What is sruja-architecture?

A workflow for discovering a software project's architecture from its code and drafting Sruja architecture files. Sruja is a language for describing software structure and boundaries.

Use it to map components and dependencies, create or update `repo.sruja`, review architecture proposals, or validate architecture changes before they are promoted.

It helps create architecture documentation from code evidence without requiring prior knowledge of Sruja's file format. It also supports checking whether the documented architecture matches the code.

sruja-architecture — Skill for Claude Code and Codex by sruja-ai

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 sruja-ai/sruja --skill sruja-architecture

Clone the repo

git clone --depth 1 https://github.com/sruja-ai/sruja

Made for: Claude Code, Codex.

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/sruja-ai/sruja/sruja-architecture/github.svg)](https://agentmods.dev/skills/sruja-ai/sruja/sruja-architecture)

Your own site

<a href="https://agentmods.dev/skills/sruja-ai/sruja/sruja-architecture"><img src="https://agentmods.dev/badge/skills/sruja-ai/sruja/sruja-architecture/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/sruja-ai/sruja/sruja-architecture"><img src="https://agentmods.dev/badge/skills/sruja-ai/sruja/sruja-architecture.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 66 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 3,919 The whole file, excluding the scripts and references it only reads on demand.

Security scan C 2 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	$0.00066	$0.03919
Opus 5	$0.00033	$0.01959
Sonnet 5	$0.00013	$0.00784
Haiku 4.5	$0.00007	$0.00392

Measured 11d ago against content hash 77181efc513a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade C, and why

sruja-architecture scanned grade C with 2 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.

The scan reads SKILL.md. This mod also ships 2 executable files (scripts/collect-evidence.sh, scripts/validate-refine.sh), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

Downloads and executes remote codehighSupply chain

curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.

curl -fsSL https://sruja.ai/install.sh | bash

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

curl -fsSL https://sruja.ai/install.sh | bash

skills/sruja-architecture/SKILL.md · 303 lines

How it starts

The opening of the file, as written. The whole thing — 303 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Sruja Architecture Skill

Deterministic, evidence-first workflow for generating and maintaining repo.sruja (or architecture.sruja). The skill guides the AI to write valid architecture from real code evidence; no DSL expertise required.

Quick Start

Evidence — Prefer .sruja/author_evidence.json when present and recent; else run sruja sync -r . (do not ask the user to run it). Use .sruja/context.json only for the small fields needed for synthesis (communities, suggested_questions, architecture_digest) and avoid loading .sruja/graph.json unless the user explicitly asks for deep dependency debugging.
Synthesis (Mandatory) — Propose a domain architecture map from evidence. Communities are import-graph hints, not containers; merge/split/rename into domain boundaries.
Questions — Ask 2–5 targeted questions only when evidence is ambiguous (boundaries, externals, datastores, deployment, runtime/data flows).
Output (Never write truth by default) — Write either (a) .sruja/proposals/<id>.json (preferred, incremental) or (b) repo.sruja.working (greenfield / big bang). Do not write repo.sruja until the user explicitly says to promote.
Promote + Validate — For proposals: sruja propose approve <id> then sruja lint repo.sruja. For working DSL: user promotes by renaming/copying to repo.sruja then sruja lint.
Refine — Run sruja drift -r . and iterate; keep unknowns as open questions instead of guessing.
Impact (Optional) — Before refactoring code, run sruja impact <target> -r . --depth 3.

Workflow checklist: [ ] Evidence gathered → [ ] Synthesis done → [ ] Questions (if needed) → [ ] Proposal/working DSL written → [ ] Promotion path used → [ ] sruja lint passed → [ ] Open questions listed

Core Principles

Evidence-first — Gather evidence before modeling.
No guessing — Surface open questions instead of fabricating answers.
Synthesis is required — Import clusters and manifests are facts; architecture boundaries and names are hypotheses backed by evidence.
Minimal DSL — Generate only what evidence supports; prefer small, reviewable proposals.
Validation — Always lint and fix errors before considering complete.

Read the full file on GitHub · 303 lines

Files

What ships with it

26 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.

11d ago First seen · 303 lines · 66 tokens per session scan C 77181efc513a

Subscribe to this mod's changes

sruja-architecture is a skill published in the GitHub repository sruja-ai/sruja (24 stars, last pushed 4d ago), licensed Apache-2.0. It adds 66 tokens to every session and 3,919 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it C with 2 findings (downloads and executes remote code, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

agent-loop agent-skills ai architecture developer-tools rust-lang

sruja-architecture

Getting it into your agent

Wrote this? Show the measurements

What it costs to keep this loaded

Grade C, and why

Downloads and executes remote codehighSupply chain

Makes network callslowCapability

How it starts

Sruja Architecture Skill

Quick Start

Core Principles

What ships with it

What this file has done since we first saw it

Other skills, from other repositories

truecourse-hooks

truecourse-analyze

init-workspace-documentation

truecourse-fix

truecourse-list

release