A code-checking skill for Spec-Driven Development, where written specifications guide code changes. It finds files that changed after their related specification was last updated.

Use it to scan configured project areas and report possible gaps between source files and specifications stored in .specs/ or linked paths.

It helps reveal when the code and its documentation no longer describe the same behavior.

sdd:drift — Skill for Claude Code by alfredoperez: A code-checking skill for Spec-Driven Development, where written specifications…

Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code

/plugin marketplace add alfredoperez/sdd

Claude Code

/plugin install sdd

Made for: Claude Code.

Or install sdd, the plugin that ships this one along with the rest of its 11 skills.

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/alfredoperez/sdd/drift.svg)](https://agentmods.dev/skills/alfredoperez/sdd/drift)

Your own site

<a href="https://agentmods.dev/skills/alfredoperez/sdd/drift"><img src="https://agentmods.dev/badge/skills/alfredoperez/sdd/drift.svg" alt="Measured on agentmods" height="20"></a>

Per session 34 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,233 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 5.1	$0.00034	$0.01233
Opus 5	$0.00017	$0.00616
Sonnet 5	$0.00007	$0.00247
Haiku 4.5	$0.00003	$0.00123

Measured 5d ago against content hash ae607fd9da11, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

sdd: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 5d 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/SKILL.md · 94 lines

How it starts

The opening of the file, as written. The whole thing — 94 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Usage: /sdd:drift (no arguments — scans every domain via the union discovery in layered-context).

Detects files that have changed since the corresponding domain's living spec (centralized .specs/<domain>/spec.md or a colocated specPath) was last updated. Useful for catching code that evolved without going through /sdd:specify → /sdd:plan → /sdd:implement, so the living spec is now lying.

Steps

1. Load configuration

Read .sdd.json (if present):

specExempt: glob list of paths to ignore. Default: ["*.config.*", "*.test.*", "**/migrations/**", "scripts/**"].
driftCheck: "off" | "warn" | "gate". Default: "warn". off short-circuits the skill (✓ Drift check disabled (.sdd.json#driftCheck = off)); warn and gate both run the report — gate is informational here (the gating decision is up to the surrounding workflow / CI).
domains: same map used by layered-context. Used to resolve which files belong to which domain and to discover colocated domains.

Stop only if there are both no configured domains in .sdd.json#domains and no .specs/*/spec.md on disk, with: No domains configured and no .specs/ folder — nothing to check. Run /sdd:init or seed .specs/<domain>/spec.md first.

2. Discover domains + last-spec-update commit

Enumerate domains and orphans by running the resolver script:

python3 lib/scripts/resolve-spec-paths.py --all

The JSON domains[] is the union of .sdd.json#domains and the .specs/*/spec.md glob (de-duplicated by resolved path), each with its resolved specPath. The JSON orphans[] is the orphan list (see below).

For each discovered domain:

Take its resolved specPath from the script output (colocated or centralized — already computed).
Get the last commit that modified that resolved path:
```
git log -n 1 --format=%H -- <resolved-spec-path>
```
Skip the domain if the file is untracked (no commits yet) — log ℹ <domain>: spec.md not yet committed; skipping drift check.

Read the full file on GitHub · 94 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.

5d ago First seen · 94 lines · 34 tokens per session scan A ae607fd9da11

Subscribe to this mod's changes

sdd:drift is a skill published in the GitHub repository alfredoperez/sdd (2 stars, last pushed 14d ago), licensed MIT. It adds 34 tokens to every session and 1,233 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.

Code review

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

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

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