agentmods.dev

okforge-webui AGENTS.md

A repository guide for okforge-webui, a web application that manages knowledge bases: collections of information that can be searched, compiled into wikis, and published. It maps the backend, browser interface, job queue, deployment files, and key documentation.

In plain words
What is it for?
Use it when changing the FastAPI backend, vanilla-JavaScript frontend, MCP server, knowledge-base jobs, or deployment setup in okforge-webui.
Why use it?
It gives a coding agent the project structure and working conventions before it edits code, reducing guesswork in an unfamiliar repository.

Instructions file for CodexOpenCode

5 19d ago A scan 554 tokens original MIT
View the source file okforge/okforge-webui
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 instructions/okforge/okforge-webui/agents-md
Clone the repo
git clone --depth 1 https://github.com/okforge/okforge-webui

Made for: Codex, OpenCode.

Per session 554 This file is loaded in full into every session.
When invoked 554 The same file — it is already loaded in full.
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 $0.00554 $0.00554
Opus 5 $0.00277 $0.00277
Sonnet 5 $0.00111 $0.00111
Haiku 4.5 $0.00055 $0.00055

Measured yesterday against content hash 058961a971e4, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

okforge-webui AGENTS.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 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.

AGENTS.md · 43 lines

How it starts

The opening of the file, as written. The whole thing — 43 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md — okforge-webui repo map

This repo is the manager for okforge knowledge bases: a FastAPI backend + vanilla-JS frontend, a strictly serial job queue, an MCP server, and Apache/systemd deploy machinery. The heavy lifting lives in two PyPI packages pinned in requirements.txt: the okforge engine (ingestion, wiki compilation, query) and okforge-vision-ocr (page-by-page VLM OCR + translation console scripts).

Map

  • README.md — what it does, install, run, configuration (env vars).
  • docs/OPERATIONS.md — operating KBs day to day: anatomy, copying, re-ingest semantics, Obsidian safety, Quartz publishing, troubleshooting.
  • webui/PLAN.md — architecture and API design notes (historical but accurate about the shape: five pipeline stages, serial queue).
  • webui/api.py — FastAPI routes + SSE log tailing.
  • webui/jobs.py — the job queue and every job runner (pilot, ocr, translate, add, full, reocr, extract, recompile, publish). The single worker is a load-bearing design decision.
  • webui/kb.py, webui/probe.py — KB discovery/init and PDF probing.
  • webui/config.py — all configuration; env-var driven, no secrets in code (hosted endpoints' API keys arrive via OKFORGE_WEBUI_ENDPOINTS, label=url|key|model).
  • webui/mcp_server.py — the /mcp streamable-HTTP server.
  • webui/static/ — the frontend (no build step).
  • webui/deploy.sh + webui/deploy/ — Apache vhost + systemd unit.

Conventions

  • The job queue is strictly serial by design — don't parallelize adds; the engine holds a per-KB ingest lock and single-slot LLM hosts choke on concurrent OCR.
  • Never restart the backend (or run deploy.sh) while a job is running.
  • Frontend changes need no restart — rsync webui/static/ to the docroot.
  • KB directories stay pure: no tool installs inside them.
  • Integration tests use throwaway scratch KBs only; queries are read-only and safe anywhere.

Read the full file on GitHub · 43 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 · 43 lines · 554 tokens per session scan A 058961a971e4

Subscribe to this mod's changes

okforge-webui AGENTS.md is an instructions file published in the GitHub repository okforge/okforge-webui (5 stars, last pushed 19d ago), licensed MIT. It adds 554 tokens to every session, about $0.0028 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 2026-08-31.

Backend and APIsFrontendLLMMemory and contextjob-queueknowledge-baselocal-llmmcpmcp-server
Related

Other instructions, from other repositories

llm-wiki-agent GEMINI.md

Instructions for SamurAIGPT/llm-wiki-agent, covering llm wiki agent — schema & workflow instructions, how to use, directory layout, page format and ingest workflow.

SamurAIGPT/llm-wiki-agent · 1,590 tokens

OpenKB AGENTS.md

Instructions for VectifyAI/OpenKB, covering agents.md — openkb map for coding agents, read next, dev commands, module map (openkb/) and hard invariants.

VectifyAI/OpenKB · 681 tokens

Starcat AGENTS.md

Instructions for starcat-app/Starcat, covering agents.md, 🚨 硬性铁律（每次写代码前必读，违反即返工）, 🌿 git 分支与 worktree（强制）, 🧭 主进度索引（每次开工前必读） and 状态符号（与功能实现总览.md 同步）.

starcat-app/Starcat · 7,077 tokens

DocMason copilot-instructions.md

Instructions for JetXu-LLM/DocMason, covering docmason github copilot notes and copilot-specific delta.

JetXu-LLM/DocMason · 482 tokens

DeepRefine-Skill GEMINI.md

Instructions for HKUST-KnowComp/DeepRefine-Skill, covering deeprefine skill for gemini cli, core behavior and commands.

HKUST-KnowComp/DeepRefine-Skill · 372 tokens

zissa-wiki CLAUDE.md

Instructions for MetamusicX/zissa-wiki, covering claude.md — research wiki schema, identity, architecture, folder conventions and raw/.

MetamusicX/zissa-wiki · 4,192 tokens