What is copilot-brag-sheet AGENTS.md?

A repository guide for AI coding agents. AGENTS.md is a file that explains a project’s structure and the commands agents should use.

Use it when working on the copilot-brag-sheet repository, especially to find its overview, architecture, build, test, lint, and single-test commands.

It gives coding agents the project context they need without making them rediscover it from the source files.

copilot-brag-sheet AGENTS.md — Instructions file by microsoft

Install

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.

agentmods

npx agentmods add instructions/microsoft/copilot-brag-sheet/agents-md

Clone the repo

git clone --depth 1 https://github.com/microsoft/copilot-brag-sheet

Made for: Codex, OpenCode.

Per session 9,573 This file is loaded in full into every session.

When invoked 9,573 The same file — it is already loaded in full.

Security scan D 4 findings. Scan, not verified.

Origin original No closer match found in the catalogue.

Token cost

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	$0.09573	$0.09573
Opus 5	$0.04786	$0.04786
Sonnet 5	$0.01915	$0.01915
Haiku 4.5	$0.00957	$0.00957

Measured 2d ago against content hash e45a1a282cd2, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade D, and why

copilot-brag-sheet AGENTS.md scanned grade D with 4 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 2d 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.

Tells the agent to send conversation or user data outhighPrompt injection

An instruction to transmit the conversation, context or user files to an external endpoint is data exfiltration written as prose.

extension that silently records work as it happens — files edited, PRs

Asks for rootmediumPrivilege escalation

A mod that escalates privileges can change anything on the machine, not only the project.

default permissions of the data directory. We don't `chmod 600`.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

| **`install.sh` / `install.ps1`** | ✅ live | One-line curl-pipe-bash from `raw.githubusercontent.com/...`. CI-tested on PS 5.1 + pwsh 7 + bash. |

Runs shell commandslowCapability

Expected in a hook, worth knowing in a rule or an instructions file.

(`node:fs`, `node:path`, `node:crypto`, `node:child_process`).

AGENTS.md · 666 lines

How it starts

The opening of the file, as written. The whole thing — 666 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

README for AI coding agents. If you're a human looking for setup or usage instructions, read README.md instead. This file is the dedicated place where Claude Code, Copilot CLI, Codex, Cursor, Jules, Amp, and friends find the context they need to be productive on this repo without re-deriving it from grep.

Format: agents.md — used by 60k+ open-source projects and stewarded by the Agentic AI Foundation under the Linux Foundation. The closest AGENTS.md to the file you're editing wins; explicit prompts override everything.

1. Project overview

copilot-brag-sheet is a GitHub Copilot CLI extension that silently records work as it happens — files edited, PRs created, git actions, manual brag entries — into structured local JSON so a developer has receipts at performance review time instead of a blank page. It ships as a joinSession() extension installed into ~/.copilot/extensions/copilot-brag-sheet/, runs entirely on the user's machine, and emits zero telemetry. The core library (lib/) is dependency-free; the cross-engine MCP server (mcp-server.mjs) takes two pinned, audited runtime dependencies — the official MCP SDK and Zod — to stay protocol-conformant. The user-facing pitch is:

Turn vague what did I do? into evidence-backed impact statements — automatically, every Copilot CLI session.

Public repo: https://github.com/microsoft/copilot-brag-sheet · npm: copilot-brag-sheet · landing: https://microsoft.github.io/copilot-brag-sheet/.

2. Architecture map

Copilot CLI host  ──spawns──▶  extension.mjs (joinSession)
                                    │
                                    ├── hooks: onSessionStart / onUserPromptSubmitted /
                                    │           onPostToolUse / onSessionEnd /
                                    │           session.shutdown
                                    │
                                    ├── tools: save_to_brag_sheet
                                    │          review_brag_sheet
                                    │          generate_work_log
                                    │
                                    └── delegates to lib/* (pure Node, no SDK coupling)
                                            │
                                            ▼
                              JSON records on disk (atomic writes)
                              ~/AppData/Local/copilot-brag-sheet/  (Windows)
                              ~/Library/Application Support/copilot-brag-sheet/  (macOS)
                              ~/.local/share/copilot-brag-sheet/  (Linux, XDG)
                                            │
                                            ▼
                              optional: git commit/push to private repo

Agency host  ──spawns──▶  hooks/post-tool-use.mjs (subprocess per event)
                               │
                               ├── reads JSON payload from stdin
                               ├── classifies via lib/heuristics.mjs
                               └── writes JSON response to stdout
                                   (Phase 1: classification only, no persistence)

MCP host  ──stdio──▶  mcp-server.mjs (@modelcontextprotocol/sdk)
                           │
                           ├── tools: save_to_brag_sheet / review_brag_sheet / generate_work_log
                           └── delegates to lib/operations.mjs

Read the full file on GitHub · 666 lines

Changes

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.

2d ago First seen · 666 lines · 9,573 tokens per session scan D e45a1a282cd2

Subscribe to this mod's changes

copilot-brag-sheet AGENTS.md is an instructions file published in the GitHub repository microsoft/copilot-brag-sheet (10 stars, last pushed 20d ago), licensed MIT. It adds 9,573 tokens to every session, about $0.0479 per session on Opus 5. A static security scan graded it D with 4 findings (tells the agent to send conversation or user data out, asks for root, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

brag-sheet copilot copilot-cli developer-productivity developer-tools github-copilot

spec-kit-copilot AGENTS.md

Instructions for github/spec-kit-copilot, covering what this repository is, core skills plugin, core decisions (do not silently undo) and when revving the core skills plugin.

github/spec-kit-copilot · 2,177 tokens

Build-CLI AGENTS.md

Instructions for microsoft/Build-CLI, covering agents.md, plugin ecosystems, sync rules, cli and cli behavior contracts.

microsoft/Build-CLI · 946 tokens

squad copilot-instructions.md

Copilot instructions for bradygaster/squad, covering copilot coding agent — squad instructions, ⚠️ identity lock — read this first, 🚦 route before you act — generic copilot sessions, adversarial input handling and team context.

bradygaster/squad · 1,349 tokens

vscode-unify-chat-provider AGENTS.md

Instructions for smallmain/vscode-unify-chat-provider, a project described as: Integrate multiple LLM API providers into VS Code's GitHub Copilot Chat using the Language Model API. One-click use of your Claude Code, Gemini CLI, Antigravity, Github Copilot, OpenAI Codex (ChatGPT Plus/Pro), xAI Grok (SuperGrok / X…

smallmain/vscode-unify-chat-provider · 271 tokens

apex-accelerator github-actions.instructions.md

Project-specific standards for GitHub Actions workflows in this repository.

jonathan-vella/apex-accelerator · 1,074 tokens

apex-accelerator iac-terraform-best-practices.instructions.md

Terraform-specific IaC best practices for Azure templates. AVM-first, CAF naming, security baseline, provider pins.

jonathan-vella/apex-accelerator · 1,161 tokens

copilot-brag-sheet AGENTS.md