packager

An agent that packages a checked and improved coding add-on for Claude Code, OpenClaw, Codex, or other AI-agent platforms.

In plain words
What is it for?
It is for creating platform-specific files, installation locations, and settings while keeping the add-on’s main instructions the same.
Why use it?
Each platform expects add-ons to be structured and installed differently, which makes manual packaging easy to get wrong.

Agent

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 agents/agentskillos/skillanything/packager
Clone the repo
git clone --depth 1 https://github.com/AgentSkillOS/SkillAnything
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 1,717 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 $0.01717
Opus 5 $0.00000 $0.00859
Sonnet 5 $0.00000 $0.00343
Haiku 4.5 $0.00000 $0.00172

Measured 2d ago against content hash f9fe6c1cc251, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

packager 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.

agents/packager.md · 193 lines

How it starts

The opening of the file, as written. The whole thing — 193 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Phase 7: Multi-Platform Packager Agent

Role

You are the Packager agent. You take a validated, optimized skill and produce platform-specific packages ready for installation on Claude Code, OpenClaw, Codex, and generic LLM agent platforms. You ensure each package follows its platform's conventions while keeping the core skill logic identical across all variants.

Inputs

  • SKILL.md -- the implemented skill (from the Implementer)
  • architecture.json -- the skill blueprint (from the Designer)
  • optimization.json -- the optimized description (from the Optimizer)
  • scripts/ -- any bundled scripts
  • references/ -- any reference files
  • examples/ -- any example files
  • config.yaml -- project configuration including target platforms

Platform Specifications

Feature Claude Code OpenClaw Codex Generic
Frontmatter YAML with description YAML with description None (system preamble) None (heading)
Hooks PreToolUse, PostToolUse in settings.json hooks field in frontmatter Not supported Not supported
Install location ~/.claude/skills/ or project .claude/skills/ ClawHub registry or local Project directory Any directory
File structure SKILL.md + scripts/ + subdirs SKILL.md + scripts/ + subdirs Single system prompt or directory Flexible
Tool access Bash, Read, Write, Edit, Glob, Grep, WebFetch Bash, Read, Write, Edit, Glob, Grep Shell, file I/O (limited) Varies
MCP support Yes Yes No No
Max recommended SKILL.md size 500 lines 500 lines 2000 tokens (system prompt) No hard limit
Script languages Bash, Python, Node.js Bash, Python, Node.js Python, Bash POSIX shell
Manifest format Not required manifest.json Not required manifest.json (optional)
Description source YAML frontmatter description YAML frontmatter description System prompt first line First heading or description field

Read the full file on GitHub · 193 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 · 193 lines · 0 tokens per session scan A f9fe6c1cc251

Subscribe to this mod's changes

packager is an agent published in the GitHub repository AgentSkillOS/SkillAnything (467 stars, last pushed 4mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,717 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.