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/jkudjo/oh-my-cursor/qagit clone --depth 1 https://github.com/Jkudjo/oh-my-cursorWhat 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 | $0.00017 | $0.00596 |
| Opus 5 | $0.00009 | $0.00298 |
| Sonnet 5 | $0.00003 | $0.00119 |
| Haiku 4.5 | $0.00002 | $0.00060 |
Grade A, and why
qa 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.
How it starts
The opening of the file, as written. The whole thing — 83 lines — stays where its author put it; the contents beside it link to each section on GitHub.
@qa
Trigger: After implementing a feature, before shipping, or when tests are failing.
Modes
| Flag | Behavior |
|---|---|
--tests (default) |
Run test suite and cycle until passing |
--build |
Run build and cycle until it succeeds |
--lint |
Run lint and cycle until clean |
--typecheck |
Run type check and cycle until clean |
--full |
Run all: typecheck → lint → build → tests |
--report |
Report only, no fixes |
Max cycles: 5. After 5 failed cycles, stop and report remaining issues.
Cycle Protocol
Per Cycle:
-
Run — execute the relevant command(s) for the selected mode.
-
Check — did it pass?
- YES → exit with success summary
- NO → continue to diagnose
-
Diagnose — analyze the failure output:
- What failed and why (root cause, not just symptoms)
- Which files/lines are involved
- Is this a real failure or a test environment issue?
-
Fix — apply the minimum fix to resolve the root cause:
- One root cause at a time
- Verify the fix makes sense before applying
- Never break passing tests to fix failing ones
-
Repeat — go back to step 1 with updated iteration count.
-
Call
update_mode_stateafter each cycle withphase="cycle-N"anditeration=N.
Exit Conditions
| Condition | Action |
|---|---|
| All checks pass | Report: PASS, N cycles used |
| Max cycles (5) reached | Report: FAIL, list remaining issues |
| Unfixable issue (env/config) | Report: BLOCKED, describe blocker |
Final Report
## QA Report: {scope}
**Result:** PASS | FAIL | BLOCKED
**Cycles used:** N/5
**Mode:** {flags}
### Issues fixed
1. `file:line` — description of fix
### Remaining issues (if FAIL)
1. `file:line` — description, repro steps
### Health score: XX/100
(−25 per critical bug, −10 per major, −3 per minor)
Call save_artifact type=specs, slug=qa-{scope-slug}, content=the report.
Call set_memory key=last-qa, value=the report.
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.
- 2d ago First seen · 83 lines · 17 tokens per session scan A bd72481e3a14
qa is a cursor rule published in the GitHub repository Jkudjo/oh-my-cursor (1 stars, last pushed 5mo ago), licensed MIT. It adds 17 tokens to every session and 596 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
code-optimization
Guidelines for optimizing duplicate and poorly structured code.
implementation-workflow
Required plan-first workflow for any implementation request (steps 1–5).
memory-bank
You are an expert software engineer with a unique characteristic: your memory resets completely between sessions. This isn't a limitation - it's what drives you to maintain perfect documentation. At the beginning of each dialogue, you rely ENTIRELY on your Memory Bank to understand the project and continue work…
docs-plain-language
Write clear, jargon-free documentation (README, docs, SECURITY, memory bank).
general
You are running in Cursor IDE. The tools of the MCP server that you are developing are connected to this IDE. When you've modified the code and want to use updated functionality, you must prompt the user to reload the server first.
create-rule-agent
This rule is responsible for creating and updating Cursor rules. Cursor rules govern the structure, hierarchy, style and organization of code in a project. This rule should be invoked in Agent mode when: 1. a user wants to create a new cursor rule, 2. a user wants to update or change an existing rule, 3. user wants…