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 conorbronsdon/agent-skills --skill guest-circuitgit clone --depth 1 https://github.com/conorbronsdon/agent-skillsWrote 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/conorbronsdon/agent-skills/guest-circuit)<a href="https://agentmods.dev/skills/conorbronsdon/agent-skills/guest-circuit"><img src="https://agentmods.dev/badge/skills/conorbronsdon/agent-skills/guest-circuit/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.
<a href="https://agentmods.dev/skills/conorbronsdon/agent-skills/guest-circuit"><img src="https://agentmods.dev/badge/skills/conorbronsdon/agent-skills/guest-circuit.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00089 | $0.02537 |
| Opus 5 | $0.00044 | $0.01269 |
| Sonnet 5 | $0.00018 | $0.00507 |
| Haiku 4.5 | $0.00009 | $0.00254 |
Grade A, and why
guest-circuit 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 10d 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 — 169 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Guest Circuit — Podcast-Appearance Research for Booking
Before you pitch a prospective guest, answer two questions. Where have they already podcasted? And what has nobody asked them yet?
The first gates the booking decision. Someone on ten shows this quarter is podcast-receptive and easy to book. Someone on zero shows may need a warmer path than a cold email. The second shapes the pitch. Inviting a guest to retell the story they told three shows ago wastes the slot and bores their audience overlap with yours.
This skill maps the circuit and produces a report you can act on: appearance timeline, the "stump speech" they repeat everywhere, the angles no show has claimed, and a one-paragraph pitch built on the gap.
Invocation: deliberately model-invocable — "research X before outreach" is the trigger. It spends web-search calls, so invoke consciously on big sweeps.
When to Use
- "Map [person]'s podcast circuit" / "where has [person] podcasted?"
- "Research [person] before I send guest outreach"
- "Find an unclaimed angle for [person]"
- Before pitching a prospective guest, to gate the booking decision and shape the pitch
(See "When NOT to Use" below for the cases this skill is wrong for.)
Step 1: Disambiguate
Input: $ARGUMENTS (guest name, plus an anchor fact if given).
Names collide. Before any search, confirm one anchor fact: company, role, or a known piece of work (book, project, paper).
- If the user provided an anchor ("Jane Doe, CTO at Acme"), proceed.
- If the user gave only a name, ask. Do not guess and do not search yet. A sweep on the wrong Jane Doe produces a confident, useless report.
Use the anchor to filter every result in later steps. A hit that cannot be tied to the anchor goes in "could not verify."
Step 2: Appearance Sweep
Three source modalities. Run them as parallel subagents in a single tool-call batch (prompt templates in patterns/subagent-prompts.md). If subagents are unavailable, run the modalities sequentially in the same order. If web access is unavailable entirely, stop and say the sweep cannot run — never populate the timeline from model memory.
What ships with it
4 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 10d ago First seen · 169 lines · 0 tokens per session scan A a4f41085ea1d
guest-circuit is a skill published in the GitHub repository conorbronsdon/agent-skills (10 stars, last pushed 1mo ago), licensed MIT. It adds 89 tokens to every session and 2,537 once invoked, about $0.0004 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
mulmoterminal-dirs
Colour-code and order the directories you actually work in, from wherever you are. Writes each project's /.mulmoterminal.json — name badge, project icon image, the seven chrome colours, xterm palette (theme / colors), terminal font size, orderPriority (where it sits in the grid and in the launcher's chips), and…
mulmoterminal-keys
Bind keyboard shortcuts and fix keyboard/clipboard behaviour in MulmoTerminal. Writes keymap, which Settings cannot set at all — its Keyboard shortcuts section is read-only, listing every action bound or not plus a send row. Explains copyOnSelect, questionPaneEnabled and terminalSubmit, which have their own Settings…
tokf-discover
Find missed token savings by scanning AI coding session files for commands that ran without tokf filtering.
dashiai-ppt
A presentation-making add-on that creates an HTML slide deck from preset visual page designs. The result can open offline in a browser and can be exported as a PowerPoint or PDF file.
skillnote
Self-hosted skill registry for OpenClaw. Stores procedures your team writes (name, description, body), syncs them to disk before each task, and collects which-helped/which-failed signals from the agent so the registry improves over time.
xiaohongshu-image-creator
An image-making assistant for Xiaohongshu, a Chinese social platform for lifestyle, product, and educational posts. It creates vertical covers and supporting images matched to the post’s topic, audience, and visual style.