drift-check

drift-check is a skill for Claude Code from marky291/claude-drift. It costs 79 tokens per session (1,789 once invoked), scanned A, original, MIT.

A project-audit tool that checks Claude-related instructions and configuration against the actual codebase. It looks for broken file or command references, outdated descriptions, and leftover explanations of past migrations.

In plain words
What is it for?
Use it to review CLAUDE.md files, skills, commands, agents, hooks, settings, MCP configuration, and project memory for stale or incorrect guidance.
Why use it?
It helps prevent an AI coding assistant from relying on instructions that no longer match the project's structure, tools, or workflow.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: reads .claude/ paths; mentions CLAUDE.md; mentions subagents.

Part of the claude-drift plugin — 1 skill, 2 agents shipped together

Good fit Use it to review CLAUDE.md files, skills, commands, agents, hooks, settings, MCP…

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/marky291/claude-drift/drift-check
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 marky291/claude-drift --skill drift-check
Clone the repo
git clone --depth 1 https://github.com/marky291/claude-drift

Made for: Claude Code.

Or install claude-drift, the plugin that ships this one along with the rest of its 1 skill, 2 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 drift-check

README.md
[![agentmods](https://agentmods.dev/badge/skills/marky291/claude-drift/drift-check.svg)](https://agentmods.dev/skills/marky291/claude-drift/drift-check)
Your own site
<a href="https://agentmods.dev/skills/marky291/claude-drift/drift-check"><img src="https://agentmods.dev/badge/skills/marky291/claude-drift/drift-check.svg" alt="Measured on agentmods" height="20"></a>
Per session 79 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,789 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 $0.00079 $0.01789
Opus 5 $0.00039 $0.00894
Sonnet 5 $0.00016 $0.00358
Haiku 4.5 $0.00008 $0.00179

Measured 6d ago against content hash 239c79d4fa81, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

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 6d 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.

skills/drift-check/SKILL.md · 133 lines

How it starts

The opening of the file, as written. The whole thing — 133 lines — stays where its author put it; the contents beside it link to each section on GitHub.

ClaudeDrift — drift check

Audit every Claude artifact that steers this project and report where it has drifted from the project's actual reality. The source of truth is the codebase you are invoked from. This is done by reasoning, not by a deterministic script — Claude reads the artifacts and the real code and judges drift, via subagents.

Three kinds of drift matter:

  • Reference drift — a path/command/script an artifact names no longer exists.
  • Context drift — the artifact's description of the architecture, workflow, tech stack, or conventions no longer matches the code, even when every path still resolves. This is the harder, higher-value class.
  • Legacy narration (forward-looking drift) — the artifact is accurate but carries superseded-history framing it shouldn't ("Use Laravel Sail (previously Herd)", "X replaced Y", housekeeping "Updated <date>: previously…"). A steering doc should state the current reality only; the fix strips the history while keeping any genuine removal-guard, provenance ref, or "instead of" comparison. The softest class, but it quietly makes every session read migration backstory.

Arguments ($ARGUMENTS):

  • --user — also audit ~/.claude artifacts (separate, clearly-marked section).
  • --changed — only audit artifacts changed since the last commit (git diff), for cheap re-runs.
  • --forward-only — spotlight only the Legacy narration class: a focused forward-looking cleanup that reports the ⚪ band alone (broken/stale findings are suppressed). Use when the goal is to make artifacts read present-tense, not to chase broken references.
  • --apply — apply accepted fixes without a second prompt.
  • a path — audit a different project directory instead of $CLAUDE_PROJECT_DIR.

The target project dir is $ARGUMENTS's path, else $CLAUDE_PROJECT_DIR, else the current working directory.

Step 1 — Map the Claude flow

Spawn the claude-flow-mapper subagent (Task tool, subagent_type: "claude-flow-mapper") on the project dir (pass --user if given). It returns the artifact inventory, a projectReality grounding summary, install-state caveats, a driftLikelihood rating per artifact, and a memorySystems list — the memory systems it inferred from the project's own artifacts + MCP config (native file memory under ~/.claude/projects/<proj>/memory/ and/or memory MCP servers). Native memory files come back as normal artifacts of type: "memory" and are audited like any other; MCP-backed memory has no files, so its drift is caught when docs that route to it are audited against the MCP config.

Read the full file on GitHub · 133 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. 6d ago First seen · 133 lines · 79 tokens per session scan A 239c79d4fa81

Subscribe to this mod's changes

drift-check is a skill published in the GitHub repository marky291/claude-drift (1 stars, last pushed 2mo ago), licensed MIT. It adds 79 tokens to every session and 1,789 once invoked, about $0.0004 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.

Related

Other skills, from other repositories