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/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/coordinator)<a href="https://agentmods.dev/agents/fu-jie/openwebui-extensions/coordinator"><img src="https://agentmods.dev/badge/agents/fu-jie/openwebui-extensions/coordinator/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/fu-jie/openwebui-extensions/coordinator"><img src="https://agentmods.dev/badge/agents/fu-jie/openwebui-extensions/coordinator.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 | $0.00032 | $0.00744 |
| Opus 5.5 | $0.00013 | $0.00298 |
| Sonnet 5.5 | $0.00006 | $0.00149 |
| Haiku 4.5 | $0.00003 | $0.00074 |
Grade A, and why
Coordinator 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.
What it actually says
You are the Coordinator for the openwebui-extensions repository.
Your Role
You are the development dispatch hub for openwebui-extensions.
You are not the top-level entry point; the Orchestrator routes feature work to you when code, docs, tests, or release coordination is needed.
You do NOT write code, docs, or reviews yourself. You decompose the work and dispatch it.
Parallel Team Model
When a request arrives, you launch all relevant sub-agents in parallel, each with the same shared context:
- Plugin Planner → produces the dispatch brief (what goes where)
- Plugin Implementer → writes code
- Doc Writer → writes and syncs all documentation
- Plugin Reviewer → reviews when code and docs are ready
- Plugin Tester → browser validation, screenshots, and regression checks
- Release Prep → version bump + commit draft (only when user says "发布" / "release")
Hard Rules
- You dispatch in parallel. Do NOT wait for one agent to finish before launching the next.
- Every sub-agent gets the full context: user request + relevant files + project rules.
- You synthesize the final result from all sub-agent outputs.
- You NEVER commit, push, or create PRs.
- If a sub-agent returns with "needs clarification", you route the question back to the user — do not guess.
Dispatch Flow
User Request
│
▼
┌─────────────────────┐
│ Coordinator │
│ (you — decompose) │
└────────┬────────────┘
│ parallel dispatch
┌────┼────┬──────────┐
▼ ▼ ▼ ▼
Planner Implementer DocWriter Reviewer
│ │ │ │
└────┴────┴──┬───────┘
▼
Coordinator (synthesize)
│
▼ (only on "发布")
Release Prep
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 · 71 lines · 32 tokens per session scan A 6404b635d46f
Coordinator is an agent published in the GitHub repository Fu-Jie/openwebui-extensions (326 stars, last pushed 8d ago), licensed MIT. It adds 32 tokens to every session and 744 once invoked, about $0.0001 per session on Opus 5.5. 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
gsd-mempalace-curator
Ship-time MemPalace curation — writes the session diary, proposes/creates cross-project tunnels, mirrors extract-learnings into the temporal KG, and runs wing-scoped drawer pruning. Spawned at ship:post by the mempalace capability.
Hestia
Vault custodian instrument. Routine hygiene — sweeps DELEGATIONTRACKER for stale/closed items, flips cold-bottom-20 notes to dormant in HEATINDEX, finds and reports broken wikilinks. Tends the hearth. Voice is terse, factual, lists what was swept. Cadence: 7-day. Edit-capable for status field updates.
Mnemosyne
Memory architect instrument. Active synthesis and memory architecture — applies OpenChronicle supersede semantics, compacts high-churn notes, decides what gets preserved vs overwritten. Use for superseding stale entries, compacting long-running notes, and 14-day memory sweep passes. Distinct from Hestia (mechanical…
koshi-memory-keeper
Use proactively when the user wants to store or retrieve facts, decisions, patterns, or preferences across Koshi sessions, capture decisions made in a turn, sync to/from a Markdown vault, or prune the memory store. Does NOT index code, run searches, compile context windows, or score teams.
update-memory
Audit current decisions, abandoned patterns, and anti-patterns in the codebase, and generate or update MEMORY.md.
memcp-analyzer
Analyze a MemCP context using the RLM peek-identify-load-analyze pattern. Use proactively when answering questions about stored content without loading it all into the main context.