Skip to content
Back to skills

Ox Cli Consult

ASecurity

Search SageOx team memory BEFORE answering from first-principles reasoning. Auto-fire when the user references recent or specific work or asks a before/after question: "I just pushed...", "did X fix Y?", "is the alert gone now?", "this request", or anything tied to a prior decision, a prod anomaly, or a metric/cost change. A confident answer that prior work contradicts is worse than a slow one — check first, then answer. Routes the cue to the right corpus: recency to `ox session list`, concep...

  • 62 stars
  • 0 votes
  • 0 copies
  • 2 views
  • Added September 21, 2026
ai-agentsgo

Works with

  • cli

Security analysis

A100/100

Scanned October 2, 2026

npx -y skills add sageox/ox --skill ox-cli-consult --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Ox Cli Consult?

Add the live security badge to your README. It updates with every re-scan.

Security grade badge for Ox Cli Consult
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/sageox-ox-cli-consult/badge)](https://www.skillsdirectory.com/skills/sageox-ox-cli-consult)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
SKILL.md
---
name: ox-cli-consult
description: >-
  Search SageOx team memory BEFORE answering from first-principles reasoning.
  Auto-fire when the user references recent or specific work or asks a
  before/after question: "I just pushed...", "did X fix Y?", "is the alert gone
  now?", "this request", or anything tied to a prior decision, a prod anomaly, or
  a metric/cost change. A confident answer that prior work contradicts is worse
  than a slow one — check first, then answer. Routes the cue to the right corpus:
  recency to `ox session list`, conceptual to `ox query`, who/when of a recorded
  conversation to `ox conversation search`, code-provenance to
  `ox code search`, decision-record work to `ox decision enrich`, a pasted
  sageox.ai recording link to `ox conversation show` (requires sign-in and
  membership in the repo's team).
---

<!-- Thin by design. The authoritative consult-first reflex — the cues, the
     "confident-wrong is worse than slow" reasoning, and the routing rationale —
     lives in the <consult-first> block of `ox agent prime` (Layer-1 floor), which
     reaches every primed AI coworker. This native skill adds discovery and
     activation ergonomics; it duplicates no reasoning. Every command it
     names is already reachable from the floor, so removing this skill loses
     ergonomics but never the floor. Do not grow this body. -->

## 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.

Attribution

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments

Loading comments…

Newsletter

Get the weekly list of safe new skills, and the ones we pulled.