agentpack-operator

agentpack-operator is a skill for Claude Code, Codex from liqiongyu/agentpack. It costs 25 tokens per session (378 once invoked), scanned A, original, MIT.

Guidance for safely operating Agentpack, a tool that manages configured changes across development environments. It favors machine-readable JSON output and preview commands.

In plain words
What is it for?
Use it to check environment health, compare expected and current state, preview or explain changes, and apply updates only when explicitly requested.
Why use it?
It helps you inspect planned changes and drift before applying them, reducing accidental modifications to the environment.

Skill for Claude CodeCodex

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 skills/liqiongyu/agentpack/agentpack-operator
Any agent
npx skills add liqiongyu/agentpack --skill agentpack-operator
Clone the repo
git clone --depth 1 https://github.com/liqiongyu/agentpack

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 agentpack-operator

README.md
[![agentmods](https://agentmods.dev/badge/skills/liqiongyu/agentpack/agentpack-operator.svg)](https://agentmods.dev/skills/liqiongyu/agentpack/agentpack-operator)
Your own site
<a href="https://agentmods.dev/skills/liqiongyu/agentpack/agentpack-operator"><img src="https://agentmods.dev/badge/skills/liqiongyu/agentpack/agentpack-operator.svg" alt="Measured on agentmods" height="20"></a>
Per session 25 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 378 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 $0.00025 $0.00378
Opus 5 $0.00013 $0.00189
Sonnet 5 $0.00005 $0.00076
Haiku 4.5 $0.00003 $0.00038

Measured 5d ago against content hash 9253838400b4, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

agentpack-operator 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 5d 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.

templates/claude/skills/agentpack-operator/SKILL.md · 38 lines

What it actually says

agentpack-operator

Operate Agentpack safely and reproducibly in Claude Code.

When to use Agentpack

  • The user asks to check drift, preview changes, apply changes, or explain why changes happened.
  • You need a safe, scriptable workflow with stable --json output and guardrails.

How to operate (Claude Code)

Prefer the /ap-* slash commands installed by agentpack bootstrap:

  • /ap-doctor: validate environment and target roots
  • /ap-update: update lock + fetch (mutating; user-invoked only)
  • /ap-preview: plan + optional diff summary (read-only)
  • /ap-plan: compute desired state plan (read-only)
  • /ap-diff: diff desired vs current (read-only)
  • /ap-deploy: apply changes (mutating; user-invoked only)
  • /ap-status: compute drift (read-only)
  • /ap-explain: explain plan/diff/status (read-only)
  • /ap-evolve: propose overlay changes from drift (mutating; user-invoked only)

If the /ap-* commands are missing or outdated, run:

agentpack --target claude_code bootstrap --scope both

Safety rules

  1. Never run deploy --apply unless the user explicitly asked to apply.
  2. Always show preview/plan first, and include diff when useful.
  3. Prefer --json for automation and keep outputs small and scoped.
  4. For mutating operations in automation, always pass --yes and require explicit user approval.
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. 5d ago First seen · 38 lines · 25 tokens per session scan A 9253838400b4

Subscribe to this mod's changes

agentpack-operator is a skill published in the GitHub repository liqiongyu/agentpack (18 stars, last pushed 6mo ago), licensed MIT. It adds 25 tokens to every session and 378 once invoked, about $0.0001 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 2026-08-30.