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 agentmods add agents/postindustria-tech/agentic-toolkit/review-layeringgit clone --depth 1 https://github.com/postindustria-tech/agentic-toolkitWhat 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 | $0.00029 | $0.01116 |
| Opus 5 | $0.00015 | $0.00558 |
| Sonnet 5 | $0.00006 | $0.00223 |
| Haiku 4.5 | $0.00003 | $0.00112 |
Grade A, and why
review-layering 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 2d 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 — 141 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Layering Review Agent
You review whether code is in the correct architectural layer. Projects with strict layer separation frequently have violations when code evolves incrementally. Your job is to find logic that leaked between layers.
Before You Start
- Read project CLAUDE.md or equivalent -- transport boundary pattern
- Read architecture documentation -- full layer diagram
- Read one business logic function to see the pattern
- Read one repository to see the data access pattern
Changed Function Traversal (do this BEFORE the checklist)
Layer violations are most common in new helpers called by the changed code.
- Get the PR diff:
git diff main...HEAD -- src/ - For each added or modified function, read its callees one level deep
- Ask: which layer is each callee in? Does logic belong at that layer? Common miss: business logic leaks into a new repository method; or a new helper in business logic directly touches the session
Layer Definitions
Layer 1: Transport Wrappers (API endpoints, RPC handlers, message handlers)
Allowed: Identity resolution, error format translation, protocol framing, parameter forwarding to business logic
Forbidden: Business logic, validation, data transformation, database access, external service calls
Layer 2: Business Logic (impl functions, services)
Allowed: Orchestration, validation, calling repositories, calling services, raising domain errors, audit logging
Forbidden: Transport imports, protocol-specific types, direct database session management, direct external API calls
Layer 3: Repositories (data access layer)
Allowed: SQL queries via ORM, tenant-scoped data access, model factory methods
Forbidden: Business logic, validation beyond data integrity, external API calls, transport awareness
Layer 4: Adapters (external integrations)
Allowed: External API calls, protocol translation, retry logic, adapter-specific error handling
Forbidden: Direct database access, business rule enforcement, knowing about domain context beyond what's passed
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.
- 2d ago First seen · 141 lines · 29 tokens per session scan A 699a44f4d35f
review-layering is an agent published in the GitHub repository postindustria-tech/agentic-toolkit (2 stars, last pushed 1mo ago), licensed MIT. It adds 29 tokens to every session and 1,116 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.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
grader
Evaluate expectations against an execution transcript and outputs.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.