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.
npx skills add raelli/octowiz --skill octowiz-setupgit clone --depth 1 https://github.com/raelli/octowizWrote 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.
[](https://agentmods.dev/skills/raelli/octowiz/octowiz-setup)<a href="https://agentmods.dev/skills/raelli/octowiz/octowiz-setup"><img src="https://agentmods.dev/badge/skills/raelli/octowiz/octowiz-setup/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.
<a href="https://agentmods.dev/skills/raelli/octowiz/octowiz-setup"><img src="https://agentmods.dev/badge/skills/raelli/octowiz/octowiz-setup.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00057 | $0.02919 |
| Opus 5 | $0.00028 | $0.01460 |
| Sonnet 5 | $0.00011 | $0.00584 |
| Haiku 4.5 | $0.00006 | $0.00292 |
Grade B, and why
setup scanned grade B with 2 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
Guide the developer to add to `~/.claude/settings.json`: Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
If this fails, check: Is LiteLLM running? `curl -s "${LITELLM_BASE_URL}/health"` How it starts
The opening of the file, as written. The whole thing — 336 lines — stays where its author put it; the contents beside it link to each section on GitHub.
octowiz:setup
Setup orchestrator for the Octowiz Bridge. Runs only the phases with gaps.
When invoked
Invoked by octowiz:octowiz when the live check reports gaps. Do not invoke directly.
Pre-flight: run the live check
octowiz-cache check
Parse the JSON output. Store hard_gaps and advisory_gaps.
If hard_gaps is empty: delete ONBOARDING.md from the current directory if it exists, then return control to octowiz:octowiz to show the A/B/C/D menu.
Create ONBOARDING.md
If .octowiz/setup-state.json does not exist in the current directory, create ONBOARDING.md:
# Octowiz Setup
## Environment (per-machine)
- [STATUS] superpowers plugin
- [STATUS] mattpocock-skills plugin
- [STATUS] antfu-skills plugin
- [STATUS] LiteLLM env vars (LITELLM_BASE_URL + API key)
- [STATUS] LiteLLM routing cache (verified within 24h)
- [STATUS] Project namespace seeded in LiteLLM Memory
## Project (per-repo)
- [STATUS] antfu skills setup (if TypeScript/Vue stack)
- [STATUS] Agent instructions file (AGENTS.md / CLAUDE.md / GEMINI.md)
- [STATUS] mattpocock-skills section in agent file (## Agent skills)
## Next step
[What is about to run]
Use [x] for passing checks, [ ] for gaps, [!] for advisory items.
Phase 1: Plugins
Run if any of these are in hard_gaps: plugin_superpowers, plugin_mattpocock-skills, plugin_antfu-skills
For each missing plugin, explain what it does and why it is required, then show the install command. Verify after each install.
superpowers
Provides workflow discipline skills — TDD, brainstorming, code review, git worktrees, subagent-driven development.
claude plugins install superpowers
Verify: ls ~/.claude/plugins/cache/*/superpowers/ 2>/dev/null | head -1
mattpocock-skills
Provides domain documentation and issue management skills — grill-with-docs, to-prd, to-issues, triage, diagnose, prototype.
Note: install ID is mattpocock-skills; slash-command namespace is /mattpocock-skills: — these match.
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.
- 12d ago First seen · 336 lines · 57 tokens per session scan B 4cbc9c9a12f9
setup is a skill published in the GitHub repository raelli/octowiz (2 stars, last pushed 1mo ago), licensed MIT. It adds 57 tokens to every session and 2,919 once invoked, about $0.0003 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.
Other skills, from other repositories
plan-feature-brainstorm
A placeholder phase in a feature-planning workflow that returns a fixed mock result. A mock result is simulated output used to test whether the surrounding workflow moves between phases correctly.
plan-feature-decision
A planning workflow stub that returns a simulated approval decision for a feature plan.
plan-feature-discuss
A mock discussion step for a feature-planning workflow. It currently returns an approved test result instead of holding a real discussion.
plan-feature-persist
A mock step that saves a feature plan to Markdown files. It currently returns an approved test result instead of performing real file persistence.
plan-feature-plan
A mock planning step for deciding how a new feature should be built. It currently returns an approved test result instead of performing real planning.
auto
A one-command workflow that runs a feature from initial research, discussion, and planning through task breakdown, verification, and retrospective. It may research first when the request is unclear.