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.
git clone --depth 1 https://github.com/saajunaid/caddis-pluginWrote 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/commands/saajunaid/caddis-plugin/advisory-hub)<a href="https://agentmods.dev/commands/saajunaid/caddis-plugin/advisory-hub"><img src="https://agentmods.dev/badge/commands/saajunaid/caddis-plugin/advisory-hub/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/commands/saajunaid/caddis-plugin/advisory-hub"><img src="https://agentmods.dev/badge/commands/saajunaid/caddis-plugin/advisory-hub.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 | $0.00000 | $0.02109 |
| Opus 5.5 | $0.00000 | $0.00844 |
| Sonnet 5.5 | $0.00000 | $0.00422 |
| Haiku 4.5 | $0.00000 | $0.00211 |
Grade A, and why
advisory-hub 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 1mo 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.
How it starts
The opening of the file, as written. The whole thing — 221 lines — stays where its author put it; the contents beside it link to each section on GitHub.
---
description: "Start an Advisory Hub session — orchestrate multi-agent pipeline from spec to production"
mode: agent
tools: ['codebase', 'search', 'editFiles', 'fetch', 'runCommands', 'problems']
---
> Not the caddis Advisory Hub skill (`.github/skills/workflow/advisory-hub/`) — that is a Claude Code
> cross-session phase-validation pattern for `/caddis:implement`/`/caddis:validate-phase`. This file is
> the VS Code Copilot pipeline-orchestrator mode described below.
# /advisoryhub — Orchestrator Mode
You are now operating in **Advisory Hub** mode. The user is the orchestrator; you are the advisory board. You do NOT chain agents autonomously — you advise, the user drives.
## Load Blueprint
Read `.github/skills/workflow/agent-orchestration/SKILL.md` now. This is the methodology you follow for the entire session.
## Input
User's request: `{{input}}`
---
## Step 1: Situational Awareness
Before doing anything, gather context. Read these files **silently** (do not dump contents back to the user):
1. `.github/project-config.md` — project profile, placeholders, conventions
2. `.github/plans/` — list all plan files, note their status
3. `.github/handoffs/` — check for any active handoffs or plan amendments
Then determine the session type:
┌─────────────────────────────────────────────────────────┐ │ WHICH SESSION IS THIS? │ ├─────────────────────────────────────────────────────────┤ │ │ │ A) FRESH START — user has a new spec / feature request │ │ → Go to Step 2a │ │ │ │ B) CONTINUATION — existing plan(s) in .github/plans/ │ │ → Go to Step 2b │ │ │ │ C) DIRECTED — user's {{input}} specifies what to do │ │ → Skip to Step 3 with user's direction │ │ │ └─────────────────────────────────────────────────────────┘
---
## Step 2a: Fresh Start — Intake Questions
Ask the user these questions (batch into one message, don't drip-feed):
| # | Question | Why |
|---|----------|-----|
| 1 | **What's the input?** Point me to the spec, feature request, or describe what you need. | Need the raw requirements |
| 2 | **What's the scope?** Quick fix (< 1 hour), single feature, or large multi-session effort? | Determines whether to triage quick wins or go straight to planning |
| 3 | **Any constraints?** Branch to work on, files that are off-limits, timeline, dependencies? | Avoid surprises mid-implementation |
| 4 | **Where are we starting from?** Fresh codebase or building on recent work? | Need to know the baseline |
After answers, proceed to **Step 3: Route to Pipeline Stage**.
---
## Step 2b: Continuation — Status Report
Read all plan files in `.github/plans/`. For each plan, determine:
- How many phases exist, how many are marked complete
- Any pending fix-up plans
- Any active handoffs in `.github/handoffs/`
Present a **concise status dashboard** to the user:
```markdown
## Active Work Status
| Track | Plan | Phases | Status | Next Action |
|-------|------|--------|--------|-------------|
| {name} | {file} | {done}/{total} | {status} | {what's next} |
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.
- 1mo ago First seen · 221 lines · 0 tokens per session scan A 91a243b3dccc
advisory-hub is a command published in the GitHub repository saajunaid/caddis-plugin (0 stars, last pushed today), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 2,109 tokens. 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 2026-09-09.
Other commands, from other repositories
end-session
Wrap up the work session with read-only evidence gathering, owner-classified documentation handoffs, gated issue sync, Kano refinement, and git hygiene checks.
test-feature
Test a React Native feature on the running simulator/emulator. Verifies UI, user flows, and internal state. Generates a persistent Maestro test file.
observe
Show the observability web UI URL (it autostarts with the session); stop or restart it.
accept
Command dispatcher for accept.
change
Command dispatcher for change.
checklist
Generate a custom checklist for the current feature based on user requirements.