reviewing-architecture

reviewing-architecture is a skill for Claude Code, Codex from porcupine-md/jonggrang. It costs 25 tokens per session (364 once invoked), scanned A, original, MIT.

An engineering review guide for checking a feature’s technical plan before implementation. It examines how data moves through the system, failure cases, tests, performance, and security.

In plain words
What is it for?
Use it to review feature plans, data models, API behavior, edge cases, testing approaches, performance risks, and security concerns.
Why use it?
It helps find design gaps before coding begins, such as missing error handling, inefficient database queries, weak test coverage, or unchecked permissions.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to review feature plans, data models, API behavior, edge cases, testing approaches, performance risks, and security concerns.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/porcupine-md/jonggrang/reviewing-architecture
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 porcupine-md/jonggrang --skill reviewing-architecture
Clone the repo
git clone --depth 1 https://github.com/porcupine-md/jonggrang

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.

agentmods badge for reviewing-architecture

README.md
[![agentmods](https://agentmods.dev/badge/skills/porcupine-md/jonggrang/reviewing-architecture/github.svg)](https://agentmods.dev/skills/porcupine-md/jonggrang/reviewing-architecture)
Your own site
<a href="https://agentmods.dev/skills/porcupine-md/jonggrang/reviewing-architecture"><img src="https://agentmods.dev/badge/skills/porcupine-md/jonggrang/reviewing-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.

agentmods 80×15 button for reviewing-architecture

Your own site · 80×15
<a href="https://agentmods.dev/skills/porcupine-md/jonggrang/reviewing-architecture"><img src="https://agentmods.dev/badge/skills/porcupine-md/jonggrang/reviewing-architecture.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 25 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 364 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00025 $0.00364
Opus 5 $0.00013 $0.00182
Sonnet 5 $0.00005 $0.00073
Haiku 4.5 $0.00003 $0.00036

Measured 11d ago against content hash fea07a2fd986, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

reviewing-architecture 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.

skills/core/reviewing-architecture/SKILL.md · 32 lines

What it actually says

Reviewing Architecture (Eng Review)

Role Constraints: Lead (Write/Bash access allowed). File Access: Do NOT use literal placeholders for file paths. Use the glob tool to search for the active feature directory under .jonggrang/.output/features/.

Objective

Act as an Engineering Manager to lock in the execution plan. Review architecture, data flow, edge cases, test coverage, and performance.

Execution Steps

  1. Gather Context: Use glob and read to find and review the feature's pitch.md, strategy-review.md, and any existing technical drafts in the active feature directory under .jonggrang/.output/features/.
  2. Review Dimensions:
    • Architecture & Data Flow: Does the data model support the feature? Are DB queries optimized?
    • Edge Cases & Error Handling: What happens when APIs fail, inputs are malformed, or state is lost?
    • Test Coverage: What is the testing strategy (unit, integration, E2E)?
    • Performance: Are there N+1 query risks? Are assets optimized?
    • Security: Are inputs sanitized? Are permissions checked properly?
  3. Iterative Refinement: Discuss identified technical gaps with the user and propose opinionated recommendations.
  4. Save Architecture Plan: Once finalized, use the write tool to output the finalized technical decisions to architecture-review.md in the active feature directory.

Completion Signal

When the architecture plan is finalized and saved, output exactly:

ARCHITECTURE_REVIEW_COMPLETE

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.

  1. 11d ago First seen · 32 lines · 25 tokens per session scan A fea07a2fd986

Subscribe to this mod's changes

reviewing-architecture is a skill published in the GitHub repository porcupine-md/jonggrang (11 stars, last pushed 3d ago), licensed MIT. It adds 25 tokens to every session and 364 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 2026-08-30.