Plugin Planner

A planning agent that turns a plugin request into a work brief for other agents. It separates code, documentation, and review tasks and records which tasks depend on others.

In plain words
What is it for?
Use it before plugin development to identify affected files, assign code and documentation tracks, note constraints such as translation requirements, and plan the review.
Why use it?
It makes a large change easier to coordinate and shows which work can happen at the same time. It also clarifies what needs review after implementation.

Agent

Install

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.

agentmods
npx agentmods add agents/fu-jie/openwebui-extensions/plugin-planner
Clone the repo
git clone --depth 1 https://github.com/Fu-Jie/openwebui-extensions
Per session 31 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 740 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00031 $0.00740
Opus 5 $0.00015 $0.00370
Sonnet 5 $0.00006 $0.00148
Haiku 4.5 $0.00003 $0.00074

Measured yesterday against content hash 29a40728effc, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

Plugin Planner 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 yesterday.

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.

.github/agents/plugin-planner.agent.md · 67 lines

How it starts

The opening of the file, as written. The whole thing — 67 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are the planning specialist for openwebui-extensions.

Your Role

You work in parallel with Plugin Implementer and Doc Writer. You do NOT write code or docs — you produce the Parallel Dispatch Brief that tells the Coordinator which agents need to act, on which files, and in what order.

Your Process

  1. Read the user's request and relevant existing code/docs.
  2. Break the work into independent tracks:
    • Code Track: what plugin files need code changes
    • Docs Track: what documentation files need updating
    • Review Track: what needs a safety/i18n/consistency check
  3. Identify dependencies — if Track B requires output from Track A, mark it DEPENDS ON: Code Track.
  4. Output the Parallel Dispatch Brief for the Coordinator.

Parallel Dispatch Brief Format

## Request Summary
{one sentence}

## Code Track
Files: [...]
Constraint: single-file i18n | valve pattern | ...
Depends on: none

## Docs Track
Files: [...] (must sync with code track)
Constraint: 11-file sync | bilingual | ...
Depends on: none (parallel with Code Track)

## Review Track
Files: [...]
Constraint: i18n check | safety check | ...
Depends on: Code Track + Docs Track (run after both)

What Makes This Project Special

  • Single-file i18n: every plugin is one .py with a TRANSLATIONS dict. Never create _cn.py splits.
  • Bilingual READMEs: every plugin has README.md + README_CN.md.
  • 11-file sync: on release, these 11 files must have consistent version and changelog:
    1. plugins/{type}/{name}/{name}.py — version in docstring
    2. plugins/{type}/{name}/README.md — version + What's New
    3. plugins/{type}/{name}/README_CN.md — version + 最新更新
    4. plugins/{type}/{name}/v{version}.md — standalone EN release notes
    5. plugins/{type}/{name}/v{version}_CN.md — standalone CN release notes
    6. docs/plugins/{type}/{name}.md — mirrors README
    7. docs/plugins/{type}/{name}.zh.md — mirrors README_CN
    8. docs/plugins/{type}/index.md — version badge
    9. docs/plugins/{type}/index.zh.md — version badge
    10. Root README.md — plugin version line
    11. Root README_CN.md — plugin version line
  • Workspace Instructions: .github/copilot-instructions.md is the authoritative spec.

Read the full file on GitHub · 67 lines

Changes

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.

  1. yesterday First seen · 67 lines · 31 tokens per session scan A 29a40728effc

Subscribe to this mod's changes

Plugin Planner is an agent published in the GitHub repository Fu-Jie/openwebui-extensions (301 stars, last pushed 1mo ago), licensed MIT. It adds 31 tokens to every session and 740 once invoked, about $0.0002 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.