planner: Skill for Claude Code

.claude/skills/new-idea/SKILL.md

new-idea is a skill for Claude Code from nickmisasi/planner. It costs 45 tokens per session (860 once invoked), scanned A, original, MIT.

A planning command for adding an idea, milestone, or feature to an existing project. A worktree is a separate working copy of a Git repository, allowing development without switching the main checkout.

In plain words
What is it for?
Use it to select a project, describe new work, create its identifier and branch name, and set up worktrees for dependent repositories.
Why use it?
It turns a rough idea into a named, trackable piece of work and prepares the repositories it depends on. This reduces setup work before implementation begins.

Skill for Claude Code

Written for Claude Code: installed under .claude/. Also seen: names the AskUserQuestion tool.

This is nickmisasi/planner's own configuration. It tells Claude Code how to work on planner itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything planner configures →

Reuse

Borrowing it

Nothing to install: this file belongs to nickmisasi/planner. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/nickmisasi/planner/main/.claude/skills/new-idea/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/nickmisasi/planner

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 new-idea

README.md
[![agentmods](https://agentmods.dev/badge/skills/nickmisasi/planner/new-idea.svg)](https://agentmods.dev/skills/nickmisasi/planner/new-idea)
Your own site
<a href="https://agentmods.dev/skills/nickmisasi/planner/new-idea"><img src="https://agentmods.dev/badge/skills/nickmisasi/planner/new-idea.svg" alt="Measured on agentmods" height="20"></a>
Per session 45 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 860 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 $0.00045 $0.00860
Opus 5 $0.00023 $0.00430
Sonnet 5 $0.00009 $0.00172
Haiku 4.5 $0.00005 $0.00086

Measured 7d ago against content hash 26372931922b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

new-idea 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 7d 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/skills/new-idea/SKILL.md · 92 lines

How it starts

The opening of the file, as written. The whole thing — 92 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Add a new idea, milestone, or feature to an existing project. Sets up worktrees across dependent repos so development can begin immediately.

Instructions

When the user invokes /new-idea, follow these steps:

1. Select the Project

Read registry.yaml to get the list of projects. If there's only one, confirm it. If multiple, use AskUserQuestion to let the user pick which project this idea belongs to.

2. Gather Idea Information

Use AskUserQuestion to collect:

  • Idea name — Short, descriptive name for this feature/milestone/refactor
  • Initial description — What's the rough concept? (Can be brief — this will be fleshed out)

3. Generate the Slug and Branch Name

Create a URL-safe slug from the idea name (lowercase, hyphens, no special chars). The CLI auto-assigns the next sequential ID (001, 002, etc.).

Generate a branch name in the format: IDEA-<NNN>-<short-description>

  • The short description should be at most 3 words, derived from the idea name
  • Examples: IDEA-001-agent-sandboxing, IDEA-003-tool-filtering, IDEA-002-mcp-apps

4. Ask About Dependent Repositories

Read projects/<project>/project.yaml to get the project's repo list. Present these repos and ask which ones this idea will touch.

Use AskUserQuestion:

This project has the following repositories:
<list repos with url and local_path>

Which repos will this idea involve? (Select all that apply, or add others)
Also — are there any additional repos not listed above that this idea depends on?

Infer suggestions based on the idea description. For example, if the idea mentions "plugin" and the project has a plugin repo, pre-select it.

5. Run the CLI to Scaffold the Idea

python3 bin/planning new-idea \
  --project project-slug \
  --name "Idea Name" \
  --slug idea-slug \
  --description "Initial description to seed the Background section of the spec"

6. Create Worktrees Across Dependent Repos

Use the CLI to create worktrees in all selected repos with the generated branch name:

Read the full file on GitHub · 92 lines

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. 7d ago First seen · 92 lines · 45 tokens per session scan A 26372931922b

Subscribe to this mod's changes

new-idea is a skill published in the GitHub repository nickmisasi/planner (5 stars, last pushed 4mo ago), licensed MIT. It adds 45 tokens to every session and 860 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.

Related

Other skills, from other repositories

prowler-commit

Creates professional git commits following conventional-commits format. Trigger: When creating commits, after completing code changes, when user asks to commit.

prowler-cloud/prowler · 33 tokens

gh-auth-isolation

Safely manage multiple GitHub identities (EMU + personal) in agent workflows.

github/gh-aw · 20 tokens

comet-github

A routing guide for Comet-related GitHub work. It directs requests about pull requests, issues, CI failures, ideas, and fixes to the appropriate review or implementation process.

rpamis/comet · 72 tokens

github-skill

Work with GitHub via the gh CLI — clone repositories, create/list/merge pull requests, create/list issues, and run any other gh command (API calls, workflow runs, releases, repo administration). List operations return parsed JSON.

zeenie-ai/OpenCompany · 51 tokens

codex-autoresearch

Run autonomous, measurable experiments in a Git repository: change one hypothesis, verify a numeric metric, keep improvements, and revert failures. Use when the user wants Codex to keep iterating toward a numeric target in the foreground or as a detached background run. Do not use for ordinary one-shot coding…

leo-lilinxiao/codex-autoresearch · 80 tokens

changelog-composer

Generates structured changelogs and release notes from git history and PRs, classifying breaking changes, features, fixes, performance, docs. Triggers on: "generate changelog", "write release notes", "what changed since", "prepare release", "release notes for", "diff since tag".

Mathews-Tom/armory · 67 tokens