New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Bello Delegate

by Makson179 in Makson179/Bello

Launch an installed Bello supervisor in the background for a repository coding task, or inspect an existing Bello run.

MITAuto-check passedAgent Workflows

Install Bello Delegate

skills CLI
$ npx skills add Makson179/Bello --skill bello-delegate -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install Makson179/Bello bello-delegate --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/Makson179/Bello.git skills-src && mkdir -p .claude/skills && cp -r skills-src/plugins/bello/skills/bello-delegate .claude/skills/bello-delegate && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
bello-delegate
GitHub stars
113
Token cost
~1k tokens
SKILL.md length
504 words
Files
2 (incl. scripts)
Skills in repo
2
Repo updated
First seen
Licence
MIT

At a glance

Launch an installed Bello supervisor in the background for a repository coding task, or inspect an existing Bello run.

  • The user asks to delegate implementation to Bello
  • SKILL.md covers Locate the helper, Start a run and Monitor and report
  • Runs Python scripts from its folder
  • Continue monitoring Bello

What it does

Bello Delegate is an agent skill from Makson179/Bello. Launch an installed Bello supervisor in the background for a repository coding task, or inspect an existing Bello run. Use when the user asks to delegate implementation to Bello, run Bello, continue monitoring Bello, or report Bello status. Do not use merely to advise on or redesign Bello configuration.

Its SKILL.md is about 1k tokens, which your agent loads only when the skill is triggered. The skill folder holds 2 other files, including scripts (for example `scripts/bello_delegate.py`).

It sits in Agent Workflows. It works with Python. The repository describes itself as: 3x more usage on your coding agent, same quality. Have an multi-agent setup in mind? Bello already supports it. Mix models, run agents in parallel, have them check each other’s… The licence is MIT.

When your agent uses it

  • The user asks to delegate implementation to Bello
  • Continue monitoring Bello
  • Report Bello status

Example prompts

  • “/bello-delegate”

Requirements

  • Python 3

What it can do on your machine

Read from SKILL.md and the folder at commit a663b73. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Ships 1 file in scripts/ (Python), which the agent can run.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Bello Delegate loads about 1k tokens when it runs. Until then it costs about 80 tokens; SKILL.md has 504 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~80
When it runs · the whole SKILL.md, loaded when a task matches
~1k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.

SKILL.md

The full file from Makson179/Bello at commit a663b73, republished under its MIT licence (© Makson179). 504 words, ~1,038 tokens.

Download SKILL.mdSave it as .claude/skills/bello-delegate/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.
name
bello-delegate
description
Launch an installed Bello supervisor in the background for a repository coding task, or inspect an existing Bello run. Use when the user asks to delegate implementation to Bello, run Bello, continue monitoring Bello, or report Bello status. Do not use merely to advise on or redesign Bello configuration.

Bello Delegate

Use Bello as the coding workflow and treat the current Codex or Claude Code agent as its launcher and observer. The frontend agent and its model do not choose Bello's coder, runtime, completion, or adversary models.

Locate the helper

Set SKILL_DIR to the directory containing this SKILL.md. For a Claude Code plugin installation that path is ${CLAUDE_PLUGIN_ROOT}/skills/bello-delegate; in other hosts use the loaded skill's own directory. Run the helper with the host's Python 3 executable:

text
python <SKILL_DIR>/scripts/bello_delegate.py status --project <repository>

The helper emits JSON. Use its absolute project and runDirectory fields in later calls.

Start a run

Run from the target repository, or pass it with --project:

text
python <SKILL_DIR>/scripts/bello_delegate.py start --project <repository>

With no task or plan options, the launcher invokes bello with no arguments. Bello then uses the project's existing .supervisor/config.json and its normal task discovery. Do not infer or pass any model, provider, effort, service-tier, runtime, distiller, review, cleanup, or restart option from the frontend session.

When the user supplies or approves a task file or plan file, append the corresponding option. This includes a plan created in a separately approved planning pass; do not invent or add a planning pass yourself:

text
python <SKILL_DIR>/scripts/bello_delegate.py start --project <repository> --task TASK.md --plan PLAN.md

The launcher validates both files as ordinary files inside the repository. It rejects a duplicate active launch and starts Bello in the background. It never installs, updates, authenticates, configures, or publishes Bello. Do not run the Bello configuration advisor as part of this workflow. Run bello config only if the user separately asks to configure Bello.

Runtime supervision, completion review, adversary, and log distiller are independent saved switches. Runtime-off makes no runtime/triage model calls; C/A still follow their own settings. It reduces live protection and allows network inside the filesystem sandbox, not automatic outside-sandbox grants. Distiller is off by default. An approved enabled run downloads Bello's pinned default model once (about 599 MB) and reuses its cache, unless a compatible local bundle is selected. The optional log-distiller dependencies must be installed; native Codex also needs the compatible selection-hook executable. On supported platforms Bello prepares that pinned helper automatically in its private cache, without changing global Codex; other platforms require an explicit compatible build. Report setup failures, do not silently install dependencies, change providers, or disable the selected feature. CPU selection has a 300-second request budget including queue time; do not promise savings. If changed runtime/distiller settings conflict with existing threads, report that a fresh run is required; do not silently restart or rewrite the saved policy.

Show full SKILL.md (102 more words)Show less

Monitor and report

Poll status at reasonable intervals while the helper reports launching or running. Treat process-liveness fields as corroboration, not proof: use .supervisor/config.json, PROGRESS.md, DECISIONS.md, and FINAL_REPORT.md as the durable source of run state. The helper also returns bounded stdout, stderr, and Git-status summaries.

