Borrowing it
Nothing to install: this file belongs to dbareagimeno/enu. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/dbareagimeno/enu/develop/.claude/skills/salud/SKILL.mdgit clone --depth 1 https://github.com/dbareagimeno/enuWrote 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/skills/dbareagimeno/enu/salud)<a href="https://agentmods.dev/skills/dbareagimeno/enu/salud"><img src="https://agentmods.dev/badge/skills/dbareagimeno/enu/salud/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/skills/dbareagimeno/enu/salud"><img src="https://agentmods.dev/badge/skills/dbareagimeno/enu/salud.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 | $0.00100 | $0.01249 |
| Opus 5.5 | $0.00040 | $0.00500 |
| Sonnet 5.5 | $0.00020 | $0.00250 |
| Haiku 4.5 | $0.00010 | $0.00125 |
Grade A, and why
salud 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 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.
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 — 92 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Pasada de salud (capa mecánica)
Cuatro detectores mecánicos: reproducibles, sin falsos positivos de LLM, y
cada uno caza una familia de fallos que las verificaciones habituales (CI por
push, DoD por sesión, juicio por diff) no cubren. El principio: el
calendario solo es buen trigger para lo que cambia aunque el código no cambie
(el corpus de fuzzing crece, las CVEs se publican, los interleavings son
loterías); para lo demás el trigger es el cambio (eso ya lo hacen CI y
/juicio).
Ejecuta los cuatro pasos; los largos, en paralelo/segundo plano. Presupuesto orientativo total: 30-45 min de máquina, casi todo desatendido.
1 · Fuzzing (dianas en internal/runtime/fuzz_test.go)
Seis dianas con invariantes fuertes sobre la lógica 🔒: FuzzSSEChunkSplit
(S20, equivalencia bajo partición de chunks), FuzzDecodeInputChunkSplit
(CP-7, disciplina pending/flush del driver), FuzzComputeDiffReconstruct
(S25, aplicar los hunks reconstruye b), FuzzWrapText y FuzzTruncateText
(S22, anchura acotada + contenido conservado), FuzzMarkdownStreamingSafe
(S23, prefijos arbitrarios no rompen).
for t in FuzzSSEChunkSplit FuzzDecodeInputChunkSplit FuzzComputeDiffReconstruct \
FuzzWrapText FuzzTruncateText FuzzMarkdownStreamingSafe; do
go test ./internal/runtime/ -run "^$t$" -fuzz "^$t$" -fuzztime 3m
done
- El corpus vive en
$GOCACHE/fuzzy se acumula entre pasadas: cada ejecución parte de donde llegó la anterior — el tiempo invertido se compone. - Un fallo deja un caso mínimo en
internal/runtime/testdata/fuzz/<diana>/: commitéalo (se convierte en test de regresión permanente que CI ejecuta como semilla) y trata el fallo como hallazgo: ¿bug de código (→ arreglar citando la diana) o invariante mal formulado en la diana (→ corregir la diana explicando por qué)? - Si una sesión nueva añade lógica 🔒 parseadora o con bordes, añade su diana aquí; el inventario de dianas crece como el 🔒: nunca se relaja.
- CI solo ejecuta las semillas (un
go testnormal no fuzzea): el coste del fuzzing vive en esta skill, no en cada push.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 92 lines · 100 tokens per session scan A d061bee1ab6a
salud is a skill published in the GitHub repository dbareagimeno/enu (2 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 100 tokens to every session and 1,249 once invoked, about $0.0004 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 2026-08-31.
Other skills, from other repositories
tmux-manual-qa
Run a single manual tmux-based QA scenario for the todo continuation feature against the real CLI (./pi-test.sh) in an interactive TUI. Captures scrollback, asserts deterministic pass/fail count markers, and cleans up test fixtures. Use only for the manual-qa milestone features.
qa
Regression test a San feature by name. Looks for a feature doc in docs/reference/ or docs/packages/2-feature/, runs automated Go tests and interactive tmux tests, then produces a pass/fail report. Use this skill when the user says "qa", "regression test", "test feature X", "verify feature", or references a feature…
pi-package-sandbox-test
Use when verifying that published Pi packages install and load for normal users, including pi.dev package compatibility checks, release validation, Daytona sandbox tests, and package installability audits.
tdd
Test-driven development — write a failing test that names the behavior, watch it fail, implement the minimum to make it pass, then refactor with tests green. Works for new features, bug fixes, and behavior changes. Use when the user says "tdd", "test-first", "write tests first", or wants a change built test-first.
pi-validation-flow
Use when validating Pi monorepo changes after editing TypeScript, Svelte, package manifests, built-in registry, tests, repo tooling, skills, or docs.
investigate
A structured root-cause investigation method for software bugs. It moves from history and reproduction through tested hypotheses, a focused fix, verification, and a report.