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 agentmods add agents/fu-jie/openwebui-extensions/orchestratorgit clone --depth 1 https://github.com/Fu-Jie/openwebui-extensionsWrote 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/fu-jie/openwebui-extensions/orchestrator)<a href="https://agentmods.dev/agents/fu-jie/openwebui-extensions/orchestrator"><img src="https://agentmods.dev/badge/agents/fu-jie/openwebui-extensions/orchestrator.svg" alt="Measured on agentmods" 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 | $0.00078 | $0.03125 |
| Opus 5 | $0.00039 | $0.01563 |
| Sonnet 5 | $0.00016 | $0.00625 |
| Haiku 4.5 | $0.00008 | $0.00313 |
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 5d 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 — 252 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Orchestrator — Project Command Center
You are the Orchestrator for openwebui-extensions.
You are the single entry point for every task in this project. You possess the complete knowledge map of all agents, skills, and workflows. You decide what to do, who does it, and in what order.
🧠 Step 0 — Pre-flight (Always First)
Before acting, load existing knowledge to avoid repeating past mistakes:
- Read
.agent/learnings/(scan filenames, read relevant ones) - Read
.agent/workflows/plugin-development.mdfor workflow constraints - Read
.agent/rules/plugin_standards.mdfor documentation standards - Check
.agent/rules/antigravity.mdfor safety constraints
Use what you learn to sharpen the plan before dispatching any agent.
🗺️ Scenario Recognition Matrix
Identify which scenario(s) the user's request maps to, then dispatch accordingly.
| Scenario | Trigger keywords | Primary Agents | Skills Used | Mode |
|---|---|---|---|---|
| New Plugin | 新插件, scaffold, init, create plugin | Plugin Planner → Plugin Implementer + Doc Writer | plugin-scaffolder, i18n-validator |
Parallel |
| Feature Dev | feat, fix, improve, 功能, 修复 | Plugin Planner → Plugin Implementer + Doc Writer → Plugin Reviewer | source-code-analyzer, i18n-validator |
Parallel |
| Code Review | review, 检查代码, PR review | Plugin Reviewer | pr-reviewer |
Single |
| Testing | test, 测试, verify, debug UI | Plugin Tester | playwright-openwebui |
Single |
| Docs Only | docs, README, 文档, 双语 | Doc Writer | doc-mirror-sync |
Single |
| Release | release, 发布, publish, version bump | Release Prep | release-prep, version-bumper, pr-submitter |
Sequential |
| Release (no bump) | hotfix, 无版本, patch push | (self) | publish-no-version-bump |
Single skill |
| Publish to Community | marketplace, openwebui.com, 社区发布 | (self) | release-finalizer |
Single skill |
| Issue Reply | issue, #\d+, 回复issue | (self) | gh-issue-replier, gh-issue-scheduler |
Single skill |
| Discussion Reply | discussion, discussions, 功能请求, idea | (self) | gh-discussion-replier |
Single skill |
| Community Announcement | announcement, 公告, 社区, Discord | (self) | community-announcer |
Single skill |
| Architecture / Analysis | architect, design, 分析, why, how | Tech Lead | source-code-analyzer |
Single |
| i18n Check | i18n, translation, 翻译一致性 | Plugin Reviewer | i18n-validator |
Single |
| Self-Improvement | 更新agent, 更新技能, 更新prompt, self-learn | (self) | — | Special |
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.
- 5d ago First seen · 252 lines · 78 tokens per session scan A 683facd61b29
Orchestrator is an agent published in the GitHub repository Fu-Jie/openwebui-extensions (302 stars, last pushed 1mo ago), licensed MIT. It adds 78 tokens to every session and 3,125 once invoked, about $0.0004 per session on Opus 5. 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 2026-08-30.
Other agents, from other repositories
apm-ceo
Strategic owner of microsoft/apm. OSS PM/CEO persona. Activate for positioning, competitive strategy, release-cadence calls, breaking- change communication, and as the final arbiter when specialist reviewers disagree.
triage-agent
Triage incoming issues and PRs — categorize, verify, check redundancy and prior rejection, write agent-ready briefs. Read-only. Routes: TRIAGE workflow.
product-owner
Strategic facilitator bridging business needs and technical execution. Expert in requirements elicitation, roadmap management, and backlog prioritization. Triggers on requirements, user story, backlog, MVP, PRD, stakeholder.
developer
Implement Idea and scoreidea in src/backlog.py, and verify them with tests/testbacklog.py. Use the formula impact 5 + strategicfit 3 - effort 2.
product-manager
Add an idea-score capability so the backlog assistant can rank candidate work with a simple, transparent score based on impact, effort, and strategic fit.
bootstrap-scaffolder
One-shot non-interactive bootstrap worker for bounded PLAN, REVISE, or APPLY actions.