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/tecnomanu/pampaWrote 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/tecnomanu/pampa/quality-assurance)<a href="https://agentmods.dev/rules/tecnomanu/pampa/quality-assurance"><img src="https://agentmods.dev/badge/rules/tecnomanu/pampa/quality-assurance/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/tecnomanu/pampa/quality-assurance"><img src="https://agentmods.dev/badge/rules/tecnomanu/pampa/quality-assurance.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 | $0.00661 | $0.00661 |
| Opus 5 | $0.00331 | $0.00331 |
| Sonnet 5 | $0.00132 | $0.00132 |
| Haiku 4.5 | $0.00066 | $0.00066 |
Grade A, and why
quality-assurance 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 9d 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 — 102 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Project Quality Assurance
This document unifies quality control practices applicable to any project, regardless of the technology stack used.
Quality Principles
- Continuous Verification: Constantly verify code quality throughout development.
- Error Prevention: Preventing errors is better than correcting them later.
- Continuous Improvement: Continually seek ways to improve processes and code.
- Documentation: Maintain accurate documentation of processes and decisions.
Automated Testing
- Regular Execution: Run automated test suites after each significant change.
- Problem Resolution: Don't consider a change complete until all tests pass.
- Coverage: Add new tests for new or modified code.
- Regression: Ensure changes don't break existing functionality.
# Run tests and verify all pass
npm run test
# Framework-specific test commands
php artisan test # Laravel
ng test # Angular
pytest # Python
go test ./... # Go
Process Logging
For complex or long-running tasks, maintain a process log:
- Checklist Creation: Create a log file in
docs/logs-process/. - Naming Convention: Use the format
YYYY-MM-DD_task-description.md. - Content Structure:
- Objectives and scope of the task
- List of subtasks with checkboxes
- Problems encountered and solutions applied
- Decisions made and their justification
Example:
# Authentication Implementation - 2024-08-15
## Objectives
- Implement email/password login
- Add OAuth authentication
- Implement password recovery
## Tasks
- [x] Create user models and migrations
- [x] Implement authentication controller
- [ ] Configure OAuth providers
- [ ] Implement password recovery emails
## Problems and Solutions
- Problem: Conflict with session storage
Solution: Use database-based storage
File Management
When creating or modifying files in the project:
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.
- 9d ago First seen · 102 lines · 661 tokens per session scan A 1c58a17f19e2
quality-assurance is a cursor rule published in the GitHub repository tecnomanu/pampa (30 stars, last pushed 11mo ago), licensed ISC. It adds 661 tokens to every session, about $0.0033 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 2026-08-30.
Other cursor rules, from other repositories
20-testing-generated-and-structure
Testing expectations, generated-file boundaries, and CLI structure contract.
fuzzing
Fuzzing setup and guidelines for skia-rs.
testing-and-quality
The testcomprehensive.py provides systematic testing of all 31 MCP tools.
STAGE_S5_TEST_POINTS
A staged workflow for turning approved requirements into a complete list of test points. It checks required earlier documents and records any requirement that has no matching test point.
testing
Testing conventions for Ion Design System using Jest and Angular Testing Library.
pre-flight-check
Mandatory fail-fast quality gate — run Typecheck, Lint, Test, and Security Audit sequentially before declaring any task done or committing code.