An architecture-drift detection command that compares the current codebase with a committed SDL specification. Architecture drift means the code has changed in ways the documented design does not record.

Scanning repositories after feature work, before architecture reviews, or in CI/CD to find topology changes missing from the SDL.

It reveals unrecorded changes to the system's structure so the architecture documentation can stay accurate.

sdl-drift — Command for Claude Code by navraj007in

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.

Clone the repo

git clone --depth 1 https://github.com/navraj007in/architecture-cowork-plugin

Made for: Claude Code.

Or install architect, the plugin that ships this one along with the rest of its 48 skills, 63 commands, 19 agents, 7 MCP servers.

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/commands/navraj007in/architecture-cowork-plugin/sdl-drift/github.svg)](https://agentmods.dev/commands/navraj007in/architecture-cowork-plugin/sdl-drift)

Your own site

<a href="https://agentmods.dev/commands/navraj007in/architecture-cowork-plugin/sdl-drift"><img src="https://agentmods.dev/badge/commands/navraj007in/architecture-cowork-plugin/sdl-drift/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/commands/navraj007in/architecture-cowork-plugin/sdl-drift"><img src="https://agentmods.dev/badge/commands/navraj007in/architecture-cowork-plugin/sdl-drift.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 15 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 2,676 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.

Model	Per session	Once invoked
Fable 5.1	$0.00015	$0.02676
Opus 5.5	$0.00006	$0.01070
Sonnet 5.5	$0.00003	$0.00535
Haiku 4.5	$0.00002	$0.00268

Measured 1mo ago against content hash 904780d74221, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

sdl-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 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.

commands/sdl-drift.md · 311 lines

How it starts

The opening of the file, as written. The whole thing — 311 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/architect:sdl:drift

Trigger

/architect:sdl:drift [--repos <path,...>] [--sdl <path>]

Optional flags:

--repos — Comma-separated repo paths to scan (default: current working directory)
--sdl — Path to the reference SDL (default: auto-detect solution.sdl.yaml or sdl/)

Purpose

Compare the current state of the codebase against a committed SDL specification to surface architecture drift — topology changes that have happened in code but haven't been reflected in the SDL yet.

Use this command:

After a sprint or major feature delivery to keep SDL in sync
Before a quarterly architecture review
As part of CI/CD to detect unreviewed topology changes
After an /architect:import to validate what drifted since last import

Workflow

Step 1: Load Reference SDL

Locate and load the reference SDL:

If --sdl was provided, read from that path.
Otherwise, look for solution.sdl.yaml in the current directory.
If not found, look for sdl/README.md and load the modular SDL directory.
If still not found, abort with:

"No committed SDL found. Run /architect:import first to generate a baseline SDL."

Parse the SDL to extract the reference topology:

All components in architecture.projects.*[] (names, types, frameworks)
All dependencies in architecture.projects.*[].dependsOn[]
All services in architecture.services[] (if present)
All datastores: data.primaryDatabase, data.secondaryDatabases[], data.cache, data.queues
All integrations in integrations.*
Deployment targets in deployment.* and environments[]

Step 2: Scan Current Codebase

Perform a targeted scan of the repos (same evidence sources as /architect:import Step 2, but read only architecturally significant files — not a full deep analysis):

Manifest scan (HIGH confidence evidence):

package.json, go.mod, pom.xml, Cargo.toml, *.csproj, requirements.txt — detect components and tech stack
docker-compose.yml, docker-compose.*.yml — detect services, dependencies, exposed ports
Kubernetes manifests (*.yaml in k8s/, deploy/, infra/) — detect services, ingress, config
Terraform/Bicep/Pulumi files — detect cloud resources
.github/workflows/*.yml, .gitlab-ci.yml, azure-pipelines.yml — detect CI/CD targets and environments

Read the full file on GitHub · 311 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.

1mo ago First seen · 311 lines · 15 tokens per session scan A 904780d74221

Subscribe to this mod's changes

sdl-drift is a command published in the GitHub repository navraj007in/architecture-cowork-plugin (2 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 15 tokens to every session and 2,676 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 2026-09-03.

Debugging ai-agent architecture claude-code-plugin developer-tool scaffolding sdl

nyann:retrofit

Audit an existing repo against a profile and fix what's drifted. Unlike doctor (read-only), retrofit detects missing hooks, misconfigured gitignore, documentation gaps, and non-compliant history, then offers to remediate via bootstrap. Idempotent — safe to re-run.

thettwe/nyann · 61 tokens

sdl-drift

Getting it into your agent

Wrote this? Show the measurements

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

/architect:sdl:drift

Trigger

Purpose

Workflow

Step 1: Load Reference SDL

Step 2: Scan Current Codebase

What this file has done since we first saw it

Other commands, from other repositories

nyann:retrofit

nyann:diagnose

spec-bugfix

zoom-out

analyze

build-fix