agentmods.dev

Langpad copilot-instructions.md

A set of GitHub Copilot instructions for Langpad, an Obsidian desktop plugin that lets users chat with external coding agents. It explains the project structure and rules for changing the code.

In plain words
What is it for?
It is for guiding changes to Langpad’s React and TypeScript interface, agent sessions, message streaming, Agent Client Protocol communication, and shared message handling.
Why use it?
It tells an agent where features belong and which architectural boundaries to respect. This reduces the chance of placing logic in the wrong layer or breaking the project’s integration code.

Instructions file for GitHub Copilot

1 3mo ago A scan 712 tokens copy · 100% Apache-2.0
View the source file LangcliTeam/Langpad
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/langcliteam/langpad/copilot-instructions
Clone the repo
git clone --depth 1 https://github.com/LangcliTeam/Langpad

Made for: GitHub Copilot.

Per session 712 This file is loaded in full into every session.
When invoked 712 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
Origin 100% copy Near-identical to another mod 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 $0.00712 $0.00712
Opus 5 $0.00356 $0.00356
Sonnet 5 $0.00142 $0.00142
Haiku 4.5 $0.00071 $0.00071

Measured 2d ago against content hash 638f6d6ea8dd, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

Langpad copilot-instructions.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 2d 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.

Origin

This is a copy

100% identical to obsidian-agent-client copilot-instructions.md — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

.github/copilot-instructions.md · 46 lines

How it starts

The opening of the file, as written. The whole thing — 46 lines — stays where its author put it; the contents beside it link to each section on GitHub.

GitHub Copilot Instructions (obsidian-agent-client)

Big picture

  • Obsidian desktop plugin (React 19 + TypeScript) that chats with external coding agents via Agent Client Protocol (ACP).
  • Uses a React Hooks Architecture: hooks own state/logic, components render, adapters integrate external systems, domain is pure types.

Key directories / “where to change things”

  • UI composition + adapter instantiation: src/components/chat/ChatView.tsx (creates adapters via useMemo, composes hooks).
  • Session lifecycle + agent switching: src/hooks/useAgentSession.ts.
  • Message state + streaming updates: src/hooks/useChat.ts.
  • ACP process + JSON-RPC wiring: src/adapters/acp/acp.adapter.ts.
  • Pure message prep/sending (mentions, auto-mention, WSL path conversion): src/shared/message-service.ts.
  • Domain contracts only (no deps): src/domain/models/*, src/domain/ports/*.

Architectural rules (project-specific)

  • Keep src/domain/** dependency-free: no obsidian imports, no @agentclientprotocol/sdk imports.
  • Add new behavior as hooks under src/hooks/ and compose them in ChatView.tsx (avoid introducing ViewModel/UseCase classes).
  • Put non-React business logic in src/shared/ as pure functions (see message-service.ts).
  • Adapters implement ports and isolate protocol/platform churn (ACP changes should mostly stay in src/adapters/acp/).

SessionUpdate / tool-call update flow (critical)

  • Use the unified pipeline: AcpAdapter.onSessionUpdate(...) → useChat.handleSessionUpdate(...).
  • Tool calls must be updated via useChat.upsertToolCall(...) using functional setMessages((prev) => ...) to avoid race conditions from streaming tool_call_update events.
  • When merging tool-call content, preserve existing values when updates are undefined and treat diffs as replace-all (see mergeToolCallContent in useChat.ts).

Obsidian & platform constraints

  • Desktop-only: ChatView throws when !Platform.isDesktopApp.
  • Use Obsidian Platform.isWin/isMacOS/isLinux helpers (avoid process.platform).
  • No innerHTML/outerHTML; use Obsidian element helpers (createEl/createDiv/createSpan).
  • Don't detach leaves in onunload.
  • Keep styling in styles.css (avoid JS style manipulation).

Read the full file on GitHub · 46 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. 2d ago First seen · 46 lines · 712 tokens per session scan A 638f6d6ea8dd

Subscribe to this mod's changes

Langpad copilot-instructions.md is an instructions file published in the GitHub repository LangcliTeam/Langpad (1 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 712 tokens to every session, about $0.0036 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to obsidian-agent-client copilot-instructions.md, differing in 0 lines, and is treated as a copy.

claude-codecodexgemini-clilangcliobsidian
Related

Other instructions, from other repositories

obsidian-mind CLAUDE.md

Claude Code instructions for breferrari/obsidian-mind, covering obsidian mind, skills & capabilities, custom slash commands, vault structure and obsidian cli.

breferrari/obsidian-mind · 9,405 tokens

obsidian-mind AGENTS.md

AGENTS.md instructions for breferrari/obsidian-mind, covering obsidian mind, hooks, commands, memory and reaching this vault from another repo.

breferrari/obsidian-mind · 1,145 tokens

obsidian-llm-hub CLAUDE.md

Instructions for takeshy/obsidian-llm-hub, covering claude.md, project overview, build commands, version bumping and architecture.

takeshy/obsidian-llm-hub · 2,259 tokens

onebrain GEMINI.md

Instructions for onebrain-ai/onebrain, covering onebrain — gemini cli, load order, project-level gemini config, tool name mapping and agent instructions.

onebrain-ai/onebrain · 468 tokens

onebrain AGENTS.md

Instructions for onebrain-ai/onebrain, covering onebrain — codex cli, load order, tool name mapping and agent instructions.

onebrain-ai/onebrain · 243 tokens

obsidian-llm-hub AGENTS.md

Instructions for takeshy/obsidian-llm-hub, a project described as: Obsidian plugin for AI chat, workflow automation, and semantic search — supports Gemini, OpenAI, OpenRouter, Grok, Ollama, and CLI backends.

takeshy/obsidian-llm-hub · 44 tokens