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/andreagriffiths11/teamxray/agents-mdgit clone --depth 1 https://github.com/AndreaGriffiths11/teamxrayWrote 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/andreagriffiths11/teamxray/agents-md)<a href="https://agentmods.dev/instructions/andreagriffiths11/teamxray/agents-md"><img src="https://agentmods.dev/badge/instructions/andreagriffiths11/teamxray/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 | $0.01656 | $0.01656 |
| Opus 5 | $0.00828 | $0.00828 |
| Sonnet 5 | $0.00331 | $0.00331 |
| Haiku 4.5 | $0.00166 | $0.00166 |
Grade A, and why
teamxray 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 5d 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 — 164 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Purpose
VS Code extension that transforms git history into team expertise maps. Discover who knows what, reveal collaboration patterns, get AI-powered management insights.
Tagline
"Stop being a stranger on your own team." 🔬
Tech Stack
- TypeScript — Extension core
- VS Code Extension API — 1.100.0+
- GitHub Copilot SDK (
@github/copilot-sdk) — Agentic analysis with custom tools - Node.js 20+ — Worker threads for git processing
- Webpack — Bundling
- simple-git — Git history parsing
Architecture
VS Code Extension
↓
ExpertiseAnalyzer (gathers git history)
↓
CopilotService (Copilot SDK session with custom tools)
↓ (agent calls tools to request team data)
AI Analysis (team profiles, management insights)
↓
Webview (dark-themed reports, HTML export)
Custom Copilot SDK Tools
Agent can request:
- Team member commit counts
- File ownership breakdown
- Collaboration patterns (co-author networks)
- Bus factor analysis (single points of failure)
- Recent activity trends
AI Provider Modes
| Mode | Provider | Setup | Fallback |
|---|---|---|---|
| 1 | Copilot SDK (default) | Copilot CLI installed + authenticated | N/A |
| 2 | BYOK OpenAI | Set API key via command | teamxray.byokBaseUrl, teamxray.byokModel |
| 3 | BYOK Anthropic | Set API key via command | teamxray.byokBaseUrl, teamxray.byokModel |
| 4 | BYOK Azure | Set API key + endpoint | teamxray.byokBaseUrl, teamxray.byokModel |
| 5 | GitHub Models | GitHub token (PAT) | Requires teamxray.aiProvider = github-models |
| 6 | Local git-only | No AI | Reduced analysis (no insights, just ownership) |
Auto-fallback: Copilot SDK → GitHub Models (if token set) → Local git-only
Features
- 🔍 File Expert Discovery — Right-click any file → find who knows it best
- 🧠 Team Expertise Analysis — AI profiles: communication styles, specializations, collab patterns
- 📊 Management Insights — Bus factor risks, growth opportunities, efficiency gaps
- 🤖 Bot/Agent Detection — Auto-identifies Dependabot, Copilot, Renovate (visual distinction)
- 📄 Dark-themed Reports — Exportable HTML with SVG charts, X-Ray branding
- 🛟 Git-backed Fallback — Works without AI (reduced view from local git)
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.
- 5d ago First seen · 164 lines · 1,656 tokens per session scan A 329ecbede567
teamxray AGENTS.md is an instructions file published in the GitHub repository AndreaGriffiths11/teamxray (17 stars, last pushed 2d ago), licensed MIT. It adds 1,656 tokens to every session, about $0.0083 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.
Other instructions, from other repositories
github-mcp-server copilot-instructions.md
Copilot instructions for github/github-mcp-server, covering github mcp server - copilot instructions, project overview, critical build & validation steps, required commands (run before committing) and when modifying mcp tools/endpoints.
kilocode AGENTS.md
AGENTS.md instructions for Kilo-Org/kilocode, covering agents.md, build and dev, quality checks, products and package instructions.
vscode-gitlens AGENTS.md
AGENTS.md instructions for gitkraken/vscode-gitlens, covering gitlens development guide, working style expectations, development environment, development commands and git & repository guidelines.
mcp-server-azure-devops AGENTS.md
Instructions for Tiberriver256/mcp-server-azure-devops: /home/tiberriver256/repos/mcp-server-azure-devops/docs/important-knowledge/azure-devops-rest-api-research.md Researching Azure DevOps REST APIs, selecting api-version, or handling Azure DevOps Server (on-prem) endpoints.
ebay-mcp AGENTS.md
Instructions for YosefHayim/ebay-mcp, covering agents.md, what this is, instruction sources, validation commands and module map (src/).
mcp-odoo CLAUDE.md
Claude Code instructions for erpipe-org/mcp-odoo: Guidance for Claude Code (claude.ai/code) working in this repository.