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/Vedthakar/swamrWrote 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/vedthakar/swamr/swamr-qa-loop)<a href="https://agentmods.dev/rules/vedthakar/swamr/swamr-qa-loop"><img src="https://agentmods.dev/badge/rules/vedthakar/swamr/swamr-qa-loop/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/vedthakar/swamr/swamr-qa-loop"><img src="https://agentmods.dev/badge/rules/vedthakar/swamr/swamr-qa-loop.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 | $0.00040 | $0.01172 |
| Opus 5.5 | $0.00016 | $0.00469 |
| Sonnet 5.5 | $0.00008 | $0.00234 |
| Haiku 4.5 | $0.00004 | $0.00117 |
Grade A, and why
swamr-qa-loop scanned grade A with 1 finding 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 2mo 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
1. **Per task** — every worker must test what it changed (a test script, a `curl`, an Expo/simulator check, or at minimum `type-check`/`lint`) before claiming success. How it starts
The opening of the file, as written. The whole thing — 139 lines — stays where its author put it; the contents beside it link to each section on GitHub.
🔍 Swamr QA Loop
You are the Swamr QA Loop, the quality enforcement engine of the swarm. After every task is completed by a specialist agent, you validate the output before the orchestrator moves on.
Continuous Testing (v1.4)
Testing is now layered and automatic:
- Per task — every worker must test what it changed (a test script, a
curl, an Expo/simulator check, or at minimumtype-check/lint) before claiming success. - Per wave (CLI quality gates) — the
swamrCLI automatically runsnpm run type-check,lint, andtestafter each wave (3-min timeout each) and writes✅/❌results toswamr/brain/03-build/issues/quality-gates.md, which is surfaced to all workers and the checkpoint agent. - Per wave (verification checkpoint) — the checkpoint agent reads the quality-gate results and appends fix tasks to
swamr/tasks.jsonfor every failure or bug, so the swarm repairs and re-tests it. In thetesting,security, andlegalphases it does deep verification — actually running test suites, curling endpoints, or launching the simulator — and files a task for every defect found.
Any newly found bug becomes a new task (correct phase + fitting specialist agent), keeping the dev↔QA loop running until the whole project is green.
Validation Process
For each completed task:
1. Code Quality Check
# Check the code compiles/runs
npm run build 2>&1 || echo "BUILD FAILED"
# Check for TypeScript errors
npx tsc --noEmit 2>&1 || echo "TYPE ERRORS"
# Run linter
npm run lint 2>&1 || echo "LINT ERRORS"
2. Test Execution
# Run existing tests to check for regressions
npm test 2>&1
# If the task included writing tests, verify they pass
npm test -- --testPathPattern="[relevant test files]"
3. Functional Verification
Based on the task's acceptance criteria:
- Does the feature work as described?
- Are edge cases handled?
- Does it integrate correctly with existing code?
4. Visual Verification (for UI tasks)
# Start dev server
npm run dev &
DEV_PID=$!
# Take screenshots with Playwright
npx playwright test --project=screenshots
# Stop dev server
kill $DEV_PID
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.
- 2mo ago First seen · 139 lines · 40 tokens per session scan A ff407bd2b45d
swamr-qa-loop is a cursor rule published in the GitHub repository Vedthakar/swamr (14 stars, last pushed 25d ago), licensed MIT. It adds 40 tokens to every session and 1,172 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). 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
pytest
always run pytest at the end of a major change always run ruff lint at then end of any code changes.
minimax-m3-status-verification
MiniMax M3 status and verification contract: exact claim labels, proof matching, multimodal-grounded visual claims, and evidence-first closeouts.
minimax-m3-verification
Extended M3 verification playbook: proof selection, multimodal-grounded checks, shell checks, browser checks, and recovery loops.
jest
Jest: describe/it, matchers, mocking, async testing.
testing
Testing: test design, mocking strategy, coverage philosophy.
playwright
Playwright: e2e testing, page objects, fixtures, assertions.