devopsby vinhnx

Run Terminal Command

vinhnx/cmd-command

Source vinhnx/vtcode ↗License Apache-2.0

Run a terminal command (usage: /command <program> [args...])

NewMaintained

On-demandOn-demand: invoked explicitly — never occupies your agent's context until called.

DevOps & SRE pack

Last verified 8/14/2026

What it changes

4 of 22 test cases passed with the skill.

Pass-rate lift: —
Tokens: -25%
Agent turns: 0%
Response time: -26%

Model gemini-3.6-flashMeasured 8/14/2026v14 of 22 cases passed with skill · 4 comparable

Tokens, turns and time describe resource use, not a dollar price.

Lift withheld: 4 comparable cases; this report requires 8.

Use this skill

Save it into your project's skills folder. Claude Code picks it up in its next session.

curl -fsSL --create-dirs -o .claude/skills/vinhnx-cmd-command/SKILL.md https://app.decimal.ai/s/vinhnx-cmd-command/SKILL.md

Want it pinned and updatable? pip install "decimalai>=0.15", then decimalai skills add vinhnx-cmd-command, and start Claude Code with claude --plugin-dir "$(git rev-parse --show-toplevel)/.agents"

1 · One-time — install the CLI (docs ↗)

pip install "decimalai>=0.15"

2 · Get the skill — writes .agents/skills/vinhnx-cmd-command/ and pins it in .decimal/skills.lock

decimalai skills add vinhnx-cmd-command

No CLI? Get the same file — curl · raw file

curl -fsSL --create-dirs -o .claude/skills/vinhnx-cmd-command/SKILL.md https://app.decimal.ai/s/vinhnx-cmd-command/SKILL.md

Raw file: /s/vinhnx-cmd-command/SKILL.md ↗ · machine-readable summary at /s/vinhnx-cmd-command.json ↗

Safety checks: 3 of 3 passed

Code scan CleanIntent PassedContent Clean

What's inside

The instructions your model reads when the skill loads.

SKILL.md9 linessingle file

Run Terminal Command

Interpret the user input as the raw command string that follows /command.

Execute that command in the current workspace.
Do not rewrite the command unless quoting or escaping is required by the shell.
Report the important result briefly, including failures.
If the command produces large output, summarize the relevant lines instead of dumping everything.
If the command is empty, respond with the expected usage instead of guessing.

Track record

Benchmark

4 / 22

test cases passed with the skill

Adoption

Users: 0
Times used: 0

Safety and source details

SkillSafety

✓ 3 of 3 passed

Code scan15 of 15 checks clean

0 critical · 0 warning · 0 info — scanner v4 — 8/3/2026

View 15 scanner checks

live_secretremote_code_executionreverse_shelldata_exfiltrationssrf_metadataagent_snoopinganti_refusaldestructive_commandsobfuscated_unicodeunicode_homoglyphopaque_blobsuspicious_urltool_overreachtrigger_abuseprompt_injection_phrasing

IntentSafe

LLM judge · does the skill do what it claims

ContentClean

LLM judge · policy & harmful-content review