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 latestaiagents/agent-skills --skill on-call-best-practicesgit clone --depth 1 https://github.com/latestaiagents/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/latestaiagents/agent-skills/on-call-best-practices)<a href="https://agentmods.dev/skills/latestaiagents/agent-skills/on-call-best-practices"><img src="https://agentmods.dev/badge/skills/latestaiagents/agent-skills/on-call-best-practices/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/latestaiagents/agent-skills/on-call-best-practices"><img src="https://agentmods.dev/badge/skills/latestaiagents/agent-skills/on-call-best-practices.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 | $0.00077 | $0.01626 |
| Opus 5 | $0.00039 | $0.00813 |
| Sonnet 5 | $0.00015 | $0.00325 |
| Haiku 4.5 | $0.00008 | $0.00163 |
Grade A, and why
on-call-best-practices 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 8d 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 — 281 lines — stays where its author put it; the contents beside it link to each section on GitHub.
On-Call Best Practices
Sustainable on-call that protects engineers and keeps systems reliable.
On-Call Philosophy
"On-call should be a learning opportunity, not a punishment."
Core Principles
- Fair distribution - Burden shared equally
- Sustainable pace - No burnout
- Clear expectations - Everyone knows their role
- Continuous improvement - Learn from every incident
Rotation Design
Recommended Structure
Primary On-Call (24/7):
- First responder for all pages
- 1 week shifts (max)
- Clear handoff process
Secondary On-Call (24/7):
- Backup if primary unavailable
- Can be shadow for training
- Steps in if primary overloaded
Business Hours Escalation:
- Subject matter experts
- Available for complex issues
- Not paged at night
Rotation Schedule Example
Week Mon Tue Wed Thu Fri Sat Sun
───────────────────────────────────────────────────────
Jan 6 Alice Alice Alice Alice Alice Alice Alice
Jan 13 Bob Bob Bob Bob Bob Bob Bob
Jan 20 Carol Carol Carol Carol Carol Carol Carol
Jan 27 Dave Dave Dave Dave Dave Dave Dave
Feb 3 Alice ...
Secondary follows same pattern, offset by 1 week
Scheduling Guidelines
| Guideline | Recommendation |
|---|---|
| Shift length | 1 week max, shorter if high volume |
| Gap between shifts | 2+ weeks minimum |
| Consecutive nights | Comp time if >2 pages |
| Holidays | Volunteer-based, compensated |
| Team size | 4+ people for sustainable rotation |
Response Expectations
Response Time SLAs
| Severity | Acknowledge | Respond | Escalate If |
|---|---|---|---|
| SEV1 | 5 min | Immediate | No ack in 5 min |
| SEV2 | 15 min | 30 min | No ack in 15 min |
| SEV3 | 1 hour | 4 hours | Business hours |
| SEV4 | Best effort | Next day | N/A |
What "On-Call" Means
During your shift:
✓ Phone charged and with you
✓ Laptop accessible within 15 min
✓ Reliable internet access
✓ Not impaired (alcohol, etc.)
✓ Able to focus if paged
You are NOT expected to:
✗ Be at your desk 24/7
✗ Respond instantly to Slack
✗ Fix everything yourself
✗ Work normal hours + on-call
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.
- 8d ago First seen · 281 lines · 77 tokens per session scan A 95904ee6a677
on-call-best-practices is a skill published in the GitHub repository latestaiagents/agent-skills (5 stars, last pushed 4mo ago), licensed MIT. It adds 77 tokens to every session and 1,626 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 2026-09-03.
Other skills, from other repositories
ai-crm-cleanup
A CRM data-cleanup assistant for reviewing whether customer and sales records are still usable.
ai-hr-performance-review
A performance-feedback writing assistant for producing and reviewing workplace performance comments.
ai-hr-pro
An HR document assistant for reviewing workplace materials and suggesting clearer wording, structure, and experiments.
ai-job-description-optimizer-cn
A business diagnosis assistant for human-resources teams, managers, operations staff, and software professionals. It uses supplied material to produce summaries, findings, action suggestions, and reusable deliverables.
ai-just-scrape
A business diagnosis assistant for marketing, operations, product, and sales questions. It uses supplied material to produce summaries, findings, action suggestions, and reusable deliverables.
ai-lark-approval
A business diagnosis assistant for operations, product, technical, and sales work. It uses supplied material to produce summaries, findings, action suggestions, and reusable deliverables.