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 trySideQuest-ai/sidequest --skill sq-updategit clone --depth 1 https://github.com/trySideQuest-ai/sidequestWrote 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/trysidequest-ai/sidequest/sq-update)<a href="https://agentmods.dev/skills/trysidequest-ai/sidequest/sq-update"><img src="https://agentmods.dev/badge/skills/trysidequest-ai/sidequest/sq-update/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/trysidequest-ai/sidequest/sq-update"><img src="https://agentmods.dev/badge/skills/trysidequest-ai/sidequest/sq-update.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 | $0.00066 | $0.00438 |
| Opus 5.5 | $0.00026 | $0.00175 |
| Sonnet 5.5 | $0.00013 | $0.00088 |
| Haiku 4.5 | $0.00007 | $0.00044 |
Grade C, and why
sq-update scanned grade C with 2 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 1mo 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.
Downloads and executes remote codehighSupply chain
curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.
Runs `curl -fsSL https://get.trysidequest.ai/install.sh | bash` which: Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
Runs `curl -fsSL https://get.trysidequest.ai/install.sh | bash` which: What it actually says
/sidequest:sq-update
Updates SideQuest (plugin + native app) to the latest version by re-running the hosted installer.
What It Does
Runs curl -fsSL https://get.trysidequest.ai/install.sh | bash which:
- Downloads the latest native app DMG, mounts it, copies to
~/Applications/ - Downloads the latest plugin tarball, extracts to Claude plugins cache, registers in Claude config
- Preserves your existing
~/.sidequest/config.json(auth token, preferences) - Verifies installation end-to-end
Steps
1. Confirm with user
Before running, confirm intent:
"This will download and install the latest SideQuest (plugin + native app). Your login and settings will be preserved. Proceed? (yes/no)"
If user says yes, proceed. Otherwise stop.
2. Run installer
curl -fsSL https://get.trysidequest.ai/install.sh | bash
Capture exit status. Installer prints its own progress.
3. Report outcome
If exit status 0:
"✓ Update complete. Run
/sidequest:sq-statusto verify everything is working."
If non-zero:
"Update failed (exit code {N}). Run
/sidequest:sq-statusto see which component failed. You can try again by running/sidequest:sq-update."
Error Handling
- If user declines, stop immediately — do not run installer
- If installer fails mid-run, do not attempt partial recovery — let user re-run after diagnosis
- If network unavailable, installer will fail fast with curl exit code
- Never modify
~/.sidequest/config.jsonmanually — the installer preserves it by design
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.
- 1mo ago First seen · 53 lines · 66 tokens per session scan C e12579ed69c0
sq-update is a skill published in the GitHub repository trySideQuest-ai/sidequest (8 stars, last pushed 5mo ago), licensed MIT. It adds 66 tokens to every session and 438 once invoked, about $0.0003 per session on Opus 5.5. A static security scan graded it C with 2 findings (downloads and executes remote code, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
cctop-setup
Use when cctop-hook command fails or is not found. Guides user to install the cctop menubar app.
dropover
Configure Dropover file-shelf workflows and URL integrations, and diagnose macOS gesture or window behavior.
appcleaner
Inspect macOS application bundles and related files for AppCleaner workflows, review removal candidates, and troubleshoot SmartDelete behavior.
refocusing
Use when a long-running agent may have lost the product outcome, when context was compacted, when work has crossed a major boundary, or when a fresh path-based trace is needed before the next consequential action. Not for fresh-session orientation, waking an idle seat, or checkpoints.
telegram-setup
Connect a Telegram bot to the Vellum Assistant gateway with automated webhook registration and credential storage.
rulesync
Generates and syncs AI rule configuration files (.cursorrules, CLAUDE.md, copilot-instructions.md) across 20+ coding tools from a single source. Use when syncing AI rules, running rulesync commands, importing or generating rule files, or managing shared AI coding configurations.