octowiz-doctowiz

octowiz-doctowiz is a skill for Claude Code from raelli/octowiz. It costs 138 tokens per session (7,310 once invoked), scanned B, original, MIT.

A diagnostic and setup skill for the Octowiz and AELLI integration, including checks, monitoring, setup guidance, upgrades, and targeted fixes.

In plain words
What is it for?
Use it to diagnose health, watch live activity, configure a new installation, migrate an older version, or fix a specific error.
Why use it?
It helps explain why the integration, hooks, or advisories are not working and provides concrete commands for addressing reported problems.

Skill for Claude Code

Written for Claude Code: $CLAUDE_PLUGIN_ROOT variable. Also seen: reads .claude/ paths; mentions Claude Code.

Not installable: its command points at a path on the author’s own machine, so it runs nowhere else. The line is /Users/you/Documents/myproject:/Users/you/Documents/other.

Part of the octowiz plugin — 3 skills, 4 hooks shipped together

Good fit Use it to diagnose health, watch live activity, configure a new installation, migrate an older version, or fix a specific error.

Compare 6 skills from other repositories ↓
Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add raelli/octowiz
Claude Code
/plugin install octowiz

Made for: Claude Code.

Or install octowiz, the plugin that ships this one along with the rest of its 3 skills, 4 hooks.

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 octowiz-doctowiz

README.md
[![agentmods](https://agentmods.dev/badge/skills/raelli/octowiz/octowiz-doctowiz/github.svg)](https://agentmods.dev/skills/raelli/octowiz/octowiz-doctowiz)
Your own site
<a href="https://agentmods.dev/skills/raelli/octowiz/octowiz-doctowiz"><img src="https://agentmods.dev/badge/skills/raelli/octowiz/octowiz-doctowiz/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 octowiz-doctowiz

Your own site · 80×15
<a href="https://agentmods.dev/skills/raelli/octowiz/octowiz-doctowiz"><img src="https://agentmods.dev/badge/skills/raelli/octowiz/octowiz-doctowiz.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 138 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 7,310 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 2 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00138 $0.07310
Opus 5 $0.00069 $0.03655
Sonnet 5 $0.00028 $0.01462
Haiku 4.5 $0.00014 $0.00731

Measured 12d ago against content hash d514280bbb77, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade B, and why

octowiz-doctowiz scanned grade B with 2 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 12d 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.

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

All required vars should be in `~/.claude/settings.json` under `"env"`:

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

curl -s -m 3 "http://localhost:${OCTOWIZ_A2A_PORT:-8765}/health" 2>/dev/null \
skills/octowiz-doctowiz/SKILL.md · 634 lines

How it starts

The opening of the file, as written. The whole thing — 634 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Doctowiz — Octowiz + AELLI Doctor

The Octowiz doctor. Diagnoses the full octowiz + AELLI integration stack, interprets every failure with a plain-language explanation and a concrete fix command, monitors live activity, and guides setup from scratch.

Mode detection

Read the user's invocation text (or context of the conversation) to pick the mode:

Trigger words Mode
(nothing / "diagnose" / "check" / "health") Diagnose (default)
"monitor" / "watch" / "tail" / "live" Monitor
"setup" / "install" / "configure" / "start fresh" Setup guide
"update" / "upgrade" / "migrate" / "I'm on 0.5" / "old version" Update helper (Mode 4)
"fix " / describes a specific error Targeted fix (Mode 5)

When uncertain, run Diagnose — it gives the most complete picture.


Mode 1 — Diagnose (default)

Run the full diagnostic, interpret every non-passing check, and offer guided fixes.

Step 1: Version inventory

Before running the diagnostic, collect version information:

# Octowiz plugin version
node -e "const p=require('$CLAUDE_PLUGIN_ROOT/package.json'); console.log('octowiz', p.version)"

# Installed plugin cache version
ls -1 ~/.claude/plugins/cache/integrahub/octowiz/ 2>/dev/null | tail -1

# AELLI version (if running locally)
node -e "try{const p=require(require('os').homedir()+'/Documents/aelli/package.json'); console.log('aelli', p.version)}catch(e){console.log('aelli not found locally')}"

# LiteLLM / AELLI env vars
echo "AELLI_BASE_URL:       ${AELLI_BASE_URL:-(not set)}"
echo "AELLI_AUTH_TOKEN:     ${AELLI_AUTH_TOKEN:-(not set)}"
echo "AELLI_LITELLM_BASE:   ${AELLI_LITELLM_BASE:-(not set)}"
echo "AELLI_ROUTER_URL:     ${AELLI_ROUTER_URL:-(not set)}"
echo "OCTOWIZ_ALLOWED_ROOTS:${OCTOWIZ_ALLOWED_ROOTS:-(not set)}"

# Local Python A2A server version (public /health since 0.9.16)
curl -s -m 3 "http://localhost:${OCTOWIZ_A2A_PORT:-8765}/health" 2>/dev/null \
  || echo "A2A server: not reachable (starts on next session open)"

# AELLI gateway health
[ -n "$AELLI_BASE_URL" ] && curl -s "$AELLI_BASE_URL/health" \
  -H "Authorization: Bearer $AELLI_AUTH_TOKEN" \
  | python3 -c "import sys,json; d=json.load(sys.stdin); print('aelli/litellm', d.get('status','?'))" 2>/dev/null \
  || echo "AELLI gateway: not reachable (expected if remote)"

Read the full file on GitHub · 634 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. 12d ago First seen · 634 lines · 138 tokens per session scan B d514280bbb77

Subscribe to this mod's changes

octowiz-doctowiz is a skill published in the GitHub repository raelli/octowiz (2 stars, last pushed 1mo ago), licensed MIT. It adds 138 tokens to every session and 7,310 once invoked, about $0.0007 per session on Opus 5. A static security scan graded it B with 2 findings (reads agent configuration directories, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories