CopilotPCF_Bidirectional CLAUDE.md

A repository instruction file explaining a project that turns chat requests into data visualizations for Microsoft 365 Copilot and Power Apps.

In plain words
What is it for?
Guiding development and testing of the Node and TypeScript server, Copilot agent, and Power Apps dashboard components.
Why use it?
It gives coding agents the project context, architecture, commands, and important configuration details needed to work safely in the repository.

Instructions file

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/adner/copilotpcf_bidirectional/claude-md
Clone the repo
git clone --depth 1 https://github.com/adner/CopilotPCF_Bidirectional
Per session 2,880 This file is loaded in full into every session.
When invoked 2,880 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 $0.02880 $0.02880
Opus 5 $0.01440 $0.01440
Sonnet 5 $0.00576 $0.00576
Haiku 4.5 $0.00288 $0.00288

Measured 3d ago against content hash cf3ffe463145, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

CopilotPCF_Bidirectional CLAUDE.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 3d 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.

CLAUDE.md · 82 lines

How it starts

The opening of the file, as written. The whole thing — 82 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 repo is

A demo where a user chats a data visualization into existence in M365 Copilot and publishes it as a live tile on a Power App PCF dashboard. Natural language → a Dataverse-backed chart, rendered two ways from one generated artifact.

Components (in build order):

  • mcp-server/ — the actual product, and where nearly all work has happened. A Node + TypeScript MCP server (also a plain web server). Done: implements the full tool + web contract below, verified against the live Dataverse env.
  • DashboardAgent/ — an M365 Copilot declarative agent (Agents Toolkit / ATK project) that consumes the MCP server. Functional. Manifests only; no app logic; regenerated by ATK, so don't hand-edit lightly. The provisioned agent's gptId is what the PCF's agentId property must be set to — an opaque agent id, per Microsoft's time-tracker sample of the form T_<guid> (tenant) or U_<guid>.declarativeAgentPowerApps (user-scoped), i.e. M365_TITLE_ID in env/.env.dev, not TEAMS_APP_ID. Verify the live value by opening the agent in the Copilot pane and running Xrm.Copilot.getCurrentAgent() in DevTools.
  • controls/dynamic-dashboard/ — the Power Apps PCF dashboard control (DDB.DynamicDashboard). Implemented + deployed (pac pcf push --publisher-prefix ddb, bound via solution import as the default grid control of the hosting table). Full-page dataset PCF that fetches GET /dashboard, iframes each tile URL, and listens for the publish nudge. Hosting table created via MCP is cr19f_dashboard (the MCP tool uses the env default publisher prefix, not ddb). See "PCF component" below.
  • spec.md — the authoritative design for the server (~14 sections). Code comments cite it as §3, §6.2, etc. When a comment says "see spec §X", spec.md is the source of truth. The client-side integration (Xrm.Copilot APIs, the widget→app postMessage bridge, the PCF's design + pitfalls) is references/power-apps-copilot-integration.md. .github/agents/ddb-only.agent.md is a scoped agent persona.

Read the full file on GitHub · 82 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. 3d ago First seen · 82 lines · 2,880 tokens per session scan A cf3ffe463145

Subscribe to this mod's changes

CopilotPCF_Bidirectional CLAUDE.md is an instructions file published in the GitHub repository adner/CopilotPCF_Bidirectional (11 stars, last pushed 2mo ago), licensed MIT. It adds 2,880 tokens to every session, about $0.0144 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.

Related

Other instructions, from other repositories

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,104 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,182 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,345 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

next.js AGENTS.md

Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens