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 skills add justnau1020/claude-os --skill plan-featuresgit clone --depth 1 https://github.com/justnau1020/claude-osWrote 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.
[](https://agentmods.dev/skills/justnau1020/claude-os/plan-features)<a href="https://agentmods.dev/skills/justnau1020/claude-os/plan-features"><img src="https://agentmods.dev/badge/skills/justnau1020/claude-os/plan-features/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.
<a href="https://agentmods.dev/skills/justnau1020/claude-os/plan-features"><img src="https://agentmods.dev/badge/skills/justnau1020/claude-os/plan-features.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00034 | $0.01911 |
| Opus 5 | $0.00017 | $0.00955 |
| Sonnet 5 | $0.00007 | $0.00382 |
| Haiku 4.5 | $0.00003 | $0.00191 |
Grade A, and why
plan-features 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.
How it starts
The opening of the file, as written. The whole thing — 241 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Plan Features
Generate a structured execution plan document that enables multi-team agent work with worktree isolation. The plan is the product -- execution is mechanical downstream.
Invocation
/plan-features [description of features/changes] [--doc path/to/requirements.md] [--output path/to/plan.md]
Examples:
/plan-features "add WebSocket support for real-time updates"/plan-features --doc docs/brainstorms/SECURITY_ROADMAP.md --output docs/brainstorms/EXECUTION_PLAN.md/plan-features "refactor plugin system to support async initialization and health checks"
What This Skill Produces
A single markdown document containing everything an executor needs to run teams without ambiguity:
- File Conflict Table -- which files each team touches (determines merge order)
- Dependency Graph -- what blocks what (determines parallelism)
- Critical Path -- the longest sequential chain
- Per-Team Specs -- files, deliverables, validation, "read these first" lists
- Risk Register -- what could break and how to mitigate
- Session Grouping -- how to batch teams for execution
Process
Step 1: Understand the Scope
Read the user's feature description or requirements doc. If the scope is ambiguous, ask clarifying questions BEFORE proceeding:
- What's in scope vs out of scope?
- Any hard constraints (prohibited libraries, deadline, legal)?
- Any prior decisions already made?
- What test infrastructure exists?
Step 2: Codebase Reconnaissance
Spawn an Explore agent to map the affected areas:
- Which files/modules will be touched?
- What are the existing patterns in those files?
- What test coverage exists for those areas?
- What's the current middleware/hook/plugin stack order?
This is the most important step. The file list drives everything.
Step 3: Decompose into Teams
Break the work into teams where each team:
- Has a single, clear deliverable
- Touches a bounded set of files
- Can be validated independently
- Maps to one worktree agent
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.
- 8d ago First seen · 241 lines · 34 tokens per session scan A 42fb3a26ad9a
plan-features is a skill published in the GitHub repository justnau1020/claude-os (3 stars, last pushed 5mo ago), licensed Apache-2.0. It adds 34 tokens to every session and 1,911 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.
Other skills, from other repositories
skill-curator
A Chinese-language evaluator for deciding whether developer tools and agent resources are suitable for a curated collection. It checks real repositories, installation paths, activity, duplicates, and security boundaries using evidence.
env-manager
An environment-variable manager for project settings stored outside the code, often in .env files. It checks variable definitions and usage while keeping secret values out of reports and terminal output.
git-workflow
A guide for handling Git repository work safely, including status checks, branches, commits, pushes, pull requests, and rebasing. Git is a version-control system that records code changes and coordinates work between developers.
perf-profiler
A performance investigation guide that uses repeatable measurements and profiling evidence to find where software spends time or resources. Profiling records runtime activity such as CPU use, memory use, database work, or network delays.
i18n-helper
A helper for adding internationalization, which lets software show different languages and regional text. It finds user-visible text written directly in code and moves it into language files.
log-analyzer
A log-analysis helper that reads application and system logs to find unusual patterns and likely causes. Logs are records of events such as errors, requests, warnings, and service activity.