agento
Use when the user types /agento <command> [args]: routes an Agento command to its skills/agento/commands/<name>.md and runs it inline or through its custom agent.
Install / Use
npx skills add david-perry-software/agento --skill agentoInstalls into whichever agent you are using.
SKILL.md
Installable skill definition
Quality Score
Category
Development & EngineeringSupported Platforms
Tags
Our assessment of agento
agento scores 57/100 on our quality scale, 4133rd of 4,607 Development & Engineering skills we index.
Its SKILL.md is 3.3 KB long, split into 7 sections and no code examples: a solid amount of guidance for an agent.
It has no GitHub stars yet, so there is no community track record; judge it on its content.
Maintenance, license and trust
- We could not determine when the repository was last updated.
- No license is declared. By default that means all rights are reserved: you can read it, but reusing or redistributing it is not clearly permitted. Ask the author before building on it commercially.
- Its trust signals score 68/100, with 3 cautions from licensing, adoption, age or documentation. These come from repository metadata, not a code audit — read the skill file before letting an agent act on it.
agento compared with similar skills
All 4 of these similar skills score higher than agento; compare them before choosing.
| Skill | Score | Stars | Updated | Format |
|---|---|---|---|---|
| agento (this skill)by david-perry-software | 57 | 0 | — | SKILL.md |
| taste-skillby Leonxlnx | 100 | 98.5k | 3d ago | CLAUDE.md |
| ai-job-searchby MadsLorentzen | 100 | 50.7k | today | CLAUDE.md |
| claude-howtoby luongnv89 | 100 | 41.9k | 2d ago | CLAUDE.md |
| algorithmic-artby anthropics | 100 | 177.9k | 25d ago | SKILL.md |
Frequently asked questions
- How do I install agento?
- Run
npx skills add david-perry-software/agento --skill agento. The install tabs above show the steps for each supported agent. - Which AI agents does agento work with?
- It is written for Universal, as a SKILL.md file. Other agents that read the same format can often use it too.
- Is agento safe to use?
- It declares no license and scores 68/100 on trust signals. Skills are instructions an agent will follow, so read the file before installing it and do not approve commands you do not understand.
- Is agento still maintained?
- We could not determine when the repository was last updated.
Skill content
View source on GitHubname: agento description: "Use when the user types /agento <command> [args]: routes an Agento command to its skills/agento/commands/<name>.md and runs it inline or through its custom agent." argument-hint: "<command> [args]" user-invocable: true disable-model-invocation: true
Agento command router
Routes /agento <name> [args] in every session (Copilot and Local) to the
command file skills/agento/commands/<name>.md and runs it inline or through its
custom agent. Follow the steps below in order.
1. Parse
The first whitespace token of the arguments is the command name; the rest is the command's argument, passed on unchanged. With no arguments, list the commands (step 4) and stop.
2. Redirect rule
A name carrying a .prompt.md, .prompt, or .md suffix — or a leading / — is
the canonical command written in an old form. Strip the suffix and any leading
/, say in one sentence which canonical command it is read as
("Reading /agento <name>.prompt as /agento <name>."), and proceed without
asking.
3. Root discovery
<agento-root> is the path in the session context line
Agento CLI: node <agento-root>/scripts/agento.mjs when that line is present.
Otherwise it is the realpath of this skill's directory, two levels up: the
user-level link ~/.copilot/skills/agento points at <clone>/skills/agento, so
the clone is the real path of the skill directory's parent's parent. Confirm
<agento-root>/skills/agento/commands/ exists.
4. Resolve
Read <agento-root>/skills/agento/commands/<name>.md. If it is missing, reply
with the valid names — the basenames of
<agento-root>/skills/agento/commands/*.md, each printed as
/agento <name> — and stop. Never guess a closest match.
5. Dispatch
The command file's agent: frontmatter decides how it runs:
| agent: | Mode |
| --- | --- |
| missing or agent | inline |
| 📋 Agento Planner, 🏛️ Agento Architect, 🛠️ Agento Mechanic, 🤖 Agento Autopilot | inline, as that agent |
| 🔨 Agento Builder, 🔍 Agento Reviewer | subagent |
- Inline (missing or
agent): follow the command file's body as this turn's instructions, with the argument as its argument. - Inline, as that agent: first read the agent's
.github/agents/*.agent.md(matched by itsname:) and follow its body as the operating rules, then the command body. Where the agent needsask-questionsorbrowserand the tool is absent, its §10 fallback applies (numbered questions in chat; headless verify). - Subagent: run
node <agento-root>/scripts/agento.mjs models pins, take the agent's pin (builder/reviewer), and invoke the agent with the subagent tool available —task(Copilot) withcopilotModelas itsmodel, orrunSubagent(Local) withsubagentModelas itsmodel, omitting the model when it isnull— passing the command body and the argument. Relay the subagent's final message verbatim, including its receipt and result lines and its command blocks.
Whichever mode applies, the dispatched command's §9 receipt line must be printed verbatim as visible text, before any question or other output.
6. No own receipt
The router adds no receipt or result line of its own; the dispatched command owns §9. The router's own outputs are only the redirect sentence and the unknown-name list.
Related Skills
taste-skill
98.5kAgent skills that give coding agents taste: art direction, reference images and a browser check instead of generic AI pages
ai-job-search
50.7kThe job search that runs on your machine. AI job application framework built on Claude Code: evaluate postings, tailor CVs, write cover letters, prep interviews. Fork it and own it.
claude-howto
41.9kA visual, example-driven guide to Claude Code — from basic concepts to advanced agents, with copy-paste templates that bring immediate value.
algorithmic-art
177.9kCreating algorithmic art using p5.js with seeded randomness and interactive parameter exploration. Use this when users request creating art using code, generative art, algorithmic art, flow fields, or particle systems.
Trust signals
From repository metadata: license, adoption, age and documentation. Not a code audit — see the Safety scan above for what the skill file itself contains.
