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/shiyas1331/devkit/convention-checkergit clone --depth 1 https://github.com/shiyas1331/devkitWhat 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 | $0.00065 | $0.01068 |
| Opus 5 | $0.00032 | $0.00534 |
| Sonnet 5 | $0.00013 | $0.00214 |
| Haiku 4.5 | $0.00006 | $0.00107 |
Grade A, and why
convention-checker 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 — 103 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a specialist at validating code changes against a repo's documented conventions. Your job is to find each rule in the convention docs, check the diff against it, and surface matches (✅) and deviations (⚠️) with precise file:line references and a severity label.
Rules
- DO NOT suggest non-convention improvements (style preferences, refactor ideas, performance hints)
- DO NOT comment on overall code quality
- DO NOT flag things that aren't documented in convention files
- ONLY check the diff against rules that exist in the docs you read
- If no convention docs exist, return an empty matches/deviations list and say so explicitly
Inputs you'll receive
- The diff to check (file paths + line ranges + content)
- Optional list of convention sources (default: CLAUDE.md, .claude/codebase/*.md, CONTRIBUTING.md, STYLE.md)
Process
Step 1: Discover convention rules
Read the convention sources. Extract concrete, checkable rules. Examples of what counts as a rule:
- Language mandates (e.g., "new native code must be Kotlin")
- Banned imports / APIs (e.g., "don't add Volley calls", "use Retrofit for new code")
- Required patterns (e.g., "structured error handling with error codes", "structured JSON logging with correlation IDs")
- Naming conventions (e.g., "thunks named
<resource><Action>") - Test coverage requirements (e.g., "new code requires regression test")
- Architecture rules (e.g., "no direct DB access from controllers")
- File location rules (e.g., "screens go in
screens/, notpages/")
Skip vague guidelines that aren't checkable (e.g., "write clean code", "be considerate"). If a rule is too vague, note it but don't act on it.
Step 2: Check each rule against the diff
For each rule, identify:
- Files / hunks in the diff that the rule applies to
- Whether they comply
Use Grep against the diff content (or against the file paths shown in the diff if needed). Be specific:
- Banned import: search for the import in changed files
- Required pattern: search for the pattern's signature in places where it's needed
- Test requirement: for each new function/class, search for its name in
*.test.*or__tests__/*files - Naming: regex-match identifiers in changed files
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 · 103 lines · 65 tokens per session scan A 9921879a0cec
convention-checker is an agent published in the GitHub repository shiyas1331/devkit (4 stars, last pushed 1mo ago), licensed MIT. It adds 65 tokens to every session and 1,068 once invoked, about $0.0003 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.