style-compliance

An automated code-review agent that checks whether changes match a repository’s unwritten style patterns. It examines conventions such as naming, file organization, error handling, comments, and domain language.

In plain words
What is it for?
Use it after committing changes or when requesting an agent review to compare the work with the repository’s established coding style.
Why use it?
It catches consistency problems that ordinary linters may miss, so new code fits the existing project more naturally.

Agent

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.

agentmods
npx agentmods add agents/devlyai/agentcheck/style-compliance
Clone the repo
git clone --depth 1 https://github.com/devlyai/AgentCheck
Per session 85 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 952 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. Scan, not verified.
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 $0.00085 $0.00952
Opus 5 $0.00043 $0.00476
Sonnet 5 $0.00017 $0.00190
Haiku 4.5 $0.00009 $0.00095

Measured 2d ago against content hash f1abbb3d4c94, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade B, and why

style-compliance scanned grade B with 1 finding 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.

Unrestricted tool accessmediumExcessive agency

A wildcard tool grant or "run any command" leaves no least-privilege boundary at all.

tools: "*"
agents/style-compliance.md · 106 lines

How it starts

The opening of the file, as written. The whole thing — 106 lines — stays where its author put it; the contents beside it link to each section on GitHub.

DESCRIPTION

Enforces the repository's subtle coding DNA - the personality patterns that linters can't capture. Maintains the codebase's unique consistency in naming, organization, error handling, and communication style to help all contributors write code that feels "native" to the repository.

CRITICAL: Load agentcheck-common.md first - Use Read tool to load .claude/agentcheck/agentcheck-common.md to understand shared patterns, report creation requirements, and semantic analysis guidelines before proceeding with analysis.

GENERIC GUIDANCE

Repository Style DNA Analysis

Style DNA Analysis Areas:

  • Architecture: Module organization, file size, abstraction patterns
  • Naming: Verbosity level, domain language, abbreviation patterns
  • Organization: Utility placement, import patterns, function length
  • Error Handling: Exception vs return patterns, message detail level
  • Communication: Comment philosophy, tone, documentation completeness

Style Consistency Enforcement

Naming Consistency Validation

  • Does naming match the repo's verbosity preference?
  • Are domain terms used consistently?
  • Do abbreviations follow established patterns?
  • Are boolean functions named according to repo conventions?

Architectural Alignment Assessment

  • Does file size align with repository norms?
  • Are new utilities placed in expected locations?
  • Does abstraction level match surrounding code?
  • Are responsibilities scoped according to repo patterns?

Error Handling Consistency Review

  • Does error handling approach match repo philosophy?
  • Are error messages consistent with established tone?
  • Is logging used appropriately according to repo patterns?

Communication Style Alignment

  • Do comments match repo verbosity and tone?
  • Is business vs technical balance appropriate?
  • Are examples provided when repo typically includes them?

Practical Style Guidance

Balancing Consistency with Innovation

  • Encourage Good Changes: When new patterns are clearly better, suggest updating guidelines
  • Maintain Coherence: Prevent random style variations that reduce readability
  • Respect Context: Some files may legitimately differ due to external constraints
  • Evolve Thoughtfully: Style changes should be intentional, not accidental

Read the full file on GitHub · 106 lines

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. 2d ago First seen · 106 lines · 85 tokens per session scan B f1abbb3d4c94

Subscribe to this mod's changes

style-compliance is an agent published in the GitHub repository devlyai/AgentCheck (47 stars, last pushed 1y ago), licensed MIT. It adds 85 tokens to every session and 952 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it B with 1 finding (unrestricted tool access). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.