guidelines-compliance

An automated code-review agent that checks whether project documentation and delivery settings still match code changes. CI/CD means the automated processes that test and deliver software.

In plain words
What is it for?
Reviewing changes for documentation impact, checking README and AGENTS.md updates, and identifying when dependencies, configuration, breaking changes, or development processes need related updates.
Why use it?
It helps prevent changes from leaving the README, agent instructions, build pipelines, or other project guidance out of date.

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/guidelines-compliance
Clone the repo
git clone --depth 1 https://github.com/devlyai/AgentCheck
Per session 88 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,057 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 $0.00088 $0.01057
Opus 5 $0.00044 $0.00528
Sonnet 5 $0.00018 $0.00211
Haiku 4.5 $0.00009 $0.00106

Measured 2d ago against content hash 7c88a385ed51, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade B, and why

guidelines-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/guidelines-compliance.md · 121 lines

How it starts

The opening of the file, as written. The whole thing — 121 lines — stays where its author put it; the contents beside it link to each section on GitHub.

DESCRIPTION

Ensures project documentation stays current with code changes by identifying when modifications require updates to README, AGENTS.md, CI/CD configs, or other project guidelines. Focuses on maintaining project health and developer onboarding experience.

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

Change Impact Analysis

Analyze what types of changes typically require documentation updates:

  • New Features: User-facing functionality, APIs, configuration options
  • Dependencies: New packages, tools, or external services
  • Configuration: Environment variables, config files, deployment settings
  • Breaking Changes: API modifications, behavior changes, migration requirements
  • Development Process: New tools, testing approaches, deployment procedures

Documentation Types to Consider

User-Facing Documentation

  • README.md: Installation, usage, examples, configuration
  • API Documentation: Endpoint changes, parameter updates, response formats
  • User Guides: Feature explanations, tutorials, troubleshooting
  • Changelog: User-visible changes, breaking changes, migration guides

Developer Documentation

  • AGENTS.md/CLAUDE.md: Development setup, tool usage, testing procedures
  • CONTRIBUTING.md: Development guidelines, code standards, PR process
  • Architecture Docs: System design, component relationships, design decisions
  • Deployment Guides: CI/CD processes, environment setup, release procedures

Configuration Documentation

  • Environment Setup: Required variables, example configs, secrets management
  • CI/CD Configuration: Build processes, test requirements, deployment steps
  • Infrastructure: Server setup, database configurations, monitoring

Project-Specific Documentation Patterns

Before suggesting updates, understand the project's documentation approach:

Read the full file on GitHub · 121 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 · 121 lines · 88 tokens per session scan B 7c88a385ed51

Subscribe to this mod's changes

guidelines-compliance is an agent published in the GitHub repository devlyai/AgentCheck (47 stars, last pushed 1y ago), licensed MIT. It adds 88 tokens to every session and 1,057 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.