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/devlyai/agentcheck/style-compliancegit clone --depth 1 https://github.com/devlyai/AgentCheckWhat 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 | $0.00085 | $0.00952 |
| Opus 5 | $0.00043 | $0.00476 |
| Sonnet 5 | $0.00017 | $0.00190 |
| Haiku 4.5 | $0.00009 | $0.00095 |
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: "*" 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
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 · 106 lines · 85 tokens per session scan B f1abbb3d4c94
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.
Other agents, from other repositories
AGENTS
Agent "AGENTS" from andreibesleaga/GABBE, covering agents.md — universal agent configuration template, 1. project identity (required variables), 2. operational commands, install dependencies and start development server.
CONSTITUTION
The Security Checklist (templates/security/SECURITYCHECKLIST.md) must be completed before every production release.
AGENTS
The core Agents SDK, published to npm as agents. This is the most complex package in the monorepo.
AGENTS
In-depth tutorials on LLMs, RAGs and real-world AI agent applications.
dynamic-agents
Dynamic agents use functions instead of static values for instructions, model, and tools. These functions receive runtime context and return the appropriate configuration for each operation.
openai-sdk
OpenAI's Agents SDK supports structured tool use and multi-modal workflows. ContextForge can serve as a unified tool registry for OpenAI agents.