AgentEye CLI Agent Skill

The AgentEye CLI skill (agenteye-cli) is an installable Agent Skill that teaches a coding agent — Claude Code, Codex, and compatible tools — to operate your AgentEye deployment through the agenteye CLI from plain-English requests: “is anything broken today?”, “give CI a key that can only push events”, “ack the firing incident and assign it to me”. It is not a service or a separate binary. It is a small instruction bundle that rides on top of the CLI you have already installed: the agent shells out to agenteye --json …, parses the clean JSON, and answers you in prose. Everything it can do, you could do yourself by typing the same commands.

---

​

How it relates to the other AgentEye interfaces

AgentEye gives you four ways to reach the same data and controls. They complement each other:

​

vs. the in-dashboard AI Assistant — an important distinction

These are two different tools with very different blast radii:

• The in-dashboard AI Assistant (assistant.md) is a chat embedded in the dashboard, backed by an internal agent container. It is read-only plus approval-gated authoring: it can draft saved queries and dashboards, but every write pauses for your explicit click-approval, and it never deletes. It is gated by the agent:use permission and only ever sees data for the org you’re viewing.
• The CLI skill runs on your workstation inside your coding agent and drives the agenteye CLI as you. It can perform the CLI’s full surface, including mutations — create/rotate/disable API keys, change org settings, resolve incidents, delete saved queries — bounded only by the permissions of your CLI login. Treat it exactly as carefully as you would treat running those commands by hand.

---

​

Prerequisites

1. The agenteye CLI installed and on PATH (see cli.md — pipx install agenteye).
2. Your dashboard URL set (AGENTEYE_DASHBOARD_URL, or the agent passes --base-url).
3. A logged-in session: run agenteye login yourself first. The skill cannot complete the emailed one-time-code login for you — it will tell you to run agenteye login if the session is missing or expired (CLI exit code 4).

---

​

Installing the skill

Agent Skills are folders that contain a SKILL.md (plus optional references). You install the agenteye-cli skill by placing its folder where your agent looks for skills:

• Claude Code — copy the agenteye-cli/ folder into ~/.claude/skills/ (available in every project) or into <your-repo>/.claude/skills/ (scoped to that repo). Claude Code auto-discovers it; verify with the /skills list, or just ask a question that matches its description.
• Codex (OpenAI) — Codex reads the same SKILL.md. The bundled agents/openai.yaml sets allow_implicit_invocation: true, so Codex auto-selects the skill when a task matches; otherwise invoke it explicitly as $agenteye-cli.

The skill is maintained alongside the agenteye CLI and is distributed as part of your AgentEye package — if you don’t have the agenteye-cli folder, ask your AgentEye contact. Nothing about it is gated: it needs no Docker image and no credential, because it only drives the public agenteye CLI against your own dashboard.

---

​

Safety — mutations do NOT prompt when an agent runs the CLI

Read this before letting an agent make changes. The agenteye CLI normally asks “are you sure?” before a destructive action. It auto-skips that confirmation whenever it is not attached to a terminal — which is exactly how a coding agent runs it — and --json skips it too. So the safety prompt will not fire for the agent. The skill is written to compensate: it is instructed to state the exact command it will run and get your explicit OK before any state change. Keep that discipline — when you drive AgentEye through an agent, you are the confirmation step. The state-changing commands to watch for:

• keys create / update / disable / regenerate
• users create / update / disable / enable
• settings set
• alerts create / update / delete / test
• the writing incidents subcommands: ack / assign / resolve / open / comment-add / comment-delete / subscribe / unsubscribe
• query create / update / delete
• agent rename / delete
• orgs switch

Everything under Observe (events, sessions, evals, errors, list, whoami, orgs list/current/perms) is read-only and changes nothing. Because the agent acts as you, it can only do what your login is permitted to do — permissions are resolved per org (see api-keys.md). A command you lack permission for returns exit code 5 with the exact permission named, so the agent can tell you precisely what to ask an admin for rather than failing opaquely.

---

​

What you can ask it

The skill maps plain-English intent to the right agenteye command, discovering valid values first (list <kind>, whoami) so it doesn’t guess:

• “Is anything broken / failing in the last 24 hours?” → errors --since 24h --aggregate, then a breakdown.
• “Why did session run-001 fail?” → events --session-id run-001 --all + evals --session-id run-001.
• “How is quality trending this week?” → evals --aggregate --since 7d, then drill into low-scoring runs.
• “Give CI a key that can only push events.” → keys create ci --add events:add (it states the command, then creates it and captures the one-time secret).
• “Who has access? Make Dana read-only.” → users list → users update dana@… --permission-set read-only (after confirming with you).
• “Ack the firing incident and assign it to me.” → incidents list --state firing → incidents ack <id> / incidents assign <id> you@….

For the exact commands, flags, and JSON shapes behind these, see cli.md and cli-recipes.md.

---

​

See also

• CLI — full command and flag reference for agenteye.
• CLI recipes for agents — copy-paste jq patterns and exit-code handling.
• AI Assistant — the in-dashboard assistant (not to be confused with this terminal skill).
• API Keys — the per-org permission model that bounds what the skill can do.