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.

How microsoft/copilot-brag-sheet configures Claude Code and Codex

About the project

Copilot Brag Sheet is a GitHub Copilot CLI extension that records coding-session activity, such as edited files, pull requests, and Git operations, in a structured local work-impact log. Developers use it to retain evidence for performance reviews without sending telemetry. The catalogue add-ons provide the extension’s automatic tracking, agent guidance, and MCP integration.

microsoft/copilot-brag-sheet · 11 stars · on GitHub

Reuse

Borrowing it

Nothing to install: this file belongs to microsoft/copilot-brag-sheet. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/microsoft/copilot-brag-sheet/main/AGENTS.md

Clone the repo

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

Made for: Claude Code, Codex, OpenCode.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/microsoft/copilot-brag-sheet/agents-md/github.svg)](https://agentmods.dev/instructions/microsoft/copilot-brag-sheet/agents-md)

Your own site

<a href="https://agentmods.dev/instructions/microsoft/copilot-brag-sheet/agents-md"><img src="https://agentmods.dev/badge/instructions/microsoft/copilot-brag-sheet/agents-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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/microsoft/copilot-brag-sheet/agents-md"><img src="https://agentmods.dev/badge/instructions/microsoft/copilot-brag-sheet/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 9,655 This file is loaded in full into every session.

When invoked 9,655 The same file — it is already loaded in full.

Security scan D 4 findings. A grade says what 26 rules found in the file — not that it is safe.

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 5.1	$0.09655	$0.09655
Opus 5.5	$0.03862	$0.03862
Sonnet 5.5	$0.01931	$0.01931
Haiku 4.5	$0.00966	$0.00966

Measured 25d ago against content hash 35f09c54d897, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, 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 25d 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 · 668 lines

How it starts

The opening of the file, as written. The whole thing — 668 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 · 668 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.

25d ago Changed · +2 lines · +82 tokens per session 35f09c54d897
1mo 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 (11 stars, last pushed 3d ago), licensed MIT. It adds 9,655 tokens to every session, about $0.0386 per session on Opus 5.5. 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.

Building agents Writing and docs brag-sheet copilot copilot-cli developer-productivity developer-tools github-copilot

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).

microsoft/vscode · 9,649 tokens

copilot-brag-sheet: Instructions file for Claude Code