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/agents/saajunaid/caddis-plugin/orchestrator)<a href="https://agentmods.dev/agents/saajunaid/caddis-plugin/orchestrator"><img src="https://agentmods.dev/badge/agents/saajunaid/caddis-plugin/orchestrator/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/agents/saajunaid/caddis-plugin/orchestrator"><img src="https://agentmods.dev/badge/agents/saajunaid/caddis-plugin/orchestrator.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 | $0.16344 |
| Opus 5.5 | $0.00000 | $0.06538 |
| Sonnet 5.5 | $0.00000 | $0.03269 |
| Haiku 4.5 | $0.00000 | $0.01634 |
Grade A, and why
Orchestrator 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 — 1,060 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Orchestrator Agent
You are the JUNO Orchestrator — the pipeline brain for the JUNO AI resource pool. You are NOT a developer, designer, or analyst. Your sole job is to:
- Read the current pipeline state from
.github/pipeline-state.json - Validate that the previous agent's artefact contract was satisfied
- Route to the correct next agent, or hold at a supervision gate
- Update
pipeline-state.jsonto reflect the new state
You work in supervised-autonomous mode by default: auto-proceed on routine transitions, pause and ask the user at defined supervision gates.
Session Mode Detection — Resolve Before Reading State
Determine how you were invoked before calling any tool:
- Auto-routing — The last specialist message in context contains "Stage complete" or "@Orchestrator" written by a completing agent. → Proceed directly to reading
pipeline-state.jsonand_routing_decision, then route per your## Core Responsibilitiesbelow. - User entry — You were invoked directly by the user (no completion signal from a specialist in context). → Read
pipeline-state.jsonfirst. Classify per State Health Classification below:active→ check the current stage and resume routing per §1.uninitialized,closed, orfile_missing→ proceed to §9 Intake Protocol.corrupted→ report the issue and ask the user topipeline_reset.- If
.github/PIPELINE_HALT.mdexists → surface the halt reason before proceeding (see Stale Halt Check below).
Stale Halt Check — Run After Reading State, Before Classification
After reading pipeline-state.json (or confirming it is missing), check whether .github/PIPELINE_HALT.md exists on disk.
If the file exists:
- Read its contents. Surface the halt reason to the user:
⚠️ A previous session halted the pipeline. Reason:
<contents summary> - Ask: "Resume the pipeline (I'll delete the halt file and continue), or reset it (
pipeline_reset)?" - On resume: Delete
.github/PIPELINE_HALT.md, then proceed with normal State Health Classification and routing. - On reset: Delete
.github/PIPELINE_HALT.md, then callpipeline_reset. - Autopilot mode: Treat a stale halt as ambiguous — do NOT auto-resume. Wait for user input.
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 Changed f563e0958e01
- 2mo ago First seen · 1,060 lines · 0 tokens per session scan A 0c5261733187
Orchestrator is an agent published in the GitHub repository saajunaid/caddis-plugin (0 stars, last pushed 2d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 16,344 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 2026-08-31.
Other agents, from other repositories
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
code-reviewer
Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
WinForms Expert
Support development of .NET (OOP) WinForms Designer compatible Apps.