capacities-mcp: Skill for Claude Code

.agents/skills/packmind-onboard/SKILL.md

packmind-onboard is a skill for Claude Code, Codex from Im-Hal-9K/capacities-mcp. It costs 38 tokens per session (2,203 once invoked), scanned A, a copy of packmind-onboard, MIT.

An automated Packmind onboarding tool that examines a codebase and prepares draft coding standards and commands. Packmind is a tool for documenting and applying team coding practices.

In plain words
What is it for?
Use it to create or select a Packmind package, analyze code patterns, and prepare standards and commands with file-based evidence.
Why use it?
It reduces the manual work of finding existing patterns and turning them into reusable project guidance, while keeping the analysis read-only and drafts reviewable.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: names the AskUserQuestion tool; installed under .agents/ (shared by several agents).

This is Im-Hal-9K/capacities-mcp's own configuration. It tells Claude Code and Codex how to work on capacities-mcp 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 capacities-mcp configures →

Reuse

Borrowing it

Nothing to install: this file belongs to Im-Hal-9K/capacities-mcp. 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/Im-Hal-9K/capacities-mcp/main/.agents/skills/packmind-onboard/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/Im-Hal-9K/capacities-mcp

Made for: Claude Code, Codex.

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 packmind-onboard

README.md
[![agentmods](https://agentmods.dev/badge/skills/im-hal-9k/capacities-mcp/packmind-onboard/github.svg)](https://agentmods.dev/skills/im-hal-9k/capacities-mcp/packmind-onboard)
Your own site
<a href="https://agentmods.dev/skills/im-hal-9k/capacities-mcp/packmind-onboard"><img src="https://agentmods.dev/badge/skills/im-hal-9k/capacities-mcp/packmind-onboard/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 packmind-onboard

Your own site · 80×15
<a href="https://agentmods.dev/skills/im-hal-9k/capacities-mcp/packmind-onboard"><img src="https://agentmods.dev/badge/skills/im-hal-9k/capacities-mcp/packmind-onboard.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 38 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,203 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 98% copy Near-identical to another mod 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 $0.00038 $0.02203
Opus 5 $0.00019 $0.01102
Sonnet 5 $0.00008 $0.00441
Haiku 4.5 $0.00004 $0.00220

Measured 10d ago against content hash 2a64854151dd, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

packmind-onboard 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 10d 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.

Origin

This is a copy

98% identical to packmind-onboard — 13 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

.agents/skills/packmind-onboard/SKILL.md · 329 lines

How it starts

The opening of the file, as written. The whole thing — 329 lines — stays where its author put it; the contents beside it link to each section on GitHub.

packmind-onboard

Run "packmind-cli --version" to get the current cli installation.

Find the highest version at or below the cli version in this list:

  • 0.16.0
  • 0.23.0 Remember this value as $PACKMIND_CLI_VERSION for the rest of the skill.

Action skill. Provides complete automated onboarding for Packmind:

  1. Creates or selects a package
  2. Analyzes codebase for patterns
  3. Generates draft Standards and Commands
  4. Creates items via CLI

Automatic package creation when none exist, user selection when packages are available.

Guarantees

  • Read-only analysis. Analysis phase does not modify any project files.
  • Drafts before creation. All items are written as drafts first, allowing review before creation.
  • Preserve existing. Never overwrite existing artifacts. If a slug already exists, create -2, -3, etc.
  • Evidence required. Every reported insight must include file-path evidence (and line ranges when feasible).
  • Focused output. Max 5 Standards and 5 Commands generated per run.
  • Graceful failure. Partial failures don't lose successful work; failed drafts are preserved.
  • User control. When packages exist, users confirm package selection before creation.

Definitions

  • Pattern (non-linter): a convention a linter cannot reliably enforce (module boundaries, cross-domain communication, workflow parity, error semantics, etc).
  • Evidence: path[:line-line] entries; omit line ranges only when the file isn't text-searchable.

Step 0 — Introduction

Print exactly:

I'll start the Packmind onboarding process. I'll create your first standards and commands and send them to your Packmind organization. This usually takes ~3 minutes.

Step 1 — Get Repository Name

Get the repository name for package naming:

basename "$(git rev-parse --show-toplevel)"

Remember this as the repository name for package creation in Step 2.

Also run packmind-cli whoami and extract the Host: value from the output. Remember this URL for the completion summary.

Read the full file on GitHub · 329 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. 10d ago First seen · 329 lines · 38 tokens per session scan A 2a64854151dd

Subscribe to this mod's changes

packmind-onboard is a skill published in the GitHub repository Im-Hal-9K/capacities-mcp (2 stars, last pushed 2mo ago), licensed MIT. It adds 38 tokens to every session and 2,203 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. It is 98% identical to packmind-onboard, differing in 13 lines, and is treated as a copy.