DirectiveOps

Your agents are following instructions. Bad ones cost 20% more and work worse.

ETH Zurich research found LLM-generated instruction files reduce task success by ~3% and increase inference costs 20–159%. Your files are making agents worse.

Most AGENTS.md and CLAUDE.md files are bloated, stale, or contradicting each other across tools. DirectiveOps scores instruction quality, detects drift, and helps you fix it — across every repo.

AGENTS.md is now a Linux Foundation standard; Codex, Claude Code, Cursor, Copilot, and Gemini CLI read these files. Tens of thousands of repos already ship them—few teams have fleet-wide visibility.

Connect GitHub to start, or try the demo first.

ManagesAGENTS.mdCLAUDE.mdGEMINI.mdcopilot-instructions.md*.instructions.md+More

Works with

CodexClaude CodeCursorCopilotGemini CLIDevinAmp

AGENTS.md is a Linux Foundation standard. Tens of thousands of repos already ship instruction files.

How it works

Coverage, drift, rollout, audit

Drift is silent; bad directives also waste cycles. Move from scattered files to inventory, governed updates, and evidence platform and security teams can rely on.

1Score

Scan instruction files and score quality — verbosity, staleness, conflicts, cross-tool consistency, and token efficiency.

2Detect

Surface drift, conflicts, stale references, security findings, and cross-tool inconsistencies across repos.

3Standardize

Compare repos to org templates and decide the baseline platform and security teams will enforce.

4Fix

Roll out updates with tracked PRs, monitor score trends, and keep an audit trail of what changed.

Quick start

Try the scanner locally

CLI scanner commands

# Clone the OSS scanner repo
$git clone https://github.com/pithpusher/DirectiveOps-Scanner.git && cd DirectiveOps-Scanner
# Install and scan
$npm install && npx directiveops-scanner scan --path /your/repo
# Export findings
$npx directiveops-scanner scan --path /your/repo --format json --output report.json --markdown report.md

From inside a repo, use --path . to scan the current directory.

Need fleet-wide standards and rollout? See pricing

Stay in the loop

Get updates on instruction standards, rollout tooling, and new releases.

Next step

See what's costing you tokens and degrading agent output, then fix it.

Connect GitHub to start, or try the demo first.