, or paired plan files with project-based names and dates.

Compare 6 skills from other repositories ↓
View source ↗ paulbaranowski/wild-horses
Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add paulbaranowski/wild-horses
Claude Code
/plugin install plan-keeper

Made for: Claude Code.

Or install plan-keeper, the plugin that ships this one along with the rest of its 9 skills.

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 plan-save

README.md
[![agentmods](https://agentmods.dev/badge/skills/paulbaranowski/wild-horses/plan-save/github.svg)](https://agentmods.dev/skills/paulbaranowski/wild-horses/plan-save)
Your own site
<a href="https://agentmods.dev/skills/paulbaranowski/wild-horses/plan-save"><img src="https://agentmods.dev/badge/skills/paulbaranowski/wild-horses/plan-save/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.

agentmods 80×15 button for plan-save

Your own site · 80×15
<a href="https://agentmods.dev/skills/paulbaranowski/wild-horses/plan-save"><img src="https://agentmods.dev/badge/skills/paulbaranowski/wild-horses/plan-save.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 83 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 5,929 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 $0.00083 $0.05929
Opus 5 $0.00042 $0.02965
Sonnet 5 $0.00017 $0.01186
Haiku 4.5 $0.00008 $0.00593

Measured 9d ago against content hash aea00f0bd030, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

plan-save 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.

plugins/plan-keeper/skills/plan-save/SKILL.md · 278 lines

How it starts

The opening of the file, as written. The whole thing — 278 lines — stays where its author put it; the contents beside it link to each section on GitHub.

plan-save

Save one or more files from the current conversation to ~/plans/<repo>/<YYYY-MM-DD>-<topic>.<ext>. The bundled plan_keeper_cli.py handles the actual I/O (slugify, date, mkdir -p, atomic write, collision detection). This skill's job is to identify the file(s), extract a topic, pick the right extension, and route to the CLI — calling it once per file when there is more than one.

Quick reference

  • Target: ~/plans/<repo>/<YYYY-MM-DD>-<topic>.<ext> (a classified .md save with --kind becomes <YYYY-MM-DD>-<topic>--<kind>.md — see Kind in filename below).
  • <repo>: auto-derived from git remote/pwd, or override from the user's invocation — see ../../repo-derivation.md.
  • <topic>: first H1/H2 of the plan, used as the CLI's --topic (CLI slugifies). For non-markdown content with no heading, use a short phrase from the user's invocation.
  • <ext>: defaults to md. Set via --extension when the content is not markdown — see Choosing the extension.
  • Date: today, in the user's local timezone (CLI handles).
  • Collision: ask the user; never overwrite silently.
  • Content: file body verbatim — no preamble, footer, or commentary. (For .md saves — heredoc and --from-path moves — the CLI injects a Status: backlog\nCreated: <iso>\n frontmatter block if one isn't present, and fills missing Status/Created fields if a partial block is; Kind is filled only when --kind is passed. Save never injects an Agent tag — that field is the groundcrew dispatch signal, written automatically only by plan-crew on promote (plan-update can still set it on explicit user request); a body that hand-declares Agent is preserved as-is. Non-.md saves stay byte-exact. On a --from-path .md move, Created comes from the source file's birthtime, not the move time, since the plan pre-existed.)
  • --kind: the document type — one of idea / prd / reqs / design / spec / exec-plan (see ../../plan-kinds.md). Infer it from the content and pass it on .md heredoc saves; plan-do later reads it to route the plan. Fill-if-absent, .md-only. See Classifying the Kind.
  • Kind in filename: a markdown save with --kind lands at <date>-<slug>--<kind>.md (double-hyphen separator). Without --kind (or for non-.md saves) the name stays <date>-<slug>.<ext>. The -- is the sole, unambiguous Kind boundary — slugify can never emit -- inside the slug, so the stages of one project (which share a slug) group cleanly in plan-list/plan-do.
  • Multiple files: when the user has produced a paired/grouped artifact (most commonly task-list-builder's .json + .md), save each file with one save invocation, sharing --topic (and --date if you set it) so the resulting filenames pair on the base name.

Read the full file on GitHub · 278 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 9d ago First seen · 278 lines · 83 tokens per session scan A aea00f0bd030

Subscribe to this mod's changes

plan-save is a skill published in the GitHub repository paulbaranowski/wild-horses (12 stars, last pushed 21d ago), licensed MIT. It adds 83 tokens to every session and 5,929 once invoked, about $0.0004 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 2026-08-30.

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

insight-error-page

Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…

vercel/next.js · 83 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