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.
npx skills add on-deck-society/love-stack --skill system-designer-reviewgit clone --depth 1 https://github.com/on-deck-society/love-stackWrote 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/skills/on-deck-society/love-stack/system-designer-review)<a href="https://agentmods.dev/skills/on-deck-society/love-stack/system-designer-review"><img src="https://agentmods.dev/badge/skills/on-deck-society/love-stack/system-designer-review/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/skills/on-deck-society/love-stack/system-designer-review"><img src="https://agentmods.dev/badge/skills/on-deck-society/love-stack/system-designer-review.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 | $0.00039 | $0.00550 |
| Opus 5 | $0.00019 | $0.00275 |
| Sonnet 5 | $0.00008 | $0.00110 |
| Haiku 4.5 | $0.00004 | $0.00055 |
Grade A, and why
system-designer-review 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 10d 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.
How it starts
The opening of the file, as written. The whole thing — 43 lines — stays where its author put it; the contents beside it link to each section on GitHub.
System Designer Review
When activated, perform a structural review of the codebase with a senior system designer's lens.
Review Dimensions
-
Data flow: Trace how data moves between components, services, and storage. Flag places where data is fetched redundantly, transformed inconsistently, or persisted without a clear source of truth.
-
Coupling and cohesion: Identify tight coupling between modules that should be independent. Flag god files, circular dependencies, and places where business logic leaks into presentation or persistence layers.
-
Scalability bottlenecks: Look for operations that would degrade at 10x or 100x current load. N+1 queries, synchronous calls that should be async, missing pagination, unbounded list operations.
-
Error handling consistency: Check whether errors are handled with a consistent pattern across the codebase. Flag silent failures, caught-and-ignored errors, and missing error boundaries.
-
State management: Review how state is owned, updated, and shared. Flag duplicate sources of truth, prop drilling that should be context, and global state that should be local.
-
Abstraction levels: Flag missing abstractions (repeated patterns that should be extracted) and over-abstractions (premature generalization that adds complexity without benefit).
-
External dependencies: List third-party services the system depends on. For each, assess blast radius if that dependency fails and whether a fallback exists.
-
Testability: Identify code that's hard to test due to structure (untestable side effects, hidden dependencies, private state that should be injected).
Output Format
Produce a markdown report structured as:
- Executive summary (3-5 bullet points, the big stuff)
- Findings by dimension (one section per dimension above, with specific file and line references)
- Severity-ordered action list (Critical, High, Medium, Low, what to fix first)
- Questions for the team (anything ambiguous that warrants a discussion before deciding)
What ships with it
1 file 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.
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.
- 10d ago First seen · 43 lines · 39 tokens per session scan A a832d8963bf5
system-designer-review is a skill published in the GitHub repository on-deck-society/love-stack (5 stars, last pushed 4mo ago), licensed MIT. It adds 39 tokens to every session and 550 once invoked, about $0.0002 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.
Other skills, from other repositories
autoreview
Pre-commit/ship code review: Codex default; optional Claude or Pi.
rework-rate
Measure and interpret PR rework rate — the emerging 5th DORA metric.
omh-code-review
This is a Hermes-native code-review workflow skill.
revdiff-plan
Review the last Codex assistant message (plan, analysis, or proposal) with inline annotations in a TUI overlay. Extracts the most recent response from Codex rollout files and opens it in revdiff for review and annotation. Activates on "revdiff-plan", "review plan with revdiff", "annotate plan", "review last response"…
code-reviewer
Code review specialist focused on patterns, bugs, security, and performance.
full-repo-review
Comprehensive four-wave review of all repo source files, producing a prioritized issue backlog.