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 serac-labs/serac --skill oncall-schedulinggit clone --depth 1 https://github.com/serac-labs/seracWrote 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/serac-labs/serac/oncall-scheduling)<a href="https://agentmods.dev/skills/serac-labs/serac/oncall-scheduling"><img src="https://agentmods.dev/badge/skills/serac-labs/serac/oncall-scheduling.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00065 | $0.01636 |
| Opus 5 | $0.00032 | $0.00818 |
| Sonnet 5 | $0.00013 | $0.00327 |
| Haiku 4.5 | $0.00006 | $0.00164 |
Grade A, and why
oncall-scheduling 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 — 139 lines — stays where its author put it; the contents beside it link to each section on GitHub.
On-Call Scheduling
"Who is on call for the database team?" is one question and four tables. Answering it by guessing at
table names is how agents end up querying sys_user_group.manager and reporting the wrong person.
The chain
sys_user_group the team being covered
└── cmn_rota a rotation on that group ("Database — primary")
├── cmn_schedule the hours the rotation covers, and its TIME ZONE
└── cmn_rota_roster a rotation pattern: weekly, 7 days, starting <date>
└── cmn_rota_member one person, with a from/to window
└── sys_user
Read it as: a group has rotations, a rotation has rosters, a roster has members. The roster is the
pattern (rotate weekly, one week each). The member row is one person's turn — it carries from and
to as glide_date, and member referencing sys_user.
A group can have several rotations at once — primary, secondary, escalation — and they are unrelated records. "The on-call person" is never a property of the group.
Who is on call right now
snow_oncall_manage({ action: "get_current_oncall", rotation_sys_id }) resolves it in three steps, and
knowing them tells you what a wrong answer means:
- Read
cmn_rota_rosterwhererota=<rotation>^active=true. - Find the
cmn_rota_memberrows belonging to those rosters whosefrom/towindow covers today. - Resolve
memberto asys_user.
Two consequences worth having in front of you:
- A rotation with no member window covering today returns nothing. That is not an error; it is a rotation whose roster has run past its generated windows. The tool says so explicitly rather than guessing at the next person.
- The dates are dates, and coverage is hours.
cmn_rota_member.from/.toare days. Whether the person is on call at 03:00 is decided by the rotation'scmn_schedule— including its time zone, which is a field on the schedule and not on the rotation. A rotation whose schedule is inUS/Pacifichands over at a different UTC moment than the same rotation inEurope/Amsterdam. Never convert on-call times yourself without readingcmn_schedule.time_zonefirst.
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 · 139 lines · 65 tokens per session scan A 34a8951fcdc0
oncall-scheduling is a skill published in the GitHub repository serac-labs/serac (78 stars, last pushed 13d ago), licensed Apache-2.0. It adds 65 tokens to every session and 1,636 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 2026-08-30.
Other skills, from other repositories
mcp-tool-developer
Build Model Context Protocol (MCP) servers and tools from scratch. Full-stack MCP development with TypeScript/Python, testing, deployment, and registry publishing.
agent-carnet
Use this skill when the user asks to save, recall, find, or organize notes. Triggers on: 'remember this', 'save this', 'note this', 'what did we discuss about...', 'check the notebook', 'find in carnet'. Also use proactively when discovering findings worth preserving across sessions.
security-audit
Audit a codebase or directory for security issues (hardcoded secrets, injection, unsafe deserialization, weak crypto, authz gaps) and produce a structured findings report. Use when the user asks for a security review, an audit, or to check code for vulnerabilities. Report only — never fix.
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.
tmux-lane-orchestrator
Manage one tmux agent lane from its matching ops pane, inspect live pane state and Codex logs on cold start, and produce concise manager summaries for OpenClaw and adjacent project work.