ultraqa

A repeatable quality-check process that runs tests, checks the build, diagnoses failures, applies fixes, and verifies the result. QA means quality assurance: checking that software works as intended.

In plain words
What is it for?
Use it when a project needs repeated testing and debugging until the tests pass and the build succeeds, with a report of remaining problems if the limit is reached.
Why use it?
It keeps unresolved test failures and regressions visible through repeated check-and-fix cycles. The process also records what was tested, what failed, and what changed.

Cursor rule

Install

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.

agentmods
npx agentmods add rules/dasomel/oh-my-cursor/ultraqa
Clone the repo
git clone --depth 1 https://github.com/dasomel/oh-my-cursor
Per session 17 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 447 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00017 $0.00447
Opus 5 $0.00009 $0.00224
Sonnet 5 $0.00003 $0.00089
Haiku 4.5 $0.00002 $0.00045

Measured 2d ago against content hash 60ed481c6469, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

ultraqa 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 2d 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.

rules/workflows/ultraqa.mdc · 65 lines

What it actually says

UltraQA Workflow

Relentless QA cycling — test, verify, fix, repeat until the goal is fully met.

Trigger Keywords

"ultraqa", "qa loop", "keep testing until it works"

Process

Cycle 1:
  1. [QA Tester]  → Run all tests, check build, verify behavior
  2. [QA Tester]  → Report failures with evidence
  3. [Debugger]   → Diagnose root cause of each failure
  4. [Executor]   → Fix each issue (minimal diff)
  5. [Verifier]   → Confirm fix works, no regressions

  If failures remain → next cycle

Cycle N (max 5):
  Repeat steps 1-5

Final:
  [Verifier] → Full verification report

Exit Conditions

  • Success: All tests pass, build succeeds, no regressions
  • Max cycles: After 5 cycles, report remaining issues to user
  • Blocked: Same failure persists after 3 fix attempts → escalate to user

Cycle Report

Each cycle appends to .omc-cursor/qa-report.md:

## Cycle {N}

### Tests Run
- Total: {count}, Passed: {count}, Failed: {count}

### Failures
| Test | Error | Root Cause | Fix Applied | Status |
|------|-------|-----------|-------------|--------|
| {test} | {error} | {cause} | {fix} | FIXED/OPEN |

### Build Status: PASS/FAIL
### Regressions: NONE / {list}

Rules

  • Always show actual test output, not summaries
  • Fix one issue at a time to isolate changes
  • Run full test suite after each fix, not just the failing test
  • Never skip a failing test — fix it or explain why it can't be fixed
  • Announce: "UltraQA Cycle {N}: Running full test suite."
Changes

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.

  1. 2d ago First seen · 65 lines · 17 tokens per session scan A 60ed481c6469

Subscribe to this mod's changes

ultraqa is a cursor rule published in the GitHub repository dasomel/oh-my-cursor (2 stars, last pushed 5mo ago), licensed MIT. It adds 17 tokens to every session and 447 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.