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/hamzakammar/mcp-workspace/agents-mdgit clone --depth 1 https://github.com/hamzakammar/mcp-workspaceWrote 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/hamzakammar/mcp-workspace/agents-md)<a href="https://agentmods.dev/instructions/hamzakammar/mcp-workspace/agents-md"><img src="https://agentmods.dev/badge/instructions/hamzakammar/mcp-workspace/agents-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 | $0.00938 | $0.00938 |
| Opus 5 | $0.00469 | $0.00469 |
| Sonnet 5 | $0.00188 | $0.00188 |
| Haiku 4.5 | $0.00094 | $0.00094 |
Grade A, and why
mcp-workspace AGENTS.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 6d 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 — 93 lines — stays where its author put it; the contents beside it link to each section on GitHub.
mcp-workspace — Agent Guide
Read this first. This file is the authoritative entry point for any AI agent or engineer working in this repository. It tells you how the codebase is structured, where decisions live, and how to make progress without breaking things.
1. What is mcp-workspace?
mcp-workspace is a personal MCP (Model Context Protocol) server workspace that gives AI assistants (Claude, Copilot, Poke, etc.) access to university tools — specifically D2L Brightspace and Piazza. It is deployed on an EC2 instance and managed via PM2. The workspace may host multiple MCP servers, each running on its own port.
2. Repo Map (progressive disclosure)
| Path | Purpose |
|---|---|
d2l-mcp/ |
D2L Brightspace + Piazza MCP server (primary MCP) |
setup/ |
Setup scripts and utilities |
tests/ |
Test suite (vitest) |
ecosystem.config.cjs |
PM2 process config for all MCPs |
package.json |
Workspace-level scripts (build-all, start-all, etc.) |
SETUP.md |
Quickstart for local dev and EC2 deployment |
docs/ |
Architecture, debt log, ADRs, and plans — start here for context |
AGENTS.md |
This file |
3. Key Conventions
- TypeScript everywhere. All new MCP tool files must be
.ts. Build todist/before deploying. - Each MCP gets its own directory and port. Do not co-locate two MCP servers in the same directory. Add new MCPs as sibling directories alongside
d2l-mcp/. - PM2 is the process manager. All servers are defined in
ecosystem.config.cjs. Do not start servers manually in production. - Sessions are managed locally and synced. D2L and Piazza session files live in
~/.d2l-session/and~/.piazza-session/. They must be synced to EC2 vianpm run sync-sessionsafter re-authentication. - Private mapping files are gitignored.
notes_map.jsonandpiazza_map.jsonare never committed. Document their schema indocs/architecture.mdif it changes. - No secrets in source. Credentials and keys live in each MCP's
.env(gitignored). Use environment variables only.
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.
- 6d ago First seen · 93 lines · 938 tokens per session scan A 712d252559a9
mcp-workspace AGENTS.md is an instructions file published in the GitHub repository hamzakammar/mcp-workspace (7 stars, last pushed 3mo ago), licensed MIT. It adds 938 tokens to every session, about $0.0047 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 2026-08-31.
Other instructions, from other repositories
open-dictionary AGENTS.md
Instructions for ahpxex/open-dictionary, covering open dictionary rewrite charter, product framing, core workflow, technical framework and 1. raw ingestion layer.
ab900 CLAUDE.md
Instructions for timothywarner-org/ab900, covering claude.md, repository purpose, architecture, commands and 2. non-ascii punctuation -- must return zero.
canvas-lms-mcp AGENTS.md
AGENTS.md instructions for bruchris/canvas-lms-mcp, covering agents.md — canvas lms mcp server, quick start, run with npx (no install needed), or install globally and architecture.
obsidian-university-workflow CLAUDE.md
Instructions for ABO896/obsidian-university-workflow, covering obsidian university workflow, project structure, rules for working on this project, templater api — always read the docs first and config alignment.
agentic-ai-engineering-course AGENTS.md
AGENTS.md instructions for towardsai/agentic-ai-engineering-course, covering the what and course map (lessons ↔ code projects).
anki-mcp-server CLAUDE.md
Claude Code instructions for nailuoGG/anki-mcp-server, covering claude.md, repository overview, development commands, build & development and install dependencies.