A command that scans a code project for drift: cases where the code, specifications, decisions, ownership, tests, usage, or dependencies no longer agree.

Use it to review project consistency, find stale tests or documentation, detect unclear ownership, and identify changes that need resolution.

It brings unresolved mismatches into one report and ranks them by severity, so changes that may cause failures or confusion are easier to find.

icpg-drift — Command for Claude Code by alinaqi/maggy

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.

Clone the repo

git clone --depth 1 https://github.com/alinaqi/maggy

Made for: Claude Code.

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/alinaqi/maggy/icpg-drift/github.svg)](https://agentmods.dev/commands/alinaqi/maggy/icpg-drift)

Your own site

<a href="https://agentmods.dev/commands/alinaqi/maggy/icpg-drift"><img src="https://agentmods.dev/badge/commands/alinaqi/maggy/icpg-drift/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/commands/alinaqi/maggy/icpg-drift"><img src="https://agentmods.dev/badge/commands/alinaqi/maggy/icpg-drift.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 350 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	$0.00000	$0.00350
Opus 5.5	$0.00000	$0.00140
Sonnet 5.5	$0.00000	$0.00070
Haiku 4.5	$0.00000	$0.00035

Measured 2mo ago against content hash 5829a4f464e3, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

icpg-drift 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 2mo 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.

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.

commands/icpg-drift.md · 60 lines

What it actually says

/icpg-drift — Show All Drift

Run a full drift scan and display all unresolved drift events, grouped by dimension and sorted by severity.

Usage

/icpg-drift

Steps

1. Run drift scan

icpg drift check

2. Also show existing unresolved drift

icpg status

3. Display results

DRIFT REPORT
═══════════════

{N} unresolved drift events across {M} symbols

BY SEVERITY:
  [0.85] spec(0.9) + decision(0.8) — validateToken drifted from "JWT auth"
  [0.60] ownership(0.7) + test(0.5) — UserService has 4 owners, tests stale
  ...

BY DIMENSION:
  Spec drift:       {count} events
  Decision drift:   {count} events
  Ownership drift:  {count} events
  Test drift:       {count} events
  Usage drift:      {count} events
  Dependency drift: {count} events

TOP ACTIONS:
  1. Fix spec drift in validateToken — checksum changed without MODIFIES edge
  2. Add tests for UserService — VALIDATED_BY tests are missing
  3. Assign single owner to PaymentProcessor — 5 different owners

4. Offer resolution

For each event, suggest:

icpg drift resolve <id> to mark resolved
Create a new MODIFIES ReasonNode if the change was intentional
Write missing tests if test drift detected

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.

2mo ago First seen · 60 lines · 0 tokens per session scan A 5829a4f464e3

Subscribe to this mod's changes

icpg-drift is a command published in the GitHub repository alinaqi/maggy (711 stars, last pushed 24d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 350 tokens. 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 2026-08-30.

Claude Code Python ai-coding claude developer-tools project-initialization

icpg-drift next to 6 commands from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
icpg-driftalinaqi/maggy	Command	711	24d ago	MIT	A	0	Claude Code
python-reviewloulanyue/awesome-claude-notes	Command	271	1mo ago	MIT	A	31	Claude Code
frappe-backendDkm0315/frappe-agent	Command	27	27d ago	MIT	A	0	Claude Code, Cursor
py-hardenmathisk2095/jko-claude-plugins	Command	3	24d ago	MIT	A	32	Claude Code
py-structuremathisk2095/jko-claude-plugins	Command	3	24d ago	MIT	A	23	Claude Code
skill-mcp-serverdewtech-technologies/dare-method	Command	5	3mo ago	MIT	A	0	Claude Code
skill-fastapi-apidewtech-technologies/dare-method	Command	5	3mo ago	MIT	A	0	Claude Code