callouts

callouts is a skill for Claude Code from HigorAlves/orc. It costs 58 tokens per session (1,242 once invoked), scanned A, original, MIT.

A writing guide for adding short callout blocks to conversations, pull requests, issues, and documentation. Callouts highlight insights, cautions, previews, or risks.

In plain words
What is it for?
Use it when explaining a non-obvious code choice or adding an informational, cautionary, preview, or danger note to GitHub-related content.
Why use it?
It keeps important warnings and explanations visually consistent and suited to where the text will be read.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: names the AskUserQuestion tool; mentions Claude Code.

Part of the orc plugin — 80 skills, 30 commands, 14 agents, 5 hooks shipped together

Good fit Use it when explaining a non-obvious code choice or adding an informational, cautionary, preview, or danger note to GitHub-related content.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/higoralves/orc/callouts
Install

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.

Any agent
npx skills add HigorAlves/orc --skill callouts
Clone the repo
git clone --depth 1 https://github.com/HigorAlves/orc

Made for: Claude Code.

Or install orc, the plugin that ships this one along with the rest of its 80 skills, 30 commands, 14 agents, 5 hooks.

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 callouts

README.md
[![agentmods](https://agentmods.dev/badge/skills/higoralves/orc/callouts.svg)](https://agentmods.dev/skills/higoralves/orc/callouts)
Your own site
<a href="https://agentmods.dev/skills/higoralves/orc/callouts"><img src="https://agentmods.dev/badge/skills/higoralves/orc/callouts.svg" alt="Measured on agentmods" height="20"></a>
Per session 58 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,242 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 original No closer match found 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 $0.00058 $0.01242
Opus 5 $0.00029 $0.00621
Sonnet 5 $0.00012 $0.00248
Haiku 4.5 $0.00006 $0.00124

Measured 7d ago against content hash 0be76ee57e81, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

callouts 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 7d 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.

orc/skills/callouts/SKILL.md · 103 lines

How it starts

The opening of the file, as written. The whole thing — 103 lines — stays where its author put it; the contents beside it link to each section on GitHub.

insights

When writing or modifying code, surface brief educational notes about non-obvious choices — in the surrounding codebase or in the change itself. This skill is also the canonical home of the orc callout palette: every must-not-miss block an orc command emits (gates, previews, destructive confirms) uses one of the shapes below.

The destination rule (which form to emit)

The palette has two forms; pick by where the text will be read:

  • Terminal form (default — anything printed into the conversation): blockquote + emoji bold header, no [!TYPE] tag. The Claude Code TUI doesn't parse GitHub alert types — a tag line just prints as literal junk text. The emoji carries the color cue.
  • GitHub form (GitHub-bound output only — PR bodies, issue/review comments, committed doc files): the same block with a > [!TYPE] first line. GitHub and editors like VS Code render it as a colored admonition.

If unsure, ask "will this land in a file or on GitHub?" — no → terminal form.

Flip condition: when a Claude Code release themes GitHub alert types natively in the terminal, converge both forms on the GitHub one (and drop this rule) — every other file copies these templates mechanically.

The palette

One shape for every conversation block:

> **<emoji> <Title>**
>
> <1–3 short lines or bullets>
Purpose Header GitHub-form tag Use for
Insight **💡 Insight** [!IMPORTANT] non-obvious choice, trade-off, thing worth knowing
Caution **⚠️ Caution** (variants **⚠️ Caution — <what>**, **⚠️ Skipped — <reason>**) [!WARNING] gotchas, footguns, skip-with-warning, non-blocking anomalies
Danger **🛑 <what>** [!CAUTION] destructive previews, discard confirms, escalations, blocked states
Gate **⛔ Gate — <name>** [!NOTE] ([!WARNING] when fired by a problem) 1–3 context lines immediately before an AskUserQuestion
Preview **📋 Preview — <action>** [!NOTE] headline over an about-to-act payload
Hint **➡️ Next** [!TIP] final handoff line only; sparingly

Read the full file on GitHub · 103 lines

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. 7d ago First seen · 103 lines · 58 tokens per session scan A 0be76ee57e81

Subscribe to this mod's changes

callouts is a skill published in the GitHub repository HigorAlves/orc (6 stars, last pushed 11d ago), licensed MIT. It adds 58 tokens to every session and 1,242 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.