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/mutacion/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/mutacion)<a href="https://agentmods.dev/skills/dbareagimeno/enu/mutacion"><img src="https://agentmods.dev/badge/skills/dbareagimeno/enu/mutacion/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/mutacion"><img src="https://agentmods.dev/badge/skills/dbareagimeno/enu/mutacion.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 | $0.00079 | $0.01207 |
| Opus 5.5 | $0.00032 | $0.00483 |
| Sonnet 5.5 | $0.00016 | $0.00241 |
| Haiku 4.5 | $0.00008 | $0.00121 |
Grade A, and why
mutacion 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 — 88 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Mutation testing (gremlins)
Convierte "creo que a la suite le falta un caso límite" en "este mutante
concreto sobrevivió": gremlins introduce fallos artificiales (invierte una
condición, cambia un + por -, un < por <=) y ejecuta los tests; si
ninguno falla, esos tests no muerden. Complementa el inventario 🔒 — la
cobertura mide qué líneas se ejecutan; la mutación mide si los tests
detectan que están rotas.
Instalación (pineada, fuera del proyecto)
go install github.com/go-gremlins/gremlins/cmd/[email protected]
Nunca en go.mod (cero dependency hell, ADR-001): es un binario externo
de desarrollo. Versión pineada, no @latest — gremlins es 0.x sin garantía de
compatibilidad; si se sube de versión, se prueba primero y se actualiza este
fichero.
Ejecución
Siempre acotada: internal/runtime es un único paquete Go enorme, y el
módulo entero tiene >1000 mutantes cubiertos a ~20 s de suite por mutante —
horas. El alcance se recorta con -E (regexp de exclusión) hasta dejar solo
los ficheros de la sesión, o con -D <rama> para mutar solo el diff.
# Modo sesión: solo los ficheros tocados (ejemplo: diff.go)
gremlins unleash \
-E 'web/.*' -E 'internal/vmwasm/.*' -E 'cmd/enu/main\.go' \
-E 'internal/runtime/[a-ce-z].*' -E 'internal/runtime/d(efault_config|river).*' \
--timeout-coefficient 300 \
--output <scratchpad>/gremlins.json \
.
# Modo diff: solo las líneas que cambia la rama actual frente a main
gremlins unleash -D main --timeout-coefficient 300 -E 'internal/vmwasm/.*' .
Reglas operativas:
--dry-runprimero, siempre: cuenta los mutantes RUNNABLE y permite estimar el coste (mutantes × duración de suite / workers) antes de lanzar.--timeout-coefficient 300es imprescindible aquí: gremlins calcula el timeout por mutante a partir de la duración base dego test, y la caché de Go la hace parecer de milisegundos → todos los mutantes saldrían TIMED OUT falsamente (pasó en el piloto de 2026-07).- Exclusión dura de
internal/vmwasm: cada mutante recompila y re-ejecuta la suite; con wazero es prohibitivo (misma razón por la que CI lo separa). - Ejecuta desde la raíz del módulo.
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 · 88 lines · 79 tokens per session scan A 6ca68376abd8
mutacion is a skill published in the GitHub repository dbareagimeno/enu (2 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 79 tokens to every session and 1,207 once invoked, about $0.0003 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.