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.
git clone --depth 1 https://github.com/archubbuck/workspace-architectWrote 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.
[](https://agentmods.dev/agents/archubbuck/workspace-architect/electron-angular-native)<a href="https://agentmods.dev/agents/archubbuck/workspace-architect/electron-angular-native"><img src="https://agentmods.dev/badge/agents/archubbuck/workspace-architect/electron-angular-native/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.
<a href="https://agentmods.dev/agents/archubbuck/workspace-architect/electron-angular-native"><img src="https://agentmods.dev/badge/agents/archubbuck/workspace-architect/electron-angular-native.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00051 | $0.01903 |
| Opus 5.5 | $0.00020 | $0.00761 |
| Sonnet 5.5 | $0.00010 | $0.00381 |
| Haiku 4.5 | $0.00005 | $0.00190 |
Grade A, and why
Electron Code Review Mode Instructions scanned grade A with 1 finding 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.
Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
- Use safe wrappers (child_process with `spawn` not `exec` for large data) This is a copy
100% identical to Electron Code Review Mode Instructions — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 287 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Electron Code Review Mode Instructions
You're reviewing an Electron-based desktop app with:
- Main Process: Node.js (Electron Main)
- Renderer Process: Angular (Electron Renderer)
- Integration: Native integration layer (e.g., AppleScript, shell, or other tooling)
Code Conventions
- Node.js: camelCase variables/functions, PascalCase classes
- Angular: PascalCase Components/Directives, camelCase methods/variables
- Avoid magic strings/numbers — use constants or env vars
- Strict async/await — avoid
.then(),.Result,.Wait(), or callback mixing - Manage nullable types explicitly
Electron Main Process (Node.js)
Architecture & Separation of Concerns
- Controller logic delegates to services — no business logic inside Electron IPC event listeners
- Use Dependency Injection (InversifyJS or similar)
- One clear entry point — index.ts or main.ts
Async/Await & Error Handling
- No missing
awaiton async calls - No unhandled promise rejections — always
.catch()ortry/catch - Wrap native calls (e.g., exiftool, AppleScript, shell commands) with robust error handling (timeout, invalid output, exit code checks)
- Use safe wrappers (child_process with
spawnnotexecfor large data)
Exception Handling
- Catch and log uncaught exceptions (
process.on('uncaughtException')) - Catch unhandled promise rejections (
process.on('unhandledRejection')) - Graceful process exit on fatal errors
- Prevent renderer-originated IPC from crashing main
Security
- Enable context isolation
- Disable remote module
- Sanitize all IPC messages from renderer
- Never expose sensitive file system access to renderer
- Validate all file paths
- Avoid shell injection / unsafe AppleScript execution
- Harden access to system resources
Memory & Resource Management
- Prevent memory leaks in long-running services
- Release resources after heavy operations (Streams, exiftool, child processes)
- Clean up temp files and folders
- Monitor memory usage (heap, native memory)
- Handle multiple windows safely (avoid window leaks)
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 · 287 lines · 51 tokens per session scan A 61e624aa3aa3
Electron Code Review Mode Instructions is an agent published in the GitHub repository archubbuck/workspace-architect (19 stars, last pushed yesterday), licensed ISC. It adds 51 tokens to every session and 1,903 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 1 finding (runs shell commands). It is 100% identical to Electron Code Review Mode Instructions, differing in 0 lines, and is treated as a copy.
Other agents, from other repositories
code-reviewer
Senior Android code reviewer that evaluates changes across five dimensions — correctness, readability, architecture, security, performance. Use for thorough code review before merge.
agentmaster-review
Cost-tiered adversarial code review. Use after implementers complete a plan, or on any diff, branch, or recent changes. Assumes the code is bad — poorly implemented, doesn't scale, violates YAGNI, SOLID, or DRY, hard to test, badly structured, insecure — and makes it prove otherwise with evidence gathered by scout and…
code-analyst
Mid-cost interpretation — trace how code works across files, reproduce and analyze test failures, research dependency changelogs and upgrade impact, run code-graph and architecture queries. Use when the answer requires reading between files, interpreting command output, or external research. Also the escalation target…
Library Curator
Curates changed skills, agents, instructions, workflows, and prompts in this lab by running frontmatter, link, and self-containment checks plus a README index sync, then proposes one fix list before editing anything.
ConfigurationAuditor
Validates updated project instructions against project templates and propagates changes.
party-visionary
Review panelist for long-horizon design commitments. Read-only.