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/LeandroPG19/MemorysWrote 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/leandropg19/memorys/swarm-forge-tdd)<a href="https://agentmods.dev/rules/leandropg19/memorys/swarm-forge-tdd"><img src="https://agentmods.dev/badge/rules/leandropg19/memorys/swarm-forge-tdd/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/leandropg19/memorys/swarm-forge-tdd"><img src="https://agentmods.dev/badge/rules/leandropg19/memorys/swarm-forge-tdd.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 | $0.00138 | $0.00138 |
| Opus 5.5 | $0.00055 | $0.00055 |
| Sonnet 5.5 | $0.00028 | $0.00028 |
| Haiku 4.5 | $0.00014 | $0.00014 |
Grade A, and why
swarm-forge-tdd 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 22d 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.
What it actually says
TDD
El test de comportamiento (unidad, contrato o e2e desde Gherkin) se escribe antes de la implementación. Rojo → código → verde. Encaja con testear-hasta-rojo.mdc.
Prohibido implementar primero y «cubrir después». Un test que nunca estuvo rojo no está verificado.
El implementador razona el rojo si no puede ejecutar; el padre o tester/qa lo corre. Afirmar rojo sin corrida ni razonamiento concreto es mentira.
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.
- 22d ago First seen · 13 lines · 138 tokens per session scan A 5377b6c9a40a
swarm-forge-tdd is a cursor rule published in the GitHub repository LeandroPG19/Memorys (30 stars, last pushed yesterday), licensed Apache-2.0. It adds 138 tokens to every session, about $0.0006 per session on Opus 5.5. 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 2026-09-24.
Other cursor rules, from other repositories
tdd-guide
Cursor rule "tdd-guide" from ulises-jeremias/agent-toolkit, covering agent vs skill rule — why agent (cite clause), when to use vs holistic, caller / skills / handoff, the tdd cycle and when invoked.
tdd-workflow-planning
Enforces proper TDD workflow planning to prevent scope limitation and incomplete test coverage.
tdd-comprehensive-testing
Enforces comprehensive test-driven development practices based on lessons learned from testing gaps and failures.
mcpnuke-tests
Test conventions for mcpnuke — enforces TDD workflow.
debug-issue
When the user reports a bug, an error, or unexpected behavior. Enforces four structured phases — reproduction, failing test, root cause isolation, fix and verify — to stop guess-and-check loops.
ponytail
Ponytail, lazy senior dev mode. Always pick the simplest solution that works.