Skill allagents
Manage AllAgents workspaces, plugins, skills, profiles, and MCP servers using a command-line interface.
- Étoiles GitHub
- 14
- Fichiers
- 1
- Dernier commit
- 11 nov. 2026
- Licence
- MIT
- Outils autorisés
- —
Que fait la skill allagents ?
allagents est une agent skill. Manage AllAgents workspaces, plugins, skills, profiles, and MCP servers using a command-line interface.
Résumé généré à partir du SKILL.md de la skill.
À propos du skill allagents
Managing AllAgents workspaces, plugins, skills, and MCP servers through a command-line interface is what this skill enables. Developers use it to initialize, inspect, update, or configure their AllAgents environment. It functions by resolving a runner, such as the allagents command on the PATH or npx, to discover the current command surface and operational contract.
An agent should load this skill when a user needs to install or remove plugins, manage global profiles, or authenticate MCP servers. Instead of relying on memory, the skill uses machine-readable help to find the correct syntax for every operation. It produces structured JSON outputs and uses specific tools like --jq for processing data. The skill relies on the installed CLI to provide authoritative instructions on positionals, options, and expected output schemas, ensuring that every command matches the current version of the software.
Ce qu'un agent peut faire avec
- 1Configure AllAgents environmentsInitialize or update workspaces and global profiles using the command line.
- 2Manage extensions and serversInstall or remove plugins and skills or manage MCP server authentication.
- 3Automate configuration tasksRun commands for automation by using JSON output and explicit selectors.
- 4Verify system stateCheck that a configuration change was successful by running a status command.
Rédigé à partir du SKILL.md du skill. Chaque cas d'utilisation est vérifié par rapport à une citation de celui-ci.
Comment installer la skill allagents
Chaque commande copie le dossier de la skill dans le répertoire des skills du client. Redémarrez le client ou démarrez une nouvelle session pour la charger.Installer la skill allagents dans Plugin
/plugin marketplace add allagentsdev/allagents /plugin install allagents@allagents
Installer la skill allagents dans Claude Code
~/.claude/skills/allagents/SKILL.md
$ npx degit allagentsdev/allagents/plugins/allagents/skills/allagents ~/.claude/skills/allagentsInstaller la skill allagents dans Claude Code (project)
.claude/skills/allagents/SKILL.md
$ npx degit allagentsdev/allagents/plugins/allagents/skills/allagents .claude/skills/allagentsInstaller la skill allagents dans Codex
~/.agents/skills/allagents/SKILL.md
$ npx degit allagentsdev/allagents/plugins/allagents/skills/allagents ~/.agents/skills/allagentsInstaller la skill allagents dans Gemini CLI
~/.gemini/skills/allagents/SKILL.md
$ npx degit allagentsdev/allagents/plugins/allagents/skills/allagents ~/.gemini/skills/allagentsInstaller la skill allagents dans Claude.ai
npx degit allagentsdev/allagents/plugins/allagents/skills/allagents allagents && zip -r allagents.zip allagents # claude.ai → Customize → Skills → + → Create skill → Upload a skill → allagents.zip
SKILL.md
Voir sur GitHubAllAgents CLI
The installed AllAgents CLI owns the current command surface and operational contract. This skill only resolves the runner, loads that contract, and applies it. Do not maintain a second command reference here.
Resolve the CLI runner
Choose one runner at the start of the task and use it for discovery, execution, and verification:
- If
allagentsis onPATH, useallagents. - Otherwise, if
npxis available, usenpx --yes allagents. - If neither is available, stop and ask the user to install AllAgents or Node.js with npm.
Examples and returned help_command values use the canonical allagents token. When npx --yes allagents is the selected runner, replace only that leading token before executing every discovery, execution, and verification command. Do not mix runners within one operation.
Load the current contract
- Confirm the selected runner with
allagents --version. - Discover the concise top-level index with
allagents --help --json. - Choose an entry, rewrite its leading runner token when required, and execute its
help_command; group responses reveal only their immediate children. - Continue through nested groups until a leaf command returns its full contract.
- Follow the leaf's
when_to_use, positionals, options, examples, interaction requirement, expected output, output schema, and JSON field allowlist.
The structured response is authoritative. Do not rely on remembered flags, copied examples, aliases, destination behavior, or mutation semantics. If the installed CLI does not advertise an operation, do not invent it.
Execute through the discovered surface
- Run
allagentswithout arguments in an interactive terminal only when the user wants to browse and choose in the TUI. - Use the discovered direct command when the operation is already known.
- For automation, use
--jsonplus only the explicit selectors and non-interactive options advertised by the leaf help. - Use
--json=<fields>only with fields in the leaf's JSON allowlist. Use--jqonly with JSON output. - Prefer an advertised CLI command over hand-editing an AllAgents declaration or generated client file.
- Preserve the exact scope, destination, profile, clients, and other ownership selectors requested by the user. If the request is insufficient and the CLI requires a choice, ask rather than guessing.
- Never echo credentials. Supply sensitive values only through mechanisms advertised by the current leaf help.
Treat the process exit code and structured result as authoritative. After a mutation, rediscover and run the relevant read-only list, get, or status command against the same selectors. Do not claim success from a config write alone when the CLI reports a partial update or failed client reconciliation.
Recover from errors
- Read the structured error before retrying.
- If command syntax is rejected, reload root, group, and leaf help; do not fall back to stale syntax.
- If a mutation may have partially applied, inspect current state before any retry.
- Follow only recovery operations exposed by the installed CLI.
Completion
Report the selected runner, command path, explicit selectors, structured result, and verification command. Completion requires the declared state and corresponding live or generated state to agree, or an explicit partial-update result with the CLI-advertised recovery path.
Fichiers de cette skill
1Questions sur la skill allagents
Comment installer la skill allagents dans Claude Code ?
Exécutez npx degit allagentsdev/allagents/plugins/allagents/skills/allagents ~/.claude/skills/allagents. Claude Code charge les skills depuis ~/.claude/skills (tous les projets) ou .claude/skills (un seul projet) et utilise une skill lorsque sa description correspond à la tâche.
Quels clients peuvent utiliser la skill allagents ?
Tout client qui lit le format Agent Skills : Claude Code, Codex, Gemini CLI et claude.ai (envoi sous forme de ZIP). Les scripts de la skill ne s'exécutent que si le client autorise l'exécution de code.
How should I run the AllAgents CLI if it is not on my PATH?
If the 'allagents' command is not on your PATH, you can use 'npx --yes allagents' provided that npx is available.
What should I do if a command syntax is rejected?
If the syntax is rejected, you should reload the root, group, and leaf help instead of falling back to old syntax.