wise-init

wise-init is a skill for Claude Code, Codex from e1024kb/wise-claude. It costs 135 tokens per session (4,245 once invoked), scanned B, original, MIT.

A first-time setup wizard for wise, guiding installation of its required Python, Node.js, GitHub CLI, and file-conversion tools.

In plain words
What is it for?
Use it when installing wise for the first time or after an update may require new dependencies. Running it again checks only what is still missing.
Why use it?
It replaces repeated dependency checks and scattered installation prompts with one guided setup, then records the results for later runs.

Skill for Claude CodeCodex

Installs and runs on its own, but its text points at files inside its plugin — anything it tells you to read at a ${CLAUDE_PLUGIN_ROOT} path is only there once the plugin is installed. Installing the plugin gets both.

Part of the wise plugin — 32 skills, 22 agents, 1 hook shipped together

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/e1024kb/wise-claude/wise-init
Any agent
npx skills add e1024kb/wise-claude --skill wise-init
Clone the repo
git clone --depth 1 https://github.com/e1024kb/wise-claude

Made for: Claude Code, Codex.

Or install wise, the plugin that ships this one along with the rest of its 32 skills, 22 agents, 1 hook.

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 wise-init

README.md
[![agentmods](https://agentmods.dev/badge/skills/e1024kb/wise-claude/wise-init.svg)](https://agentmods.dev/skills/e1024kb/wise-claude/wise-init)
Your own site
<a href="https://agentmods.dev/skills/e1024kb/wise-claude/wise-init"><img src="https://agentmods.dev/badge/skills/e1024kb/wise-claude/wise-init.svg" alt="Measured on agentmods" height="20"></a>
Per session 135 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,245 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. 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 $0.00135 $0.04245
Opus 5 $0.00068 $0.02122
Sonnet 5 $0.00027 $0.00849
Haiku 4.5 $0.00014 $0.00424

Measured 4d ago against content hash 26c5f0d93d00, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade B, and why

wise-init scanned grade B with 1 finding 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 4d 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.

Asks for rootmediumPrivilege escalation

A mod that escalates privileges can change anything on the machine, not only the project.

it's a user-space install with no sudo and no system packages.
plugins/wise/skills/wise-init/SKILL.md · 396 lines

How it starts

The opening of the file, as written. The whole thing — 396 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/wise-init — first-time setup wizard

Why this skill exists

Before 0.41.0, every workflow-adjacent wise skill ran scripts/bootstrap-deps.sh as its first step — probing Python, Node, and the gh CLI on every invocation. That was correct but slow on the hot path and clumsy for fresh installs: the user got piecemeal "install X, now install Y, now gh auth login" across successive skill invocations instead of one guided walkthrough.

/wise-init is that walkthrough. It probes each dep in turn, shows installer options with exact commands to paste when something's missing, pauses for the user to run them, re-probes, and finally writes a registry file the workflow engine consumes as a fast-path on every subsequent run. Re-runs are cheap — the wizard skips deps that are already present.

The registry lives at ${CLAUDE_PLUGIN_ROOT}/.wise-init-registry.yaml. That's inside the plugin install dir on purpose — it gets wiped on every /plugin install wise@…, which is exactly the invalidation signal we want: "the plugin updated, something new might be required, user should re-init".

Arguments

This skill takes no arguments. Ignore anything the user types beyond the skill name.

Procedure

1. Preamble

Print one short paragraph to the user introducing the flow. Keep it under 4 lines:

First-time setup. I'll walk you through the system deps wise needs —
Python 3, Node ≥22, the gh CLI (with auth), and markitdown (file →
markdown text extraction). Re-runs are safe: I skip what's already
installed. After this I cache the probe results so future workflow
runs skip the live check.

2. Python (and its pip modules)

2a. Probe.

bash "${CLAUDE_PLUGIN_ROOT}/scripts/init.sh" probe-python

The probe emits bare KEY=VALUE lines — STATUS, BINARY, VERSION, MODULE_YAML, MODULE_ULID, MODULE_TYPING_EXTENSIONS (all three probes reuse the same bare key names by design; see init.sh). Read them into per-dep Claude-side variables — referred to below as PY_STATUS, PY_BINARY, PY_VERSION, PY_MODULE_*.

Read the full file on GitHub · 396 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. 4d ago First seen · 396 lines · 135 tokens per session scan B 26c5f0d93d00

Subscribe to this mod's changes

wise-init is a skill published in the GitHub repository e1024kb/wise-claude (4 stars, last pushed 8d ago), licensed MIT. It adds 135 tokens to every session and 4,245 once invoked, about $0.0007 per session on Opus 5. A static security scan graded it B with 1 finding (asks for root). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.