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 instructions/fu-jie/openwebui-extensions/gemini-mdgit 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/instructions/fu-jie/openwebui-extensions/gemini-md)<a href="https://agentmods.dev/instructions/fu-jie/openwebui-extensions/gemini-md"><img src="https://agentmods.dev/badge/instructions/fu-jie/openwebui-extensions/gemini-md.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 5.1 | $0.01682 | $0.01682 |
| Opus 5 | $0.00841 | $0.00841 |
| Sonnet 5 | $0.00336 | $0.00336 |
| Haiku 4.5 | $0.00168 | $0.00168 |
Grade A, and why
openwebui-extensions GEMINI.md 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 — 164 lines — stays where its author put it; the contents beside it link to each section on GitHub.
OpenWebUI Extensions — Gemini CLI Project Context
This file is loaded automatically by Gemini CLI as project-level instructions. Full engineering spec:
.github/copilot-instructions.md
Project Overview
openwebui-extensions is a collection of OpenWebUI plugins authored by Fu-Jie.
Repository: https://github.com/Fu-Jie/openwebui-extensions
Plugin types: actions / filters / pipes / pipelines / tools
Non-Negotiable Rules
- No auto-commit. Never run
git commit,git push, orgh pr createunless the user says "发布" / "release" / "commit it". Default output = local file changes only. - No silent failures. All errors must surface via
__event_emitter__notification or backendlogging. - No hardcoded model IDs. Default to the current conversation model; let
Valvesoverride. - Chinese responses. Reply in Simplified Chinese for all planning, explanations, and status summaries. English only for code, commit messages, and docstrings.
- Knowledge capture. Whenever you discover a non-obvious pattern, gotcha, or workaround (e.g., internal API contracts, mock object requirements, parameter injection quirks), save it to
.agent/learnings/{topic}.mdbefore ending the session. See.agent/learnings/README.mdfor format and existing entries.
Plugin File Contract
Every plugin MUST be a single-file i18n Python module:
plugins/{type}/{name}/{name}.py ← single source file, built-in i18n
plugins/{type}/{name}/README.md ← English docs
plugins/{type}/{name}/README_CN.md ← Chinese docs
Docstring (required fields)
"""
title: Plugin Display Name
author: Fu-Jie
author_url: https://github.com/Fu-Jie/openwebui-extensions
funding_url: https://github.com/open-webui
version: 0.1.0
description: One-line description.
"""
Required patterns
Valves(BaseModel)withUPPER_SNAKE_CASEfields_get_user_context(__user__)— never access__user__directly_get_chat_context(body, __metadata__)— never infer IDs ad-hoc_emit_status(emitter, msg, done)/_emit_notification(emitter, content, type)- Async I/O only — wrap sync calls with
asyncio.to_thread loggingfor backend logs — no bareprint()in production
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 · 164 lines · 1,682 tokens per session scan A 0b14372b65a1
openwebui-extensions GEMINI.md is an instructions file published in the GitHub repository Fu-Jie/openwebui-extensions (304 stars, last pushed yesterday), licensed MIT. It adds 1,682 tokens to every session, about $0.0084 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 instructions, from other repositories
Acontext AGENTS.md
Instructions for memodb-io/Acontext, covering acontext, navigation guide, plan-driven development, modules and rules.
powercontext AGENTS.md
AGENTS.md instructions for oceanbase/powercontext, covering repository guidelines, project structure & module organization, build, test, and development commands, agent skills and coding style & naming conventions.
keep-the-why AGENTS.md
AGENTS.md instructions for oliver-zehentleitner/keep-the-why, covering agents.md and working conventions (no why needed, just follow these).
remind AGENTS.md
Instructions for sandst1/remind, covering remind - development guide for ai agents, project overview, architecture, key abstractions and data models (models.py).
robrain AGENTS.md
Instructions for adelinamart/robrain, covering robrain — context management (oss self-hosted), session start (mandatory, first thing in every new chat), after every response (mandatory) and session end (last thing).
aiduMEI AGENTS.md
AGENTS.md instructions for monkey2jack/aiduMEI, covering agents.md — deploy, verify, operate aidumei, choose your engine mode, one-line prompt (canonical), install and start and prove memory is actually working.