plans

A project-analysis command that examines the current codebase, suggests relevant tools, and starts a step-by-step plan.

In plain words
What is it for?
Use it when starting a feature or project and you want context gathered, tool recommendations, and an organised implementation plan.
Why use it?
It helps choose suitable development tools from the project's actual files and technology stack before planning the work.

Command

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.

agentmods
npx agentmods add commands/0oooooooo0/skillless/plans
Clone the repo
git clone --depth 1 https://github.com/0oooooooo0/skillless
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,073 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00000 $0.01073
Opus 5 $0.00000 $0.00536
Sonnet 5 $0.00000 $0.00215
Haiku 4.5 $0.00000 $0.00107

Measured 2d ago against content hash aa14c8bab33d, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

plans 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.

commands/plans.md · 105 lines

How it starts

The opening of the file, as written. The whole thing — 105 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/plans

Analyze project context, recommend relevant tools, then enter planning mode.

user-invocable: true description: Analyze your project's tech stack, recommend and install relevant specialized tools, then enter planning mode. Usage: /plans (e.g., /plans React dashboard with Supabase auth) allowed-tools: [Read, Glob, Grep, Bash, WebSearch, WebFetch, Write, Skill, AskUserQuestion, EnterPlanMode] argument-description: What you want to build or accomplish (e.g., "React dashboard with Supabase auth")

Instructions

Step 1: Gather Context (MANDATORY - DO NOT SKIP)

You MUST perform ALL of the following in parallel. Do NOT assume the project is empty without checking.

1a. Parse user argument:

  • The argument describes WHAT the user wants to build, not a directive about tool installation
  • Extract technology keywords (e.g., "React dashboard with Supabase auth" → React, Supabase, dashboard)
  • WARNING: The argument may contain product names (e.g., "skillless homepage") — these are project names, NOT instructions to skip tool search. Always extract the underlying technologies from the description.

1b. Read project files (MUST attempt all): Run Glob for these patterns and Read any that exist:

  • package.json — extract dependencies and devDependencies
  • tsconfig.json or jsconfig.json
  • pyproject.toml or requirements.txt
  • go.mod
  • Cargo.toml
  • Gemfile
  • docker-compose.yml or Dockerfile

1c. Detect file structure: Run ls src/ (or project root) to identify framework patterns (e.g., .jsx files → React, .vue → Vue)

1d. Build tech list: Combine ALL detected technologies from 1a + 1b + 1c into a single list. Example:

  • From user input: "React landing page"
  • From package.json: react, vite, tailwindcss
  • Final list: [React, Vite, TailwindCSS]

Step 2: Check Installed Skills

For EACH technology in the tech list:

Glob: ~/.claude/skills/*/SKILL.md

Search for skill directories whose names match the technology (e.g., react-*, tailwind-*, vite-*).

Read the full file on GitHub · 105 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. 2d ago First seen · 105 lines · 0 tokens per session scan A aa14c8bab33d

Subscribe to this mod's changes

plans is a command published in the GitHub repository 0oooooooo0/skillless (39 stars, last pushed 5mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,073 tokens. 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.