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-handoff)<a href="https://agentmods.dev/rules/leandropg19/memorys/swarm-forge-handoff"><img src="https://agentmods.dev/badge/rules/leandropg19/memorys/swarm-forge-handoff/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-handoff"><img src="https://agentmods.dev/badge/rules/leandropg19/memorys/swarm-forge-handoff.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 | $0.00498 | $0.00498 |
| Opus 5.5 | $0.00199 | $0.00199 |
| Sonnet 5.5 | $0.00100 | $0.00100 |
| Haiku 4.5 | $0.00050 | $0.00050 |
Grade A, and why
swarm-forge-handoff 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
Handoff
Cada entrega entre roles es un fichero .cursor/handoffs/*.yml con exactamente:
from,to:especificador|implementador|mejorador|arquitecto|endurecedor|qatype:git_handoff|notetask: una líneacommit: hash onone(solonote)evidence: comando corrido + resultado (ononeen specifier)tests:written|frozen— obligatorio cuandocommitno esnone, y prohibido cuando lo es
El campo tests
Declara qué hizo esta pasada con los tests, y el guardia lo comprueba comparando las regiones
#[cfg(test)] de rust/src —y los ficheros de rust/tests/ enteros— contra ese commit:
written: esta pasada escribió tests. Falla si ninguna región cambió, porque una pasada roja que no movió un test no escribió nada que pueda ponerse rojo.frozen: esta pasada no tocó ningún test. Falla si alguna cambió, que es la pasada verde ajustando un test para que encaje con el código — lo único que las dos pasadas existen para impedir.
Es de dos sentidos a propósito, como los techos del gate: declarar mal cualquiera de los dos da rojo,
así que omitir el campo no es una salida. Si un test de la pasada roja parece incorrecto, se para y se
devuelve un handoff type: note; no se edita.
Hasta 0.27 el campo commit solo tenía que parecer hexadecimal: nadie comprobaba que existiera y
nada comparaba los tests contra él. El protocolo dependía de la honestidad del agente en vez de un
guardia, y dos ciclos de dos pasadas pasaron por ahí sin que nada los mirara.
El receptor no avanza si scripts/validar-handoff.sh falla. No hay entrega «de palabra».
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 · 36 lines · 498 tokens per session scan A 74bfa176e0bf
swarm-forge-handoff is a cursor rule published in the GitHub repository LeandroPG19/Memorys (30 stars, last pushed yesterday), licensed Apache-2.0. It adds 498 tokens to every session, about $0.0020 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
workflow
Development workflow and commit practices.
hook-commits
Set up pre-commit hooks with lint-staged (Prettier), type checking, and tests in the current repo. Use when user wants to add pre-commit hooks, set up Husky, configure lint-staged, or add commit-time formatting/typechecking/testing.
git-author
Git author identity for commits so GitHub attributes contributions correctly.
no-git-commit-by-agent
Keep git commits user-owned.
fusebase-flow-implementation
Fusebase Flow implementation phase rules. Use when editing source code per a locked spec.
development-workflow
Cursor rule "development-workflow" from floriscornel/todo-mcp, covering development workflow for todo mcp, testing & quality assurance, commit structure, branch & pr workflow and publication & releases.