microsoft/semanticworkbench is a user interface and set of services for prototyping, testing, and measuring assistants and multi-assistant conversations. Developers use it to create or connect assistants built with different frameworks and programming languages through REST APIs. The catalogue entry provides an instruction for working with the workbench.
Borrowing it
Nothing to install: this file belongs to microsoft/semanticworkbench. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/microsoft/semanticworkbench/main/CLAUDE.mdgit clone --depth 1 https://github.com/microsoft/semanticworkbenchWrote 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/microsoft/semanticworkbench/claude-md)<a href="https://agentmods.dev/instructions/microsoft/semanticworkbench/claude-md"><img src="https://agentmods.dev/badge/instructions/microsoft/semanticworkbench/claude-md/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/instructions/microsoft/semanticworkbench/claude-md"><img src="https://agentmods.dev/badge/instructions/microsoft/semanticworkbench/claude-md.svg" alt="Reviewed on agentmods" width="80" 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 | $0.01145 | $0.01145 |
| Opus 5.5 | $0.00458 | $0.00458 |
| Sonnet 5.5 | $0.00229 | $0.00229 |
| Haiku 4.5 | $0.00114 | $0.00114 |
Grade A, and why
semanticworkbench 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 2mo 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.
How it starts
The opening of the file, as written. The whole thing — 83 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Semantic Workbench Developer Guidelines
AI Context System
Generate comprehensive codebase context for development:
make ai-context-files- Generate AI context files for all components- Files created in
ai_context/generated/organized by logical boundaries:- Python Libraries (by functional group):
PYTHON_LIBRARIES_CORE.md- Core API model, assistant framework, eventsPYTHON_LIBRARIES_AI_CLIENTS.md- Anthropic, OpenAI, LLM clientsPYTHON_LIBRARIES_EXTENSIONS.md- Assistant/MCP extensions, content safetyPYTHON_LIBRARIES_SPECIALIZED.md- Guided conversation, assistant drivePYTHON_LIBRARIES_SKILLS.md- Skills library with patterns and routines
- Assistants (by individual implementation):
ASSISTANTS_OVERVIEW.md- Common patterns and all assistant summariesASSISTANT_PROJECT.md- Project assistant (most complex)ASSISTANT_DOCUMENT.md- Document processing assistantASSISTANT_CODESPACE.md- Development environment assistantASSISTANT_NAVIGATOR.md- Workbench navigation assistantASSISTANT_PROSPECTOR.md- Advanced agent with artifact creationASSISTANTS_OTHER.md- Explorer, guided conversation, skill assistants
- Platform Components:
WORKBENCH_FRONTEND.md- React app components and UI patternsWORKBENCH_SERVICE.md- Backend API, database, and service logicMCP_SERVERS.md- Model Context Protocol server implementationsDOTNET_LIBRARIES.md- .NET libraries and connectors
- Supporting Files:
EXAMPLES.md- Sample code and getting-started templatesTOOLS.md- Build scripts and development utilitiesCONFIGURATION.md- Root-level configs and project setupASPIRE_ORCHESTRATOR.md- Container orchestration setup
- Python Libraries (by functional group):
Using AI Context for Development:
- New developers: Read
CONFIGURATION.md+PYTHON_LIBRARIES_CORE.mdfor project overview - Building assistants:
- Start with
ASSISTANTS_OVERVIEW.mdfor common patterns - Use specific assistant files (e.g.,
ASSISTANT_PROJECT.md) as implementation templates
- Start with
- Working on specific assistants: Load the relevant
ASSISTANT_*.mdfile for focused context - Library development: Choose appropriate
PYTHON_LIBRARIES_*.mdfile by functional area - Frontend work: Study component patterns in
WORKBENCH_FRONTEND.md - API development: Follow service patterns from
WORKBENCH_SERVICE.md - MCP servers: Use existing servers in
MCP_SERVERS.mdas templates - AI tools: Provide relevant context files for better code generation and debugging
- Code reviews: Reference context files to understand cross-component impacts
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.
- 2mo ago First seen · 83 lines · 1,145 tokens per session scan A fb6769fe9233
semanticworkbench CLAUDE.md is an instructions file published in the GitHub repository microsoft/semanticworkbench (407 stars, last pushed 7mo ago), licensed MIT. It adds 1,145 tokens to every session, about $0.0046 per session on Opus 5.5. 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.
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).
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
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.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.