What is drift-detect?

A read-only method for comparing project plans, roadmaps, documentation, issues, and code to find where they no longer agree. It then produces a repair plan based on evidence.

Use it before restarting an abandoned project, releasing from old plans, or deciding what to rebuild when the documented direction may differ from the code.

It reveals when project memory or planned work has become outdated after implementation or scope changes.

drift-detect — Skill for Claude Code and Codex by OutlineDriven

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 OutlineDriven/odin-claude-plugin --skill drift-detect

Clone the repo

git clone --depth 1 https://github.com/OutlineDriven/odin-claude-plugin

Made for: Claude Code, Codex.

Or install odin, the plugin that ships this one along with the rest of its 26 skills, 14 plugins.

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/outlinedriven/odin-claude-plugin/drift-detect/github.svg)](https://agentmods.dev/skills/outlinedriven/odin-claude-plugin/drift-detect)

Your own site

<a href="https://agentmods.dev/skills/outlinedriven/odin-claude-plugin/drift-detect"><img src="https://agentmods.dev/badge/skills/outlinedriven/odin-claude-plugin/drift-detect/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/skills/outlinedriven/odin-claude-plugin/drift-detect"><img src="https://agentmods.dev/badge/skills/outlinedriven/odin-claude-plugin/drift-detect.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 56 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 3,119 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. Third-party audits

NVIDIA SkillSpector pass 7 Sept 2026

How audits are shown

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	$0.00056	$0.03119
Opus 5.5	$0.00022	$0.01248
Sonnet 5.5	$0.00011	$0.00624
Haiku 4.5	$0.00006	$0.00312

Measured 1mo ago against content hash f86e59a84adc, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

drift-detect 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 1mo 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-detect/SKILL.md · 204 lines

How it starts

The opening of the file, as written. The whole thing — 204 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Drift Detect - reality check and reconstruction planning

Add a temporary evidence layer over the repo, compare stated intent with actual implementation, then synthesize the next repair plan. This is read-only unless the caller explicitly asks to apply follow-up fixes.

The invariant: every drift claim cites a concrete source - issue number, PR, milestone, doc line, file path, symbol, test/CI signal, or git-history signal. Without an evidence line, there is no finding.

When to Apply / NOT

Apply when the user asks whether a roadmap, PLAN, README, milestone, issue backlog, or project memory still matches the code. Also apply before restarting an abandoned project, cutting a release from stale plans, or deciding what to rebuild after scope changed.

Do NOT apply to one local test failure, a known bug with a single repro, a branch-quality audit, or greenfield planning with no existing docs/issues/code to compare. Do not mutate docs, close issues, or edit code during this pass.

Inputs and Flags

Default invocation shape:

drift-detect --sources=github,docs,code --depth=thorough

--sources=github,docs,code - comma list; omit a source only when unavailable or irrelevant.
--depth=quick|thorough - quick samples active surfaces; thorough follows related docs, symbols, and history.
Optional output artifact: .outline/drift-detect/reality-check-YYYYMMDD-HHMM.md when the report is too long for chat.

Workflow

Scope the scan.
- Restate the user's target: whole repo, named plan file, named milestone, release branch, or feature area.
- Resolve sources from flags. If no flags are given, use all three.
- Create a scratch evidence bundle in memory or .outline/drift-detect/evidence.json only when needed for long synthesis. Keep it minimal: {github, docs, code, signals, generatedAt}.

Collect GitHub reality (--sources=github). Use gh JSON output; never scrape web HTML.

gh issue list --state open --limit 200 --json number,title,labels,state,assignees,createdAt,updatedAt,milestone,url
gh pr list --state open --limit 100 --json number,title,state,isDraft,labels,createdAt,updatedAt,mergeStateStatus,reviewDecision,changedFiles,additions,deletions,files,url
gh api repos/{owner}/{repo}/milestones --paginate --jq '[.[] | {number,title,state,open_issues,closed_issues,due_on,updated_at,description}]'

Read the full file on GitHub · 204 lines

Files

What ships with it

2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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.

1mo ago First seen · 204 lines · 56 tokens per session scan A f86e59a84adc

Subscribe to this mod's changes

drift-detect is a skill published in the GitHub repository OutlineDriven/odin-claude-plugin (38 stars, last pushed 24d ago), licensed Apache-2.0. It adds 56 tokens to every session and 3,119 once invoked, about $0.0002 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 2026-08-30.

Claude Code Planning Project management claude-code-plugin claude-code-plugins claude-marketplace claude-plugins outline-driven-development

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

systematic-debugging

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

obra/superpowers · 21 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 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

insight-error-page

Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…

vercel/next.js · 83 tokens