Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add skills/lakpriya1s/agent-rack/tool-selectionnpx skills add lakpriya1s/agent-rack --skill tool-selectiongit clone --depth 1 https://github.com/lakpriya1s/agent-rackWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/lakpriya1s/agent-rack/tool-selection)<a href="https://agentmods.dev/skills/lakpriya1s/agent-rack/tool-selection"><img src="https://agentmods.dev/badge/skills/lakpriya1s/agent-rack/tool-selection.svg" alt="Measured on agentmods" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00053 | $0.01319 |
| Opus 5 | $0.00026 | $0.00660 |
| Sonnet 5 | $0.00011 | $0.00264 |
| Haiku 4.5 | $0.00005 | $0.00132 |
Grade A, and why
tool-selection scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 4d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 87 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Choosing an agent-rack execution mode
agent-rack exposes two execution models for the same underlying sub-agents. Pick deliberately, don't default to one out of habit.
Synchronous (agent_run, or <agentId>_run shortcuts)
Use for short, one-shot tasks where blocking until it finishes is fine: quick edits, single-file fixes, small investigations. This is the simplest path — prefer it unless there's a specific reason to go async.
If the agent id is already known and fixed for the task (e.g. the user explicitly said "use
codex"), prefer the shortcut tool (mcp__plugin_agent-rack_agent-rack__codex_run, mcp__plugin_agent-rack_agent-rack__claude_run,
mcp__plugin_agent-rack_agent-rack__opencode_run, mcp__plugin_agent-rack_agent-rack__agy_run) over agent_run with an agent
parameter — it's the same call with less to get wrong.
Background (agent_session_create + agent_session_status/_logs/_send/_cancel)
Use when:
- the task is likely long-running (large refactors, broad migrations, anything that could plausibly run past a couple of minutes),
- the user wants to keep working while it runs, or
- the task should be cancelable (
agent_session_cancel) if it goes off track.
Follow-up input works, but not the same way for every agent. Read followUpMode on the
session info (or in agent_list_available) before promising anything:
live(opencode) — write to the running process; the session must still be running.resume(claude,codex) — the agent is restarted with its own resume flag to continue the same conversation, so the current turn must have finished. Acompletedsession is still continuable; that is the precondition, not a dead end.none(agy) — no continuation; the equivalent is a new session with the follow-up as its prompt.
The practical consequence: only opencode can be steered mid-flight. For claude and codex,
follow-up means "another turn once this one lands", so don't tell the user they can interrupt a
running turn.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 4d ago First seen · 87 lines · 53 tokens per session scan A c1ef9be41f18
tool-selection is a skill published in the GitHub repository lakpriya1s/agent-rack (1 stars, last pushed 1mo ago), licensed MIT. It adds 53 tokens to every session and 1,319 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
cao-workflow
Author and run CAO Python workflow scripts — multi-step, parameterized, fan-out orchestrations executed by cao workflow run. Use when the user wants a repeatable multi-step job (e.g. data analysis over many files, a review pipeline, a parameterized batch). Authoring ends at a validated script file; running it is a…
aidlc-portfolio
Coordinate multiple AI-DLC workflows across repositories and Git worktrees using an evidence-backed portfolio catalog and deterministic workspace tooling. Use when initializing an AI-DLC portfolio workspace, discovering organization or business context, registering projects and dependencies, creating child intents and…
cao-plugin
Create a new CAO (CLI Agent Orchestrator) plugin. Use this skill whenever the user wants to add a plugin that reacts to CAO lifecycle or messaging events, scaffold a plugin package, understand plugin requirements, or integrate an external system (Discord, Slack, dashboards, logging, metrics) with CAO. Also use when…
cao-provider
Create a new CLI agent provider for CAO (CLI Agent Orchestrator). Use this skill whenever the user wants to add support for a new CLI-based AI agent (e.g., a new coding assistant CLI), integrate a new provider, or scaffold a provider implementation. Also use when the user asks about the provider architecture, what…
cao-session-management
Interact with CAO (CLI Agent Orchestrator) — launch multi-agent sessions, check status, send follow-up instructions, unblock stuck terminals, or shut down sessions. Use when working with CAO sessions in any capacity.
agui-author
Author live dashboard UI from an agent via the emitui MCP tool. Emit one of six allow-listed components (approvalcard, choiceprompt, diffsummary, progress, metric, agentcard) with JSON props and it renders in any AG-UI client watching the fleet. Use when you want the operator to see a decision, a diff, or a status…