everruns/yolop/yolop-config

Claude Code and agent skill by everruns/yolop

Trust tier 3
  • community
Source check pending

Checking that the SKILL.md file is still in the repository.

Manage Yolop settings, continuation budgets, persistent default model, and model catalog through the config command.

Install

npx vskill@latest install everruns/yolop/yolop-config

SKILL.md

Yolop configuration

Use Bash to run yolop config. The command works both detached and through the current Yolop session. Attached calls remain attached inside scripts, pipelines, redirection, substitutions, and background execution.

Persistent settings

  • yolop config get [key] shows all settings or one schema key.
  • yolop config set <key> <value> sets scalar and provider-scoped fields.
  • yolop config set capabilities --json '<object>' appends one capability override; --json preserves the former structured configuration semantics.
  • yolop config clear <key> clears a field, or all capability overrides when the key is capabilities.

Automatic continuation budget

When the user asks to extend the budget, use the matching setting:

  • yolop config set continuation_max_turns 10, default 5 automatic turns.
  • yolop config set continuation_max_tokens 512000, default 256000 tokens.
  • yolop config set continuation_max_seconds 3600, default 600 seconds.

Values must be positive integers. The first reached limit pauses continuation. The original user turn is excluded. Attached changes apply at the next continuation check without resetting usage; change the relevant limits when the user asks for longer work. These are persistent settings, with named profile overrides supported by yolop config --profile <name> set|clear.

At exhaustion Yolop asks the user to approve resuming with a fresh budget. Approval is conversational and requires no specific words; approval alone does not increase the persistent limits. Do not send approval on the user's behalf.

Persistent default model

  • yolop config model show|set <model>|clear inspects, sets, or clears the

persistent default provider and model used by future sessions.

  • A model may be provider/model, provider:model, or a bare id that is unique

in the configured list.

  • These commands do not switch the live session. Use /model, /setup, or the

runtime model controls for live switching.

Model list

  • yolop config models (or models list) shows the ordered list.
  • yolop config models add <provider> <model> [--effort E] [--label L] [--position N] adds an entry.
  • yolop config models rm <model> removes an entry.
  • yolop config models move <model> <position> reorders an entry.
  • yolop config models edit <model> [options] edits an entry.
  • yolop config models reset restores defaults.

Model-list edits persist to settings.toml. When run attached, they also refresh the current session's menu. The config capability intentionally exposes no agent tools. Use these top-level commands instead of get_config or set_config.

Security

  • Security scanPassed, 90 of 100Pattern checks on the skill's files.
  • Model reviewPassed

Quality evaluation

  • Task evaluationNot runNo evaluation yet. Run one in Skill Studio.

Source

Popularity

7-day trend score
0

Not refreshed yet.

Works with

Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.

  • Claude Code
  • Cursor
  • GitHub Copilot
  • Windsurf
  • Codex
  • Gemini CLI
  • Cline
  • Amp
  • Roo Code
  • Goose
  • Continue
  • Kilo Code
  • Junie
  • Trae
  • OpenHands
  • Qwen Code
  • AI Agent
  • Tabnine Chat
  • Sourcegraph Cody
  • Amazon Q
  • Firebase Genkit
  • Sweep
  • Devin
  • Phind
  • Mentat
  • Claude Desktop
  • Aider
  • GPT Pilot
  • Plandex
  • bolt.new
  • v0
  • Replit Agent
  • Anse
  • TypingMind
  • BetterChatGPT
  • LibreChat
  • Warp AI
  • Pieces
  • Fig AI
Embed badge
vskill VERIFIED badge
[![vskill VERIFIED](https://verified-skill.com/api/v1/skills/everruns/yolop/yolop-config/badge)](https://verified-skill.com/skills/everruns/yolop/yolop-config)

Something wrong with this skill or its page? Tell us.