This file orients bundle maintainers, not end-users. End-users see README.md. A generic Amplifier mode bundle. Ships modes that wrap the Karpathy LLM Wiki pattern. Project-side policy (schema, publish, viewer) lives in projects that use this bundle, not here. This is the load-bearing design choice. See docs/ARCHITECTURE.md for the reasoning. Use /mode-design from amplifier-bundle-modes. Three phases: Drop the result in modes/. Verify it parses by including the bundle in a test project and /mode list. The bundle is dogfooded in a…
The chat UI uses a vendored JavaScript bundle at src/chat_plugin/static/vendor.js containing: Prerequisites: Node.js >= 18. The script installs dependencies into a local nodemodules/, bundles them via esbuild, and writes the output to src/chatplugin/static/vendor.js. Entry point: scripts/vendor-entry.js After rebuilding, commit the updated vendor.js. Tests are Python-based (pytest) and include both backend route tests and frontend code-pattern assertions that verify structural invariants in index.html.
A static, single-page web guided assistant (index.html) for Microsoft Purview / data security guidance. No build system or backend — the page is self-contained and served statically (e.g. GitHub Pages). This file is the entry point for humans and coding agents. Run the setup commands once after cloning or when dependencies change. verify.ps1 validates the approved dependency source and lockfile structure without network access, validates the HTML and inline JavaScript, exercises a representative labeling workflow in Chromium, and checks the…
Before drafting, editing, or returning repository prose, invoke /humanize-writing. This includes technical documentation, session kits, runbooks, Markdown, slide content, and user-facing explanations. In this repository, use the skill to simplify wording and remove AI-patterns from technical content. Its general technical-writing exclusion does not apply here. Use the clear-thinker voice unless the user requests another voice. Before finishing, complete both checks: 1. Apply the prose simplification rules in this file. 2. Apply the /humanize-writing AI-pattern dictionary and revise the draft until…
You are a coding agent helping with the Setu project, a high-performance inference engine for large language models. This is a complex C++/Python hybrid project requiring strict adherence to coding standards. The build system intelligently detects what needs to be built and chooses the optimal strategy automatically. Use failed-only test targets during development for faster iteration cycles.
Agent-to-agent (A2A) communication for Amplifier. The behavior behaviors/a2a.yaml composes a client tool (tool-a2a) and an HTTP server hook (hooks-a2a-server, default port 8222), plus a /a2a plain-language expert mode (setup, status, connect, troubleshoot). 1. Unit + lint (fast, host). The modules import amplifier_core, so a bare pytest won't collect — run the suite with the deps wired in: uv run --no-project --with amplifier-core --with aiohttp --with zeroconf \ --with pytest --with pytest-asyncio \ --with-editable modules/tool-a2a --with-editable modules/hooks-a2a-server \ pytest -q Then…
amplifier-bundle-dot-runner implements the vendored strongdm/attractor nlspec faithfully (see README.md "Spec fidelity" and docs/VISION.md). This file exists to make sure that stays true as the repo evolves. Before any design proposal, issue report, or code change touching engine or spec-adjacent behavior, ask yourself: "Did you check what the strongdm/attractor nlspec has to say about this first?" 1. Check the nlspec first. The canonical, pinned copies live in contracts/external/. Cite the section (e.g. "attractor-spec-canonical.md §5.2") in your issue, PR, or design doc.…
Read docs/VISION.md and the relevant contract in contracts/ before changing product behavior. Draft status is not evidence of approval or working software. - Commit settled product outputs and durable repo guidance. - Keep temporary design drafts, session plans, agent thinking, return logs, and workflow bookkeeping in the surrounding workspace, not this repository. - Do not copy workspace working documents into the repo as context. - The skill that reads this catalog is amplifier-smart-tools, maintained in microsoft/amplifier-smart-tools. Do not add a…
For contributors changing this repo. (For agents using the bundle at runtime, see bundle.md, skills/, and agents/ instead -- this file is the other audience: the one editing the code.) Direct pushes are rejected -- work goes through a PR, and merges are squash only (linear history required). Full ruleset: .github/branch-protection-ruleset.json, maintainer notes in CONTRIBUTING.md. One point worth repeating here: requiredapprovingreview_count is 0, not 1-with-a-bypass, because a bypass actor bypasses the entire ruleset -- including required status checks -- which…
This is the master entry point for humans and coding agents working on SMBBestPracticeTool: repeatable, idempotent PowerShell automation for Microsoft 365 best-practice configurations. Each product's README defines its scope and release status. Read the linked guidance before editing; each topic has one owner below. - Repository layout. - Deployment architecture and shared helpers. - Authoring and safety conventions. - Verification commands and definition of done: repository-wide checks, individual checks, pilot-tenant validation, and docs preview. - Branch, release, and PR workflow.…
This repo uses a dev-trio loop with subagent delegation: * Planner orchestrates everything. Delegates implementation and audit to subagents. Owns ALL logging, notifications, and user questions. The planner is the only agent that talks to the developer directly. * Implementer receives prompts from planner, audits constraints, implements code, runs builds and tests. Returns results to planner. Does NOT log, notify, or ask questions. * Critic receives implementer output from planner, audits against all binding constraints. Returns verdict to planner. Does…
Global Secure Access Troubleshooting Tool — a single-file PowerShell diagnostic utility (GSATool.ps1) for troubleshooting Microsoft Entra Global Secure Access (GSA). This file is the entry point for humans and coding agents. verify.ps1 confirms GSATool.ps1 parses cleanly (no syntax errors) and, if PSScriptAnalyzer is installed, that it reports no errors. A change is done when verify.ps1 passes and the tool still runs against a test tenant per README.md.
A static, single-page web app (index.html) that generates Statements of Work (SOW) for Microsoft Purview / MIP engagements. No build system or backend — the page is self-contained and served statically (e.g. GitHub Pages). This file is the entry point for humans and coding agents. The verify loop checks the basic HTML document and runs the Playwright browser smoke test. The test serves the static site locally and exercises analytics consent, form entry, SOW generation, encrypted JSON export, reset, and…
Guidance for AI coding agents (and any human author) working in this repository. This file is the single source of truth for the lab's scenario facts ("canon") and its MCAP authoring conventions. Read it before editing any page under docs/. This repository is a Jekyll-based training lab (just-the-docs theme, published to GitHub Pages) in Microsoft's MCAP TechWorkshop format. It is the Module 3 hands-on lab — Cross-Layer Attack Lab (End-to-End) — of the L300/L400 workshop Using AI to Secure the…
Converts Zero Trust Assessment output into a Zero Trust Workshop format via a single PowerShell script (Convert-ZTAssessmentToZTWorkshop.ps1) driven by a JSON mapping (test-mapping.json). This file is the entry point for humans and coding agents. verify.ps1 confirms the converter script parses cleanly and test-mapping.json is valid JSON. A change is done when verify.ps1 passes and a sample conversion still succeeds per readme.md.
This repo is documentation. Almost every change is prose that someone will read while they follow along with a terminal open, so the writing matters as much as the accuracy.
About this repo: repo-weaver is a deterministic git → wiki front-end over the wiki-weaver engine. It makes zero direct LLM calls; all synthesis/query is delegated to wiki-weaver via subprocess. See ARCHITECTURE.md for the full picture. This file is auto-loaded each session. Treat it as binding repo convention. Whenever a change touches any of: you MUST, in the same change: A change that alters architecture without updating these is incomplete. Consult these conventions at the start of work and at each…
MicrosoftAGENTS.md