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/adepanges/teamretro-mcp-server/copilot-instructionsgit clone --depth 1 https://github.com/adepanges/teamretro-mcp-serverWrote 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/adepanges/teamretro-mcp-server/copilot-instructions)<a href="https://agentmods.dev/instructions/adepanges/teamretro-mcp-server/copilot-instructions"><img src="https://agentmods.dev/badge/instructions/adepanges/teamretro-mcp-server/copilot-instructions.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 | $0.01832 | $0.01832 |
| Opus 5 | $0.00916 | $0.00916 |
| Sonnet 5 | $0.00366 | $0.00366 |
| Haiku 4.5 | $0.00183 | $0.00183 |
Grade A, and why
teamretro-mcp-server copilot-instructions.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 4d 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 — 135 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Copilot Coding Agent Instructions
Project Overview
This is a TypeScript MCP (Model Context Protocol) server that integrates with the TeamRetro API. It acts as a bridge between AI clients and TeamRetro's platform, providing 20+ tools for managing teams, users, actions, retrospectives, agreements, health checks, health models, and reports.
The server communicates over stdio using the @modelcontextprotocol/sdk.
Tech Stack
- Runtime: Node.js ≥ 18
- Language: TypeScript (ES2020 target, ES2022 modules)
- Package Manager: pnpm (v9, lockfile version 9.0)
- Schema Validation: Zod
- Build:
tsc+tsc-alias(for path alias resolution)
Build & Run Commands
pnpm install # Install dependencies (also runs build via "prepare" script)
pnpm run build # Clean build: rimraf dist && tsc && tsc-alias
pnpm run watch # Dev mode with auto-rebuild
pnpm run start # Run the server: node dist/index.js
pnpm run inspector # Build and launch MCP inspector (requires .env file)
pnpm run clean # Remove dist/
Build Errors to Watch For
- The
pnpm installstep triggerspreparewhich runspnpm run build. Ifpnpmis not installed globally, install it first:npm install -g pnpm@9. - The
TEAMRETRO_API_KEYenvironment variable is required at runtime. Without it, the server will throw aTeamRetroErrorwith codeCONFIG_ERRORon startup. For build-only tasks, this is not needed.
Testing
There is no test infrastructure in this project. The test script in package.json is: echo "Error: no test specified" && exit 0. Do not add test frameworks unless explicitly asked to.
Project Structure
src/
├── index.ts # Entry point: TeamRetroMCPServer class, stdio transport
├── config.ts # Environment variable loading via env-var
├── tools.ts # Tool registry: aggregates all feature tools, creates schemas & handlers
├── features/ # Feature modules (one per API domain)
│ ├── actions/ # Each feature has: service.ts + tools.ts
│ ├── agreements/
│ ├── health-checks/
│ ├── health-models/
│ ├── reports/
│ ├── retrospectives/
│ ├── team-members/
│ ├── teams/
│ └── users/
├── schemas/ # Zod schemas for API entities
│ ├── generic.ts # Shared schemas: pagination, id, name, email, date, tags
│ ├── Action.ts
│ ├── Agreement.ts
│ ├── Base.ts
│ ├── HealthCheck.ts
│ ├── HealthModel.ts
│ ├── Retrospective.ts
│ ├── Team.ts
│ └── User.ts
├── services/
│ └── TeamRetro.service.ts # Abstract HTTP client base class (get/post/patch/put/delete)
├── types/ # TypeScript type declarations
│ ├── api.d.ts # Global API response types (ListApiResponse, SingleApiResponse)
│ ├── config.d.ts # Global config types (TeamRetroConfig, LogConfig)
│ ├── errors.d.ts # TeamRetroError class
│ └── tool.ts # Tool/Tools types
└── utils/
├── error.ts # ErrorMCP class and formatClientError
├── formatter.ts # Markdown table/item formatting for "simple" response mode
├── logger.ts # File-based logger singleton
├── tools.ts # createToolResponse, toolErrorHandlers
└── url.ts # URL search params helper
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.
- 4d ago First seen · 135 lines · 1,832 tokens per session scan A 0f60ec1104f0
teamretro-mcp-server copilot-instructions.md is an instructions file published in the GitHub repository adepanges/teamretro-mcp-server (0 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 1,832 tokens to every session, about $0.0092 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
OpenIntegrations AGENTS.md
AGENTS.md instructions for Bayselonarrend/OpenIntegrations, covering руководство для agents, каноничный исходный код, каноничные тесты, описание релизов and зеркало onescript и автогенерация в ci/cd.
silkweave CLAUDE.md
Instructions for silkweave/silkweave, covering claude.md, commands, mcp inspector (connects to mcp stdio example via .mcp.json), architecture and packages.
gorest AGENTS.md
AGENTS.md instructions for pilinux/gorest, covering agents.md, project overview, build and run commands, build and tidy dependencies.
gmgn-skills CLAUDE.md
Claude Code instructions for GMGNAI/gmgn-skills, covering claude.md, critical rule — read this first, project overview, available skills and quick decision guide.
substack-gateway-oss CLAUDE.md
Claude Code instructions for jakub-k-slys/substack-gateway-oss, covering claude.md, commands, install dependencies (dev included, all workspace members), run the server (dev mode with reload) and lint.
mcp-agent-langchainjs AGENTS.md
Instructions for Azure-Samples/mcp-agent-langchainjs, covering mcp agent langchain.js project instructions, architecture overview, component communication flow, key architectural patterns and authentication & state management.