agent-toolkit: Skill for Claude Code

.agents/skills/ox-consult/SKILL.md

ox-consult is a skill for Claude Code, Codex from sageox/agent-toolkit. It costs 139 tokens per session (429 once invoked), scanned A, a copy of ox-cli-consult, Apache-2.0.

A team-memory lookup step that searches earlier project context before answering questions about recent work, decisions, incidents, or changes. It chooses how to search based on the kind of question.

In plain words
What is it for?
Use it before answering questions about recent code changes, production problems, alerts, costs, metrics, or earlier decisions.
Why use it?
It reduces answers based only on general reasoning when the relevant facts are in the team's past work.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: installed under .agents/ (shared by several agents).

This is sageox/agent-toolkit's own configuration. It tells Claude Code and Codex how to work on agent-toolkit itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything agent-toolkit configures →

Reuse

Borrowing it

Nothing to install: this file belongs to sageox/agent-toolkit. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/sageox/agent-toolkit/main/.agents/skills/ox-consult/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/sageox/agent-toolkit

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for ox-consult

README.md
[![agentmods](https://agentmods.dev/badge/skills/sageox/agent-toolkit/ox-consult/github.svg)](https://agentmods.dev/skills/sageox/agent-toolkit/ox-consult)
Your own site
<a href="https://agentmods.dev/skills/sageox/agent-toolkit/ox-consult"><img src="https://agentmods.dev/badge/skills/sageox/agent-toolkit/ox-consult/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for ox-consult

Your own site · 80×15
<a href="https://agentmods.dev/skills/sageox/agent-toolkit/ox-consult"><img src="https://agentmods.dev/badge/skills/sageox/agent-toolkit/ox-consult.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 139 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 429 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin 88% copy Near-identical to another mod in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00139 $0.00429
Opus 5 $0.00069 $0.00215
Sonnet 5 $0.00028 $0.00086
Haiku 4.5 $0.00014 $0.00043

Measured yesterday against content hash 4f281f6f07cb, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

ox-consult 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 yesterday.

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.

Origin

This is a copy

88% identical to ox-cli-consult — 2 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

.agents/skills/ox-consult/SKILL.md · 35 lines

What it actually says

Use when

The user's message carries a consult cue — STOP and search before reasoning:

  • References recent or specific work: "I just pushed...", "this request", "did X fix Y?", "is the alert gone now?"
  • Touches a prior decision, a prod anomaly, or a metric/cost change — anything with a before/after.

Route the cue

The authoritative cue→corpus routing (recency vs conceptual vs code-provenance, with the exact commands) lives in the <consult-first> block of your ox agent prime output — follow it from there rather than from this file. If it is not in context (session not primed), run ox agent prime first, then route.

Changes

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.

  1. yesterday First seen · 35 lines · 139 tokens per session scan A 4f281f6f07cb

Subscribe to this mod's changes

ox-consult is a skill published in the GitHub repository sageox/agent-toolkit (10 stars, last pushed today), licensed Apache-2.0. It adds 139 tokens to every session and 429 once invoked, about $0.0007 per session on Opus 5. A static security scan graded it A with 0 findings. It is 88% identical to ox-cli-consult, differing in 2 lines, and is treated as a copy.