Stop polling when the launcher reports exited, launch_failed, or stale. On success, report the final Bello status, concise result, changed files, and validations from FINAL_REPORT.md. On failure or staleness, report the diagnostic without silently starting a replacement run. Do not edit Bello's .supervisor state files or take over the delegated coding work unless the user explicitly asks.

© Makson179, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 1 other file (scripts) in plugins/bello/skills/bello-delegate of Makson179/Bello.

  • SKILL.md
  • scripts/bello_delegate.py

Open the folder on GitHubat commit a663b73

Compare with similar skills

Bello Delegate next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Bello Delegate compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Bello Delegate this skillMakson179/Bello113—~1kAutomated safety check: PassMIT
MCP Server Builderanthropics/skills180k63 repos~2.3kAutomated safety check: PassApache-2.0
MCP Server BuildershareAI-lab/learn-claude-code78k5 repos~1.2kAutomated safety check: PassMIT
Mem0 CLI Memory Commandsmem0ai/mem067k—~2kAutomated safety check: NotesApache-2.0
MemPalace Setup and OperationMemPalace/mempalace59k—~2.2kAutomated safety check: PassMIT
Google Antigravity SDKgoogle-antigravity/antigravity-sdk-python3.7k—~2.1kAutomated safety check: NotesApache-2.0

Similar skills

  • MCP Server Builder

    anthropics/skills

    Official

    Guides the design and implementation of Model Context Protocol servers in TypeScript or Python, from tool naming and error messages to evaluation.

    180k GitHub starsUsed in 63 repos~2.3k tokens
    Agent WorkflowsAuto-check passed

  • MCP Server Builder

    shareAI-lab/learn-claude-code

    Walks through building MCP servers in Python or TypeScript that expose tools, resources and prompts to Claude, with templates, registration and testing.

    78k GitHub starsUsed in 5 repos~1.2k tokens
    Agent WorkflowsAuto-check passed

  • Mem0 CLI Memory Commands

    mem0ai/mem0

    Adds, searches, lists, updates and deletes memories on the Mem0 platform from the terminal with the mem0 command, including a JSON mode built for agents.

    67k GitHub stars~2k tokensUpdated today
    Agent WorkflowsAuto-check: notes

  • MemPalace Setup and Operation

    MemPalace/mempalace

    Installs and configures MemPalace as a private local palace, a shared-brain hub or a client of an existing hub, including MCP registration and version-correct initialization.

    59k GitHub stars~2.2k tokensUpdated yesterday
    Agent WorkflowsAuto-check passed

  • Google Antigravity SDK

    google-antigravity/antigravity-sdk-python

    Design, implement, and debug autonomous AI agents and multi-agent systems using the Google Antigravity (AGY) SDK.

    3.7k GitHub stars~2.1k tokensUpdated 2 days ago
    Agent WorkflowsAuto-check: notes

  • SkillOpt-Sleep Self-Improvement Cycle

    microsoft/SkillOpt

    Official

    Runs a nightly or on-demand sleep cycle for a local Codex agent: review past sessions, replay recurring tasks and stage validated skill and memory edits for adoption.

    18k GitHub stars~2.3k tokensUpdated 3 days ago
    Agent WorkflowsAuto-check passed

More from Makson179/Bello

  • Bello Config Advisor

    Makson179/Bello

    Inspect a coding task, repository, and user preferences, then recommend one concrete Bello configuration and decide whether a separate planning pass should precede execution.

    113 GitHub stars~2.4k tokensUpdated today
    Auto-check passed

Works with

Categories

Questions about Bello Delegate

What does Bello Delegate do?

Launch an installed Bello supervisor in the background for a repository coding task, or inspect an existing Bello run. Bello Delegate is an agent skill from Makson179/Bello. Launch an installed Bello supervisor in the background for a repository coding task, or inspect an existing Bello run.

When should I use Bello Delegate?

Bello Delegate fits situations like: the user asks to delegate implementation to Bello; continue monitoring Bello; report Bello status.

How do I install Bello Delegate in Claude Code?

Run `npx skills add Makson179/Bello --skill bello-delegate -a claude-code`. Or copy the skill folder (plugins/bello/skills/bello-delegate in Makson179/Bello) into .claude/skills/bello-delegate in your project. Claude Code loads it when a task matches its description.

How do I install Bello Delegate in Codex?

Run `npx skills add Makson179/Bello --skill bello-delegate -a codex`. Or copy the skill folder (plugins/bello/skills/bello-delegate in Makson179/Bello) into .agents/skills/bello-delegate in your project. Codex loads it when a task matches its description.

Can I use Bello Delegate in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add Makson179/Bello --skill bello-delegate -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/bello-delegate, .gemini/skills/bello-delegate, .github/skills/bello-delegate and .opencode/skills/bello-delegate in your project.

What does Bello Delegate need to run?

Going by SKILL.md and its folder, Bello Delegate needs Python for the scripts in its folder. Our summary lists: Python 3.

Does Bello Delegate access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Bello Delegate safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.

What licence does Bello Delegate use?

Bello Delegate is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Bello Delegate use?

About 1k tokens (SKILL.md is roughly 4.2k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Bello Delegate?

Skills that share tags, products or a category with Bello Delegate: MCP Server Builder (anthropics/skills, 180k stars), MCP Server Builder (shareAI-lab/learn-claude-code, 78k stars), Mem0 CLI Memory Commands (mem0ai/mem0, 67k stars) and MemPalace Setup and Operation (MemPalace/mempalace, 59k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Bello Delegate?

Makson179 (a GitHub user) maintains it in Makson179/Bello, which has 113 GitHub stars. The repository holds 2 skills in this directory. The repository was last updated on October 8, 2026.

Source: Makson179/Bello on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.