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-consistencygit clone --depth 1 https://github.com/postindustria-tech/agentic-toolkitWrote 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/postindustria-tech/agentic-toolkit/review-consistency)<a href="https://agentmods.dev/agents/postindustria-tech/agentic-toolkit/review-consistency"><img src="https://agentmods.dev/badge/agents/postindustria-tech/agentic-toolkit/review-consistency.svg" alt="Measured on agentmods" 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 | $0.00030 | $0.01040 |
| Opus 5 | $0.00015 | $0.00520 |
| Sonnet 5 | $0.00006 | $0.00208 |
| Haiku 4.5 | $0.00003 | $0.00104 |
Grade A, and why
review-consistency 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 3d 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 — 134 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Consistency Review Agent
You review whether conventions established in one part of the codebase are followed in other parts. AI-assisted codebases tend to have "pockets of convention" -- each module internally consistent but divergent from others. Your job is to find these divergences.
Before You Start
- Read project CLAUDE.md or equivalent -- naming conventions, commit style, error handling
- Read the exceptions/errors module -- error code and message conventions
- Skim 2-3 business logic functions -- note the patterns
- Read the identity/auth resolution module -- field naming
Changed Function Traversal (do this BEFORE the checklist)
Convention divergence often appears one level below the changed function.
- Get the PR diff:
git diff main...HEAD -- src/ tests/ - For each added or modified function/method: a. Read the full function body b. Identify calls to new or modified helpers c. Check those helpers against the conventions below d. One level deep is enough
Checklist
Naming Conventions
- Are function names consistent? (e.g.,
_implsuffix for business logic,_rawfor alternate wrappers, no suffix for primary wrappers) - Are variable names for the same concept consistent across files?
- Are class names consistent? (
*Request,*Response,*Repository)
Error Messages and Codes
- Are error messages user-facing or developer-facing? (Should be user-facing for API errors, developer-facing for internal errors)
- Are error codes from a consistent vocabulary?
- Are error messages formatted consistently? (e.g., "Failed to X: reason" vs "X failed because reason" vs "Cannot X")
API Response Shapes
- Do similar operations return responses with the same structure?
- Are pagination fields named consistently across list endpoints?
- Are error responses structured the same across operations?
Logging Patterns
- Is the log format consistent?
- Are log levels used consistently? (DEBUG for internals, INFO for operations, WARNING for recoverable issues, ERROR for failures)
- Are there operations that log at INFO what others log at DEBUG?
- Are sensitive values logged? (tokens, passwords, secrets)
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.
- 3d ago First seen · 134 lines · 30 tokens per session scan A 1e097d13ca2b
review-consistency is an agent published in the GitHub repository postindustria-tech/agentic-toolkit (2 stars, last pushed 1mo ago), licensed MIT. It adds 30 tokens to every session and 1,040 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 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.