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/jiang198012/workbuddian/claude-mdgit clone --depth 1 https://github.com/jiang198012/workbuddianWrote 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/jiang198012/workbuddian/claude-md)<a href="https://agentmods.dev/instructions/jiang198012/workbuddian/claude-md"><img src="https://agentmods.dev/badge/instructions/jiang198012/workbuddian/claude-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 | $0.02005 | $0.02005 |
| Opus 5 | $0.01002 | $0.01002 |
| Sonnet 5 | $0.00401 | $0.00401 |
| Haiku 4.5 | $0.00200 | $0.00200 |
Grade A, and why
workbuddian CLAUDE.md scanned grade A with 1 finding 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.
Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
- `tests/acpClient.test.ts` mocks `child_process` (`jest.mock('child_process')`) to drive the ACP transport without a real CLI; `tests/api.test.ts` / `tests/providerCallbacks.test.ts` instead mock `providers/codebuddy/ac How it starts
The opening of the file, as written. The whole thing — 57 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
What this is
Workbuddian is a desktop-only Obsidian community plugin (isDesktopOnly: true, Obsidian ≥ 1.7.2) that embeds the local WorkBuddy / CodeBuddy CLI as an AI chat agent inside a vault. Its UI references Claudian (MIT). Windows + macOS only; Linux is unsupported. Logs are prefixed [WB].
Commands
npm install # required first — node_modules is not checked in
npm run dev # esbuild watch build (rebuilds main.js on save)
npm run build # tsc -noEmit typecheck THEN esbuild production bundle
npm test # jest --coverage
npm run test:watch # jest watch mode
npx jest tests/manager.test.ts # run a single test file
npx jest -t "substring of test name" # run tests matching a name
npm run build runs tsc -noEmit -skipLibCheck purely as a typecheck gate — the actual bundle is produced by esbuild, not tsc. There is no separate lint step.
Build & distribution model
- Entry point
src/main.ts(default exportWorkbuddianPlugin) is bundled byesbuild.config.mjsinto a singlemain.jsat the repo root.obsidian,electron, CodeMirror packages, and Node builtins are markedexternal. main.jsis committed —.gitignoreignores all*.jsbut re-includes!main.js. The distributable plugin is the three filesmain.js+manifest.json+styles.css. When you change source, the committedmain.jsis only correct after a build.- Two versions coexist and can drift:
package.json(1.0.13, npm/dev) vsmanifest.json(0.1.0, the Obsidian-facing plugin version).version-bump.mjs(vianpm version) syncsmanifest.json+versions.json.
Architecture
Layered, single-responsibility modules under src/. The flow of a message: features/chat/input.ts → core/context/assembleContext.ts → providers/codebuddy (ACP persistent process) → streams StreamChunks back into the DOM and into core/session/manager.ts for persistence.
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 · 57 lines · 2,005 tokens per session scan A 9a6d030536ea
workbuddian CLAUDE.md is an instructions file published in the GitHub repository jiang198012/workbuddian (51 stars, last pushed 9d ago), licensed MIT. It adds 2,005 tokens to every session, about $0.0100 per session on Opus 5. A static security scan graded it A with 1 finding (runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other instructions, from other repositories
llm-wiki-agent GEMINI.md
Gemini CLI instructions for SamurAIGPT/llm-wiki-agent, covering llm wiki agent — schema & workflow instructions, how to use, directory layout, page format and ingest workflow.
hoop CLAUDE.md
Claude Code instructions for hoophq/hoop, covering claude.md, project overview, toolchain & prerequisites, architecture and module breakdown.
gini-agent AGENTS.md
AGENTS.md instructions for Open-Curiosity/gini-agent, covering gini agent instructions, shape, adrs, boundaries and branches.
InvestSkill GEMINI.md
Gemini CLI instructions for yennanliu/InvestSkill, covering investskill — gemini cli setup & usage guide, installation & setup, quick start, navigate to the investskill directory and start gemini cli (loads gemini.md automatically).
rome CLAUDE.md
Claude Code instructions for rome-os/rome, covering rome, playbook and traps.
zapcode CLAUDE.md
Instructions for TheUncharted/zapcode, covering claude.md, git, read agents.md first, codebase orientation and how to add a new language feature.