DirectiveOps

Find out why your AI coding agent keeps ignoring your rules.

Score your AGENTS.md in 30 seconds — free, local, no signup.

If you use Copilot, Cursor, or Claude Code, a hidden markdown file (AGENTS.md, CLAUDE.md, copilot-instructions.md) tells the agent how to behave. When it's bloated, stale, or contradicts itself, the agent drops instructions and ships bad code. DirectiveOps scans the file, scores it, and tells you exactly what to fix.

$ npx directiveops scan

No install. One command. Paste it in the repo you already have open.

~/your-repo

$ npx directiveops scan

Scanning 4 instruction files...
  AGENTS.md            ok
  CLAUDE.md            drift
  GEMINI.md            drift
  .github/copilot-instructions.md  conflict

Quality score: 62 / 100
Findings:
  ⨯ CLAUDE.md and copilot-instructions.md contradict on test command
  ⚠ GEMINI.md references src/legacy/ (deleted 4 months ago)
  ⚠ AGENTS.md has 1,840 tokens of unused context

→ See this in the dashboard: https://directiveops.com/claim

Try the demo Or connect GitHub for the hosted dashboard →

Run the scan, or browse a pre-loaded demo workspace first.

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

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

Standards momentum: AGENTS.md is a Linux Foundation standard. Codex, Claude Code, Cursor, Copilot, and Gemini CLI all read these files.

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 →

Open core

From scanner to fleet control

Free and local

OSS scanner

Score instruction files locally — quality, conflicts, staleness, and security findings.

Quality scores for every instruction file
Cross-tool conflict detection
Security findings and stale reference checks
JSON and Markdown export — no signup required

Hosted product

Hosted platform

Fleet-wide quality dashboard, drift alerts, and — on Team — rollout PRs.

Org-wide quality scores and trends
Drift alerts and PR comment bot
Rollout PRs and standards (Team+)
Audit log and compliance evidence (Growth+)

Pricing

Start free. Upgrade when your team grows.

Compare plans

Free

OSS / Free Scanner

Local scanning

$29/mo

Starter

Up to 5 repos

$99/mo

Team

Up to 25 repos

$299/mo

Growth

Up to 100 repos

Next step

Run the scanner, try the demo, or see pricing.

GitHub

View the source

Documentation

Scanner, onboarding, and API

Demo workspace

Try the hosted dashboard

Contact

Sales, support, and enterprise

Stay in the loop