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-workflowgit 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-workflow)<a href="https://agentmods.dev/skills/raelli/octowiz/octowiz-workflow"><img src="https://agentmods.dev/badge/skills/raelli/octowiz/octowiz-workflow/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-workflow"><img src="https://agentmods.dev/badge/skills/raelli/octowiz/octowiz-workflow.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 | $0.00139 | $0.03134 |
| Opus 5 | $0.00069 | $0.01567 |
| Sonnet 5 | $0.00028 | $0.00627 |
| Haiku 4.5 | $0.00014 | $0.00313 |
Grade B, and why
octowiz scanned grade B with 2 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
> ~/.claude/settings.json to enable memory-backed doctrine. See the octowiz README Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -s "$LITELLM_BASE_URL/v1/memory/team%3A${OCTOWIZ_NAMESPACE:-allspark}%3Aconfig%3Aretrieval-contract" \ How it starts
The opening of the file, as written. The whole thing — 308 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Octowiz Workflow Coordinator
You are the entry point for the AI-assisted coding workflow. Read the project, fetch operating doctrine from IntegraHub memory, and route to the right installed skills.
Service pre-flight
Run this first — before everything else.
Check that the two required background services are running and that the current repo is within the daemon's allowed roots. Run all three checks in parallel:
# 1. Node daemon status
launchctl list de.integrahub.octowiz-daemon 2>/dev/null
# 2. Python A2A server status (port 8765)
nc -z 127.0.0.1 8765 2>/dev/null && echo "a2a:up" || echo "a2a:down"
# 3. Current repo allowed-roots check
node -e "
const roots = (process.env.OCTOWIZ_ALLOWED_ROOTS || '').split(':').filter(Boolean);
const cwd = process.cwd();
const ok = roots.some(r => cwd.startsWith(r));
console.log(ok ? 'roots:ok' : 'roots:missing cwd=' + cwd);
" 2>/dev/null || echo "roots:unknown"
Interpreting results and fixing gaps
Node daemon not running (launchctl output has - as PID or returns nothing):
launchctl load ~/Library/LaunchAgents/de.integrahub.octowiz-daemon.plist
Wait 3 seconds, then re-run the launchctl check to confirm PID is assigned.
Python A2A server down (a2a:down):
The server is normally auto-started by the CC session hook. Start it manually:
cd ~/Documents/octowiz/apps/a2a-agent
python3 -m uvicorn main:app --host 127.0.0.1 --port 8765 &
Wait 2 seconds, then re-check with nc -z 127.0.0.1 8765.
Current repo not in allowed roots (roots:missing):
The daemon will reject tasks from this repo. Tell the user:
"This repo is not in
OCTOWIZ_ALLOWED_ROOTS. Add its path to the launchd plist and reload the daemon:# Open plist, add path to OCTOWIZ_ALLOWED_ROOTS, then: launchctl unload ~/Library/LaunchAgents/de.integrahub.octowiz-daemon.plist launchctl load ~/Library/LaunchAgents/de.integrahub.octowiz-daemon.plistPlist is at:
~/Library/LaunchAgents/de.integrahub.octowiz-daemon.plist"
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 · 308 lines · 139 tokens per session scan B 24edd7d953bb
octowiz is a skill published in the GitHub repository raelli/octowiz (2 stars, last pushed 1mo ago), licensed MIT. It adds 139 tokens to every session and 3,134 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.
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.