nainishshafinainishshafi/developer-productivity-skills/AGENTS.md

developer-productivity-skills

AGENTS.md1 starsChanged 4 days agoMITView on GitHub

[!IMPORTANT] ALWAYS use the local virtual environment for running Python scripts in this workspace: - Windows (PowerShell / CMD): .\.venv\Scripts\python.exe <script> <args> - Linux / macOS (Bash / Zsh): .venv/bin/python <script> <args>

Where files are headingNew AGENTS.md files have more rules about keeping secrets out of the code, and fewer about code style.
Of the AGENTS.md files we read, the 31,843 first seen in the last six months, against the older ones: the kind of rule that gained most share, and the kind that lost most. About files like this in general, not this one, and an estimate, since a kind is a pattern in the words.
In this repository32 other files it gives its agents.
- agent-orchestratorSkill
- algorithmic-complexity-analyzerSkill
- api-securitySkill
- architectural-planningSkill
- caching-queues-reviewerSkill
- code-reviewerSkill
- csharp-developerSkill
- design-pattern-detectorSkill
- detect-overengineeringSkill
- github-security-scanner-hookSkill
- java-developerSkill
- legacy-code-modernizationSkill
- llm-as-judgeSkill
- load-memorySkill
- nodejs-executorSkill
- playwright-bdd-testerSkill
- powershell-writerSkill
- python-api-writerSkill
- python-developerSkill
- python-linterSkill
- react-developerSkill
- remote-pod-log-analyzerSkill
- save-memorySkill
- scan-halucinated-testsSkill
- scan-repo-readmeSkill
- skill-creatorSkill
- sql-connectorSkill
- sql-executorSkill
- sync-github-forksSkill
- trace-code-contextSkill
- troubleshoot-and-fixSkill
- typescript-developerSkill

The file

We split this AGENTS.md into the rules it gives an agent

4 rules. About 0 are common, 1 is distinctive, and 3 are very specific to this project.

≈0
Common · estimate
Many files like this have a rule of this kind.
≈1
Distinctive · estimate
This author's own choices. Worth a look.
3
Very specific
Tied to their project's names, files or tools. Probably skip.

Common
Distinctive
Very specific

Very specific:
Every script execution, test runner, linting task, and tool command requiring Python must use .\.venv\Scripts\python.exe.
line 13
Very specific:
Use the project-memory MCP server and skills (save-memory and load-memory) to track project truths, active WIP, and lessons learned.
line 19
Very specific:
Always run check-overengineering (via orchestrator-context-manager.py check-overengineering --file <path>) or language-specific anti-bloat …
line 30
Distinctive:
Never introduce speculative generality (YAGNI), 1:1 single-implementation interfaces, redundant DTO layers, or trampoline pass-through …
line 31

≈ “Common” is an estimate: at least 1 in 5 of the 40,246 AGENTS.md files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.

Files

AGENTS.md

Project Guidelines & Agent Instructions

Python Execution Standard (STRICT)

[!IMPORTANT] ALWAYS use the local virtual environment for running Python scripts in this workspace:
Windows (PowerShell / CMD): .\.venv\Scripts\python.exe <script> <args>
Linux / macOS (Bash / Zsh): .venv/bin/python <script> <args>

Why This Rule Exists:

Never invoke bare python or py: On Windows machines with Microsoft Store redirection aliases, invoking python directly launches the WindowsApp stub which fails inside sandboxes with ApplicationFailedException / NativeCommandFailed. Invoking py fails with No suitable Python runtime found.
The workspace has a fully configured virtual environment located at .\.venv containing Python 3.13 and all necessary project dependencies.
Every script execution, test runner, linting task, and tool command requiring Python must use .\.venv\Scripts\python.exe.

Memory & Sub-Agent Tracking

Use the project-memory MCP server and skills (save-memory and load-memory) to track project truths, active WIP, and lessons learned.
Database location: .project-memory/memory.db.
The 3 memory categories:
- ledger: Permanent architectural decisions, conventions, and security policies.
- sidecar: Active task state and WIP handoffs.
- journal: Session and stage completion recaps requiring BOTH summary (work done) and learnings (mistakes made or avoided).

In-The-Loop Over-Engineering Prevention

Always run check-overengineering (via orchestrator-context-manager.py check-overengineering --file <path>) or language-specific anti-bloat self-checks in the loop (during development, code review, and bug remediation).
Never introduce speculative generality (YAGNI), 1:1 single-implementation interfaces, redundant DTO layers, or trampoline pass-through methods.
Re-run check-overengineering during defect remediation to guarantee bug fixes do not introduce "fix bloat".

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

Reviews can't be read right now.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free