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 agentmods add skills/saolalab/clawforce/monitoringnpx skills add saolalab/clawforce --skill monitoringgit clone --depth 1 https://github.com/saolalab/clawforceWhat 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 | $0.00038 | $0.01266 |
| Opus 5 | $0.00019 | $0.00633 |
| Sonnet 5 | $0.00008 | $0.00253 |
| Haiku 4.5 | $0.00004 | $0.00127 |
Grade A, and why
monitoring 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 2d 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 — 172 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Monitoring & Observability
Framework for defining service level indicators, objectives, and error budgets.
SLI/SLO Definitions
Service Level Indicator (SLI)
A quantitative measure of service quality from the user's perspective.
Common SLIs:
- Availability:
(successful_requests / total_requests) * 100 - Latency: P50, P95, P99 percentiles
- Error Rate:
(error_requests / total_requests) * 100 - Throughput: Requests per second
- Freshness: Time since last successful data update
Service Level Objective (SLO)
A target value for an SLI over a time window.
Example:
- SLI: Availability
- SLO: 99.9% over 30 days
- Window: Rolling 30-day window
Service Level Agreement (SLA)
A business commitment with consequences if SLO is violated (usually customer-facing).
Error Budget Policy
Error budget = 100% - SLO target
Example:
- SLO: 99.9% availability
- Error budget: 0.1% downtime = 43.2 minutes/month
Error Budget States
| State | Budget Remaining | Action |
|---|---|---|
| Green | > 50% | Normal feature velocity |
| Yellow | 25-50% | Reduce feature velocity, focus on reliability |
| Red | < 25% | Feature freeze, reliability work only |
| Exhausted | 0% | Emergency reliability sprint |
Burn Rate
Rate at which error budget is consumed.
- Fast burn: > 14x normal rate → Alert immediately
- Slow burn: 2-14x normal rate → Alert within 6 hours
- Normal burn: < 2x normal rate → Monitor
Alert Design Principles
Good Alerts
✅ Actionable — Clear action to take when alert fires ✅ Specific — Precise condition, not vague "high CPU" ✅ Not noisy — Only alert on real issues, not transient spikes ✅ Documented — Runbook exists for every alert ✅ Tested — Alert has been tested and works
Bad Alerts
❌ Noisy — Fires frequently without real issues ❌ Vague — "Something is wrong" without specifics ❌ Non-actionable — No clear remediation steps ❌ Undocumented — No runbook or context ❌ Untested — Never verified to work
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.
- 2d ago First seen · 172 lines · 38 tokens per session scan A 079023e9d3db
monitoring is a skill published in the GitHub repository saolalab/clawforce (38 stars, last pushed 4mo ago), licensed Apache-2.0. It adds 38 tokens to every session and 1,266 once invoked, about $0.0002 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
agenticmail
🎀 AgenticMail — Full email, SMS, storage & multi-agent coordination for AI agents. 63 tools.
ai-meeting-scheduling
Booking links fail for groups. SkipUp schedules meetings with 2-50 participants via email — one API call coordinates across timezones automatically. Also: check status, pause, resume, or cancel requests. Async only — does not instant-book, access calendars, or do free/busy lookups.
agentic-paper-digest-skill
Fetches and summarizes recent arXiv and Hugging Face papers with Agentic Paper Digest. Use when the user wants a paper digest, a JSON feed of recent papers, or to run the arXiv/HF pipeline.
eachlabs-voice-audio
Text-to-speech, speech-to-text, voice conversion, and audio processing using EachLabs AI models. Supports ElevenLabs TTS, Whisper transcription with diarization, and RVC voice conversion. Use when the user needs TTS, transcription, or voice conversion.
arxiv-summarizer-orchestrator
End-to-end orchestration skill for periodic arXiv collection and reporting using three sub-skills: arxiv-search-collector, arxiv-paper-processor, and arxiv-batch-reporter. Supports manual language control across all markdown outputs and Stage-B processing strategy (subagentparallel default max 5, or serial).
academic-literature-search
这是一个专注于学术文献检索的专业工具，集成了多个权威学术数据库，提供全面、快速、准确的文献检索服务。支持多数据库并发检索、高级过滤、智能排序和多种输出格式。.