What is mpga-drift-check?

A checker for evidence drift, meaning claims or links that have become stale or can no longer be verified.

Use it for quick, full, or CI checks across a chosen scope, with severity labels and automatic healing for minor findings.

It helps detect outdated references after files change and makes stale evidence visible before it causes confusion.

mpga-drift-check — Skill for Claude Code and Codex by benrben: A checker for evidence drift, meaning claims or links…

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.

agentmods

npx agentmods add skills/benrben/mpga/drift-check

Any agent

npx skills add benrben/MPGA --skill drift-check

Clone the repo

git clone --depth 1 https://github.com/benrben/MPGA

Made for: Claude Code, Codex.

Or install mpga, the plugin that ships this one along with the rest of its 18 skills, 26 commands, 3 agents.

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/skills/benrben/mpga/drift-check.svg)](https://agentmods.dev/skills/benrben/mpga/drift-check)

Your own site

<a href="https://agentmods.dev/skills/benrben/mpga/drift-check"><img src="https://agentmods.dev/badge/skills/benrben/mpga/drift-check.svg" alt="Measured on agentmods" height="20"></a>

Per session 35 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 569 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. Scan, not verified.

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	$0.00035	$0.00569
Opus 5	$0.00017	$0.00284
Sonnet 5	$0.00007	$0.00114
Haiku 4.5	$0.00003	$0.00057

Measured 4d ago against content hash e4a17439e845, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

mpga-drift-check 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 4d 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.

mpga-plugin/skills/drift-check/SKILL.md · 67 lines

How it starts

The opening of the file, as written. The whole thing — 67 lines — stays where its author put it; the contents beside it link to each section on GitHub.

drift-check

Evidence drift is never tolerated — stale links and unverified claims get caught and fixed.

Trigger: After file writes (automatic via hook), or on demand.

Delegation

This skill is a thin wrapper around the auditor agent's drift detection capabilities. The auditor owns drift classification and severity tiers. This skill exists for convenience and hook integration.

Protocol

Invoke the auditor agent in drift mode with the appropriate sub-mode:
- Quick check (default, used by hooks): auditor runs drift-quick for the affected scope
- Full drift review (on demand): auditor runs drift across all scopes
- CI gate check: auditor runs drift-ci with threshold enforcement
The auditor will: a. Detect all drift findings b. Classify each by severity: CRITICAL, HIGH, MEDIUM, LOW c. Auto-heal LOW (cosmetic) findings d. Report everything else with recommended actions

Shortcut commands (these invoke the auditor under the hood):

mpga drift --quick --scope <scope>
mpga drift --quick
mpga drift --ci --threshold 80

Hook Integration

This skill is called automatically by the PostToolUse hook after Write/Edit operations. In hook mode, output should be minimal — only warn if drift is detected. The auditor runs in drift-quick mode during hooks for speed.

Severity Tiers

CRITICAL: broken evidence links to deleted files/functions — blocks shipping, fix immediately.
HIGH: evidence links to renamed/moved symbols — needs healing.
MEDIUM: stale evidence (>30 days old, file significantly changed) — should verify.
LOW: cosmetic drift (whitespace, formatting) — auto-healable.

Voice announcement

If spoke is available (mpga spoke --help exits 0), announce completion:

mpga spoke '<brief 1-sentence result summary>'

Keep the message under 280 characters. This plays the result in Trump's voice — TREMENDOUS.

Output

Output comes from the auditor agent's drift report. See auditor agent for full output format:

Number of findings per severity tier
Number of links auto-healed (LOW tier)
Links that need manual review (HIGH/CRITICAL)
Overall health percentage
Prefer scope-local drift checks during active work; reserve repo-wide reports for CI or explicit review

Read the full file on GitHub · 67 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.

4d ago First seen · 67 lines · 35 tokens per session scan A e4a17439e845

Subscribe to this mod's changes

mpga-drift-check is a skill published in the GitHub repository benrben/MPGA (5 stars, last pushed 5mo ago), licensed MIT. It adds 35 tokens to every session and 569 once invoked, about $0.0002 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 2026-08-31.

Research

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

chronicle

Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…

microsoft/vscode · 72 tokens

imagegen

Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…

openai/codex · 113 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens