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 skills add HigorAlves/orc --skill calloutsgit clone --depth 1 https://github.com/HigorAlves/orcWrote 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/higoralves/orc/callouts)<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>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 | $0.00058 | $0.01242 |
| Opus 5 | $0.00029 | $0.00621 |
| Sonnet 5 | $0.00012 | $0.00248 |
| Haiku 4.5 | $0.00006 | $0.00124 |
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.
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 |
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.
- 7d ago First seen · 103 lines · 58 tokens per session scan A 0be76ee57e81
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.
Other skills, from other repositories
taiyi-ui-design
A design-planning guide for describing how an application's user interface should look and behave. It produces a UI-DESIGN.md document covering layouts, components, interactions, accessibility, and error states.
flow-next-resolve-pr
Resolve PR review feedback. Fetches unresolved threads, triages, fixes, replies and resolves via GraphQL. Use when asked to address review comments.
flow-next-tracker-sync
Project a flow-next spec to a tracker issue (Linear, GitHub, GitLab, Jira) and reconcile two-way. Use when asked to sync to a tracker. NOT plan-sync.
taiyi-evolve
A workflow skill that compares the implemented code with the frozen design after development and testing. It records architecture changes and proposes updates to DESIGN.md, the document describing the intended system structure.
taiyi-diagram-c4
A code-scanning tool that builds C4 architecture documents from a repository. It separates facts observed in the code from conclusions inferred about the design and uses Mermaid diagrams as the source format.
flow-next-prime
Assess codebase agent and production readiness. Classifies the project, verifies commands run, leads with a verdict and ranked next actions.