agentmods.dev

mpga-drift-check

mpga-drift-check is a skill for Claude Code from benrben/MPGA. It costs 35 tokens per session (569 once invoked), scanned A, original, MIT.

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

In plain words
What is it for?
Use it for quick, full, or CI checks across a chosen scope, with severity labels and automatic healing for minor findings.
Why use it?
It helps detect outdated references after files change and makes stale evidence visible before it causes confusion.

Skill for Claude Code

Written for Claude Code: PostToolUse hook event.

Part of the mpga plugin — 18 skills, 26 commands, 3 agents shipped together

not rated 5repo 7mo ago A scan 35 tokens original MIT

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

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/benrben/mpga/drift-check
View source ↗ benrben/MPGA
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.

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.

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.

agentmods badge for mpga-drift-check

README.md
[![agentmods](https://agentmods.dev/badge/skills/benrben/mpga/drift-check/github.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/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.

agentmods 80×15 button for mpga-drift-check

Your own site · 80×15
<a href="https://agentmods.dev/skills/benrben/mpga/drift-check"><img src="https://agentmods.dev/badge/skills/benrben/mpga/drift-check.svg" alt="Reviewed on agentmods" width="80" 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. 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00035 $0.00569
Opus 5.5 $0.00014 $0.00228
Sonnet 5.5 $0.00007 $0.00114
Haiku 4.5 $0.00003 $0.00057

Measured 2mo ago against content hash e4a17439e845, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, 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 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.

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

  1. 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

  2. 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

  3. 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.

  1. 2mo 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 7mo ago), licensed MIT. It adds 35 tokens to every session and 569 once invoked, about $0.0001 per session on Opus 5.5. 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
Related

mpga-drift-check compared with skills from other repositories

mpga-drift-check next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
mpga-drift-checkbenrben/MPGASkill57mo agoMITA35Claude Code
imagegenopenai/codexSkill135ktodayApache-2.0A113Codex
playwright-climicrosoft/playwrightSkill100ktodayApache-2.0A19Claude Code
browser-automationopenclaw/openclawSkill394ktodayMITA36Claude Code
local-ai-agentsmicrosoft/ai-agents-for-beginnersSkill79k4d agoMITA200Claude Code, Codex
systematic-debuggingobra/superpowersSkill316k8d agoMITA21Claude Code
next-cache-components-adoptionvercel/next.jsSkill143ktodayMITA95Claude Code