Repository navigation
docs(agents): add AGENTS.md, agent guides and Claude Code guardrails - #2
Merged
Merged
Conversation
AGENTS.md is the entry point shared by most coding agents; CLAUDE.md imports it. Detailed guides and step-by-step workflows live in docs/agents.
…ain glossary Reorganizes AGENTS.md following GitHub's AGENTS.md study and the Claude Code best practices: stack versions and verified commands first, pair programmer role, Always / Ask first / Never boundaries, security and privacy (LGPD), gotchas, precedence and a self-maintenance rule. The domain glossary gives one translation for every business term.
Deny rules for Bash and PowerShell: push to main, force push and trusting the HTTPS development certificate. Personal settings stay out of git.
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
What
Adds the guidelines for the AI coding agents that commit to this repository, following the practices recommended by GitHub's study of 2,500+ AGENTS.md files, the Claude Code documentation and the agents.md specification.
AGENTS.md: entry point read by most agents (Codex, Copilot, Cursor, Gemini, Claude), 135 lines:localhost, HTTPS certificate;CLAUDE.md: importsAGENTS.md, so Claude Code shares the same source of truth..claude/settings.json: Claude Code permission rules that block pushing tomain, force pushing and trusting certificates, for both Bash and PowerShell.docs/agents/guides/: architecture, domain glossary (pt-BR → code → wire), coding conventions, testing, documentation, local environment, communication.docs/agents/workflows/: git and pull requests, implement a feature, record a decision, review dependency updates.docs/agents/trabalhando-com-agentes.md(Portuguese): how the owner asks for tasks, reviews pull requests and pairs with agents..gitignoreexcludes.claude/settings.local.json.Why
Commits will be made by AI agents. The rules that protect the project must be explicit, short enough to be followed, and enforced where possible.
Decisions taken by the owner:
Co-authored-bylines.How to test
AGENTS.mdand follow the links: all 18 agent-related Markdown files were checked for broken relative links.dotnet dev-certs https --check --trust, which only reads). Claude Code also enforced them live during this session.dotnet build,dotnet testanddotnet format --verify-no-changespass (documentation and configuration only).Checklist
dotnet test --solution ControlService.slnxpasses locallydocs/03-regras-de-negocio.md(not applicable)