What is generate-improvements?

A review command that examines the AgentRC TypeScript command-line project and suggests improvements to its features, bug fixes, security, performance, and engineering quality.

Use it to review AgentRC for missing features, defects, security issues, slow code, or other engineering improvements.

It helps turn a broad request for project improvements into a focused list of possible changes instead of requiring a developer to inspect the whole project unaided.

How microsoft/agentrc configures GitHub Copilot

About the project

AgentRC prepares repositories for AI coding agents by analyzing their code and generating project-specific instructions, evaluations, and development configuration. It is used through a CLI, VS Code extension, or CI pipeline to measure AI readiness, keep context useful, and detect drift; the catalogue entries support these repository-preparation workflows.

microsoft/agentrc · 1,052 stars · on GitHub

Reuse

Borrowing it

Nothing to install: this file belongs to microsoft/agentrc. 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/agentrc/main/.github/prompts/generate-improvements.prompt.md

Clone the repo

git clone --depth 1 https://github.com/microsoft/agentrc

Made for: GitHub Copilot.

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/commands/microsoft/agentrc/generate-improvements.svg)](https://agentmods.dev/commands/microsoft/agentrc/generate-improvements)

Your own site

<a href="https://agentmods.dev/commands/microsoft/agentrc/generate-improvements"><img src="https://agentmods.dev/badge/commands/microsoft/agentrc/generate-improvements.svg" alt="Measured on agentmods" height="20"></a>

Per session 22 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 1,957 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 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	$0.00022	$0.01957
Opus 5	$0.00011	$0.00979
Sonnet 5	$0.00004	$0.00391
Haiku 4.5	$0.00002	$0.00196

Measured yesterday against content hash 58b95c624f98, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

generate-improvements 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 yesterday.

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.

.github/prompts/generate-improvements.prompt.md · 136 lines

How it starts

The opening of the file, as written. The whole thing — 136 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a senior software engineer reviewing the AgentRC project — a TypeScript CLI tool that primes repositories for AI-assisted development by analyzing codebases, generating instructions and VS Code configs, running evaluations, and producing readiness reports.

Architecture Context

Tech Stack: TypeScript (ESM, strict), Node.js, React (Ink for TUI), Commander for CLI
Entrypoint: src/index.ts → runCli in src/cli.ts
Dependencies: @github/copilot-sdk, @octokit/rest, simple-git, ink, commander, fast-glob, @inquirer/prompts

Key Directories

src/commands/ — CLI subcommands (init, generate, pr, eval, tui, instructions, readiness, batch, batch-readiness)
src/services/ — Core logic:
- analyzer.ts — Scans repo files to detect languages, frameworks, package manager, monorepo workspaces
- instructions.ts — Generates .github/copilot-instructions.md using Copilot SDK agent sessions
- generator.ts — Writes .vscode/settings.json and .vscode/mcp.json configs
- evaluator.ts — Runs eval cases comparing agent responses with/without instructions, builds trajectory viewer HTML
- readiness.ts — Multi-pillar readiness assessment (style, build, testing, docs, dev-env, code-quality, observability, security, ai-tooling)
- visualReport.ts — Generates beautiful HTML readiness reports with summary cards, pillar charts, level distribution
- git.ts — Clone/branch operations via simple-git
- github.ts / azureDevops.ts — GitHub (Octokit) and Azure DevOps API integrations
- copilot.ts — Locates and validates the Copilot CLI binary
- evalScaffold.ts — Scaffolds starter eval config files
src/ui/ — Ink/React-based TUI components (tui.tsx, BatchTui.tsx, BatchReadinessTui.tsx, BatchTuiAzure.tsx, AnimatedBanner.tsx)
src/utils/ — Shared utilities (fs.ts for safe file writes, logger.ts, pr.ts)

CLI Commands

Command	Description
`agentrc init`	Interactive setup wizard (instructions + configs)
`agentrc generate <type>`	Generate `instructions`, `agents`, `mcp`, or `vscode` configs
`agentrc instructions`	Generate copilot-instructions.md via Copilot SDK
`agentrc eval`	Run evaluation cases comparing with/without instructions
`agentrc readiness`	Readiness assessment with optional visual HTML report
`agentrc batch`	Batch process multiple repos across GitHub/Azure orgs
`agentrc batch-readiness`	Batch readiness reports across multiple repos
`agentrc pr`	Automate branch/PR creation for generated configs
`agentrc tui`	Interactive Ink-based terminal UI

Read the full file on GitHub · 136 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.

yesterday First seen · 136 lines · 22 tokens per session scan A 58b95c624f98

Subscribe to this mod's changes

generate-improvements is a command published in the GitHub repository microsoft/agentrc (1,052 stars, last pushed yesterday), licensed MIT. It adds 22 tokens to every session and 1,957 once invoked, about $0.0001 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 2026-09-06.

Code review

agentrc: Command for GitHub Copilot

Borrowing it

Wrote this? Show the measurements

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

Architecture Context

Key Directories

CLI Commands

What this file has done since we first saw it

Other commands, from other repositories

sdd-init

review-branch

init

merge-conflict-analysis

review-sdk-app

repo-audit