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-do-not-disturbgit 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-do-not-disturb)<a href="https://agentmods.dev/skills/trysidequest-ai/sidequest/sq-do-not-disturb"><img src="https://agentmods.dev/badge/skills/trysidequest-ai/sidequest/sq-do-not-disturb/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-do-not-disturb"><img src="https://agentmods.dev/badge/skills/trysidequest-ai/sidequest/sq-do-not-disturb.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 | $0.00094 | $0.00652 |
| Opus 5.5 | $0.00038 | $0.00261 |
| Sonnet 5.5 | $0.00019 | $0.00130 |
| Haiku 4.5 | $0.00009 | $0.00065 |
Grade A, and why
sq-do-not-disturb 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 2mo 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 — 83 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/sidequest:sq-do-not-disturb
Pause quests for 2 hours, or cancel an active timer.
Steps
- Read the current config:
cat ~/.sidequest/config.json
-
Check the current value of
do_not_disturbin the config. -
Decide action:
- If
do_not_disturbis set and the timestamp is in the future → the user wants to cancel. Remove the field. - Otherwise → the user wants to activate. Set
do_not_disturbto current time + 7200 (2 hours).
- If
-
To activate, update the config using Python:
python3 -c "
import json, os, time, tempfile
config_path = os.path.expanduser('~/.sidequest/config.json')
with open(config_path) as f:
config = json.load(f)
config['do_not_disturb'] = int(time.time()) + 7200
fd, tmp = tempfile.mkstemp(dir=os.path.dirname(config_path))
with os.fdopen(fd, 'w') as f:
json.dump(config, f, indent=2)
os.rename(tmp, config_path)
"
- To cancel, update the config using Python:
python3 -c "
import json, os, tempfile
config_path = os.path.expanduser('~/.sidequest/config.json')
with open(config_path) as f:
config = json.load(f)
config.pop('do_not_disturb', None)
fd, tmp = tempfile.mkstemp(dir=os.path.dirname(config_path))
with os.fdopen(fd, 'w') as f:
json.dump(config, f, indent=2)
os.rename(tmp, config_path)
"
- Display confirmation:
If activated:
Do Not Disturb: ON
==================
Quests paused for 2 hours.
Resumes at: {human_readable_time}
Run /sidequest:sq-do-not-disturb again to cancel early.
If cancelled:
Do Not Disturb: OFF
===================
Quests will resume normally.
Error Handling
- If
~/.sidequest/config.jsondoesn't exist, tell the user: "SideQuest not configured. Run /sidequest:sq-login first." - If JSON parsing fails, tell the user: "Config file is corrupted. Run /sidequest:sq-login to reset."
Implementation Note
The stop-hook checks do_not_disturb automatically. It stores a Unix timestamp — quests are suppressed while current time < timestamp. Once the timer expires, quests resume without any action needed.
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.
- 2mo ago First seen · 83 lines · 94 tokens per session scan A 70ff9a1e8e91
sq-do-not-disturb is a skill published in the GitHub repository trySideQuest-ai/sidequest (8 stars, last pushed 6mo ago), licensed MIT. It adds 94 tokens to every session and 652 once invoked, about $0.0004 per session on Opus 5.5. 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.
sq-do-not-disturb compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| sq-do-not-disturbtrySideQuest-ai/sidequest | Skill | 8 | 6mo ago | MIT | A | 94 | Claude Code |
| cctop-setupst0012/cctop | Skill | 161 | 1mo ago | MIT | A | 31 | Claude Code |
| dropoveralivirgo/Major-AI-Skills | Skill | 2 | today | MIT | A | 23 | Claude Code |
| batch-apiQwenLM/qwen-code | Skill | 29k | today | Apache-2.0 | A | 51 | Claude Code |
| todosJetBrains/thinkrail | Skill | 8.0k | today | Apache-2.0 | A | 58 | Claude Code, Codex |
| gmailvellum-ai/vellum-assistant | Skill | 1.5k | yesterday | MIT | A | 20 | Claude Code, Codex |
| gmail-triggervellum-ai/vellum-assistant | Skill | 1.5k | yesterday | MIT | A | 37 | Claude Code, Codex |