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.
git clone --depth 1 https://github.com/bernierllc/agents-environment-configWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/rules/bernierllc/agents-environment-config/development-workflow)<a href="https://agentmods.dev/rules/bernierllc/agents-environment-config/development-workflow"><img src="https://agentmods.dev/badge/rules/bernierllc/agents-environment-config/development-workflow/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/rules/bernierllc/agents-environment-config/development-workflow"><img src="https://agentmods.dev/badge/rules/bernierllc/agents-environment-config/development-workflow.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.01107 | $0.01107 |
| Opus 5.5 | $0.00443 | $0.00443 |
| Sonnet 5.5 | $0.00221 | $0.00221 |
| Haiku 4.5 | $0.00111 | $0.00111 |
Grade A, and why
development-workflow 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 21d 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 — 135 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Development Workflow Rules
Version Control
Branching Strategy
- Feature Branches: Use feature branches for all new development
- Main Branch Protection: Don't commit new changes to main branch
- Conventional Commits: Use conventional commit style for all commits
- Commit Frequency: Make commits for each feature/update
Commit Standards
# Conventional commit format
<type>(<scope>): <description>
# Examples
feat(api): add user authentication endpoint
fix(port): resolve port conflict in development
docs(readme): update installation instructions
refactor(models): extract user validation logic
Code Quality
Documentation Standards
- Public Symbols: Docstrings on every public symbol
- Self-Documenting: Expressive identifiers, minimal explanatory comments
- Code Comments: Only when necessary, prefer clear code over comments
Error Handling
- Explicit Handling: No uncaught exceptions
- Error Messages: Clear, actionable error messages
- Logging: Appropriate logging levels for debugging
Code Organization
- Separation of Concerns: Models, repositories, routes, docs in separate packages
- DRY Principle: Reuse abstractions and ship simplest working solution
- KISS Principle: Keep it simple and straightforward
Development Environment
Python Projects
- Virtual Environment: Ensure local venv exists; create if absent
- Dependency Management: Use requirements.txt or pyproject.toml
- Environment Isolation: Never use system Python for project dependencies
Database Standards
- Default Database: PostgreSQL unless project rules specify otherwise
- Connection Management: Proper connection pooling and error handling
- Migrations: Version-controlled database schema changes
Shell Scripts
- Commander.js: Use commander.js for CLI tools
- Human-Friendly: Clear, helpful output with color coding
- Error Handling: Graceful error handling and user feedback
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.
- 21d ago Changed · +13 tokens per session 0a61c018d7b9
- 1mo ago First seen · 135 lines · 1,094 tokens per session scan A 98876ab835d9
development-workflow is a cursor rule published in the GitHub repository bernierllc/agents-environment-config (11 stars, last pushed today), licensed MIT. It adds 1,107 tokens to every session, about $0.0044 per session on Opus 5.5. 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 cursor rules, from other repositories
mise
Use mise run fix and build only for agent work.
github-workflow
Aggregating MCP server: one authenticated endpoint for every MCP server a platform runs, with meta-tool discovery, toolsets, OAuth 2.1 and SSO through Dex, and Kubernetes custom resources.
practices
Engineering practices and definition of done for agent work.
beads
This project uses Beads (bd) for issue tracking.
Git Worktrees 工作流
A workflow for Git worktrees, which let you have several branches checked out in separate folders at the same time. You can work between branches without stashing changes or switching the current branch.
commits
Commit message standards and conventions.