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 rules/gosha70/code-copilot-team/stack-constraintsgit clone --depth 1 https://github.com/gosha70/code-copilot-teamWhat 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 | $0.00018 | $0.00473 |
| Opus 5 | $0.00009 | $0.00236 |
| Sonnet 5 | $0.00004 | $0.00095 |
| Haiku 4.5 | $0.00002 | $0.00047 |
Grade A, and why
stack-constraints 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 yesterday.
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 — 54 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Stack Constraints
Rules for managing dependency versions and technology choices across all project types.
Version Pinning Policy
When starting a new project, prefer stable, well-documented versions over bleeding-edge:
- ORM / database tools — use latest stable, not pre-release (e.g., avoid beta/canary/rc).
- Framework — use LTS or latest stable release.
- Language runtime — use latest stable (not beta/rc).
- UI libraries — use latest stable release.
Check package documentation for "stable" vs "experimental" badges before adopting.
Dependency Installation Protocol
When agents create code requiring new packages:
- Agents should install dependencies as part of their task — if they have Bash permission, they must install what they import.
- If an agent lacks permission, pause and instruct the user to install manually before continuing.
- Always test the build after new dependencies — run the dev server, not just the type checker. Static analysis doesn't catch missing runtime packages.
- Check for peer dependency warnings — these often surface as runtime crashes, not compile errors.
When to Downgrade
Downgrade from a newer version to a stable one when:
- CLI or build tooling breaks (common with major version bumps of ORMs, bundlers, and frameworks).
- Runtime behavior changes unexpectedly from documented behavior.
- Community plugins/extensions don't yet support the new version.
- Error messages reference features marked "experimental" or "early access."
Document the version pin and the reason in the project CLAUDE.md or a DECISIONS.md so future contributors know why.
Stack-Specific Notes
Add version constraints relevant to your project in the project-level CLAUDE.md. For example:
## Stack Constraints
- ORM: Prisma 6.x (7.x has breaking CLI changes as of Feb 2026)
- Runtime: Node 20 LTS (not 22 — some deps don't support it yet)
- Framework: Next.js 14 stable (not 15 canary)
This keeps global rules generic while allowing each project to pin its own versions.
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.
- yesterday First seen · 54 lines · 18 tokens per session scan A 1bc7920f295c
stack-constraints is a cursor rule published in the GitHub repository gosha70/code-copilot-team (6 stars, last pushed 2d ago), licensed MIT. It adds 18 tokens to every session and 473 once invoked, about $0.0001 per session on Opus 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
angular-20
This rule provides comprehensive best practices and coding standards for Angular development, focusing on modern TypeScript, standalone components, signals, and performance optimizations.
dev-standard
Apache Superset development standards and guidelines for Cursor IDE.
typescript
Changes to these high-fan-out internals can affect every message, delta, element, or rerun. Keep work in them minimal, and benchmark changes with representative stress-test apps.
coolify-ai-docs
Master reference to all Coolify AI documentation in .ai/ directory.
python_lib
Tips and guidelines specific to the development of the Streamlit Python library, not applicable to scripts and e2e tests.
specs
This directory contains product and tech specs for Streamlit features.