A codebase analysis command that reconstructs how an existing software project is organised and records it in architecture files.

Use it to create an architecture description, findings report, and project-intent file when taking over or analysing a repository.

It gives developers a documented view of the system based on the code that exists, rather than assumptions about an ideal design.

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

Your own site

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

Per session 14 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 672 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	$0.00014	$0.00672
Opus 5	$0.00007	$0.00336
Sonnet 5	$0.00003	$0.00134
Haiku 4.5	$0.00001	$0.00067

Measured 11d ago against content hash 6bc7447df87f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

import 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 11d 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/import.md · 49 lines

How it starts

The opening of the file, as written. The whole thing — 49 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/architect:import

Trigger

/architect:import [scan context JSON]

Purpose

Analyze an existing codebase folder. Using the static scan results (detected tech stack, frameworks, databases, etc.) as a starting point, perform a deep analysis of the actual source code to understand the architecture, then generate:

solution.sdl.yaml — A complete SDL capturing the inferred architecture
architecture-output/import-analysis.md — Detailed findings report
intent.json — Derived project intent for lifecycle continuity

FIDELITY RULE — SDL must reflect current reality, not aspirations.

The SDL generated by import describes what is actually in the codebase right now — nothing more. Do NOT add patterns, sections, or fields that are absent from the code just because they are good practice or would be present in an ideal architecture.

If no circuit breaker library is detected → do NOT add resilience.circuitBreaker

If no SLO config exists → do NOT add slos.services[] targets

If no health check endpoints exist → do NOT add observability.healthChecks

If no compliance signals exist → do NOT add compliance.frameworks

If no design tokens exist → do NOT add design.typography

Features in features.sdl.yaml = only what is currently built, not what should be built

Costs in costs.sdl.yaml = only costs visible in Terraform/compose/env vars, not ideal projections

Missing patterns belong in the Recommendations section of import-analysis.md, not in the SDL. The SDL is a snapshot of reality. blueprint is for ideal architecture.

Workflow

This command is split across five files for size (each part is a continuation of the previous — read them in order):

Part	File	Steps
1	`command-parts/import-1.md`	Step 0 (detect scan mode) · Step 1 (load scan context) · Step 2 (deep source analysis)
2	`command-parts/import-2.md`	Step 3.1 (mapping rules) · Step 3.2 (SDL output structure)
3	`command-parts/import-3.md`	Step 3.3 (write modular files) · Step 3.4 (confidence report) · Step 3.5 (unknowns & review checklist) · Step 3.2a (multi-file SDL) · Step 3.3 validation
4	`command-parts/import-4.md`	Step 4 (generate import analysis)
5	`command-parts/import-5.md`	Step 5 (generate intent) · Step 6 (generate recommendations)

Read the full file on GitHub · 49 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.

11d ago First seen · 49 lines · 14 tokens per session scan A 6bc7447df87f

Subscribe to this mod's changes

import is a command published in the GitHub repository navraj007in/architecture-cowork-plugin (2 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 14 tokens to every session and 672 once invoked, about $0.0001 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.

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

nyann:doctor

Run nyann's read-only hygiene + documentation audit on the current repo. Emits the same drift sections retrofit uses, but never offers remediation or writes to the filesystem. Use this on session start, in CI, or any time you want to sanity-check a repo without risking mutations.

thettwe/nyann · 61 tokens

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

nyann:apply

Apply an Infrastructure-as-Code change — the highest-stakes mutator in nyann; it can change real cloud infrastructure. Re-runs the plan, shows it, confirms, then applies. Unmistakably opt-in: apply is never the default and destructive applies require a second explicit confirm. For IaC apply intent only (not "apply a…

thettwe/nyann · 85 tokens

import