executor SKILL.md skillA

This file is byte-identical to the first copy the registry indexed. Same content hash, so the same checks give both the same grade.

executor from p2p2sp/viber is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add p2p2sp/viber/executor@git:20260924.1101a9b

Pins git:20260924.1101a9b in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
p2p2sp/viber
Path
docs/archive/superdev/skills/executor/SKILL.md
Versions recorded
1
Latest version
git:20260924.1101a9b, committed Sep 24, 2026
Size
9,374 bytes
Repository stars
8
License
MIT

Runs ONE build, test, lint, type-check or other shell command in a forked context and returns a short verdict - the tool's own summary line, the failures, a log path - instead of the output itself. Use it whenever an outcome must be judged but its output must not enter the caller's context. Two modes, one reply shape: `command:` runs the command verbatim; `log:` + `exit:` + `duration:` runs nothing and reads a log an earlier direct `run.sh` call already wrote. Not for output the caller wants…

Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.

What the file says

# Command executor (fork)

Return a few lines about ONE shell command: did it pass, what did the tool itself say, which cases failed, where the full log sits. In `command:` mode you run it yourself; in `log:` mode it already ran - a caller invoked `run.sh` directly, got back `RESULT: DEVIATION`, and hands you the log that run wrote - so you run nothing and report from that file. The reply is the same either way. The output never leaves this fork - it stays in the log, and the reply is the summary.

# Input contract

`ARGUMENTS` carries one `label: value` per line. An unknown label is ignored. Exactly ONE of `command:` and `log:` is present, and it picks the mode.

**`command:` mode - run it, then report.**

- `command:` (required in this mode) - one shell line, run verbatim: never rewritten, never completed, never "corrected".
- `cwd:` (optional) - the directory to run in, passed to `run.sh` untouched.
- `timeout:` (optional) - seconds, passed to `run.sh` untouched.

**`log:` mode - report on a run that already happened.**

- `log:` (required in this mode) - the path of the log that run wrote, from its `LOG:` line.
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add p2p2sp/viber/executor@sha256:c411a4850163bf8b

The line at the top of this page pins the label git:20260924.1101a9b, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_zlkiutr3teubow7g.svg)](https://markdownregistry.com/a/art_zlkiutr3teubow7g)

2 badge image fetches in 30 days. What the badge shows.

Versions

The registry has recorded 1 version of this file, committed on Sep 24, 2026.

versioncommittedcommitsizeaudit
git:20260924.1101a9b latest2026-09-24 1101a9b 9,374 BA view

Audit of the latest version

A  17 of 17 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.
  • pass: Frontmatter block present
  • pass: Frontmatter declares a name
  • pass: Frontmatter declares a description
  • pass: Size between 200 bytes and 200 KB (9374 bytes)
  • pass: No zero-width or bidi control characters
  • pass: No instruction hidden inside an HTML comment
  • pass: No link to an exfiltration or paste host
  • pass: No credential-shaped string
  • pass: No instruction to send local credentials anywhere
  • pass: No text hidden with inline styles
  • pass: No prompt-injection phrasing
  • pass: No curl or wget piped into a shell
  • pass: No recursive delete of root, home or parent
  • pass: No instruction to read or print local credentials
  • pass: No base64 blob over 200 characters
  • pass: No link to a raw IP address
  • pass: No script tag

Source

GitHub

p2p2sp/viber · 8 stars · license MIT · pushed 2026-10-22 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_zlkiutr3teubow7g
GET https://markdownregistry.com/api/v1/resolve?ref=p2p2sp/viber/executor
GET https://markdownregistry.com/api/v1/blob/c411a4850163bf8b6765bafc1b07368c58f058ae148486a3d9dd49af16042499

Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.

Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.

More from p2p2sp/viber

CLAUDE.md CLAUDE.md file
p2p2sp/viber · CLAUDE.md
git:20261021.e0a0e76 · audit A · 8 stars
signoz SKILL.md skill
p2p2sp/viber · devtools/skills/signoz/SKILL.md · SigNoz logs, dashboards and alerts through its HTTP API.
git:20261016.1921705 · audit A · 8 stars
CLAUDE.md@docs CLAUDE.md file
p2p2sp/viber · docs/CLAUDE.md
git:20261007.aaa7079 · audit A · 8 stars
CLAUDE.md@docs/archive/superdev CLAUDE.md file
p2p2sp/viber · docs/archive/superdev/CLAUDE.md
git:20261007.aaa7079 · audit A · 8 stars
CLAUDE.md@docs/archive/superdev/skills CLAUDE.md file
p2p2sp/viber · docs/archive/superdev/skills/CLAUDE.md
git:20261007.aaa7079 · audit A · 8 stars
adr SKILL.md skill
p2p2sp/viber · docs/archive/superdev/skills/adr/SKILL.md · Judges an intent interview's confirmed decisions against the three ADR criteria (hard to reverse, surprising without…
git:20260924.1101a9b · audit A · 8 stars
e2e SKILL.md skill
p2p2sp/viber · docs/archive/superdev/skills/e2e/SKILL.md · Generate and locally verify Playwright tests for the scenarios of one docs/qa handoff file, then commit them for CI.
git:20260924.1101a9b · audit A · 8 stars
intent SKILL.md skill
p2p2sp/viber · docs/archive/superdev/skills/intent/SKILL.md · You MUST ALWAYS use this skill every time a user wants to do something creative - a new idea, a new feature, build…
git:20260924.1101a9b · audit A · 8 stars
phases-reviewer SKILL.md skill
p2p2sp/viber · docs/archive/superdev/skills/phases-reviewer/SKILL.md · Invoked only by phases skill.
git:20260924.1101a9b · audit A · 8 stars
phases SKILL.md skill
p2p2sp/viber · docs/archive/superdev/skills/phases/SKILL.md · Cuts one confirmed intent into ordered phases, saves phases.md plus one intent.md per phase, and resumes a phased run…
git:20260924.1101a9b · audit A · 8 stars
setup SKILL.md skill
p2p2sp/viber · docs/archive/superdev/skills/setup/SKILL.md · Setup superdev environment.
git:20260924.1101a9b · audit A · 8 stars
simplebuild SKILL.md skill
p2p2sp/viber · docs/archive/superdev/skills/simplebuild/SKILL.md · Build orchestrator for an approved SimplePlan (a plan without a Spec line). Use it ONLY when the approved plan's body…
git:20260924.1101a9b · audit A · 8 stars

Every file in p2p2sp/viber

Other files named executor

executor SKILL.md skill
p2p2sp/p2p2.claude · docs/archive/superdev/skills/executor/SKILL.md · Runs ONE build, test, lint, type-check or other shell command in a forked context and returns a short verdict - the…
git:20260924.1101a9b · audit A · 8 stars

Browse by kind, by grade A, or by owner.