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 commands/danielbodnar/skills/cpugit clone --depth 1 https://github.com/danielbodnar/skillsWhat 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 | $0.00000 | $0.00404 |
| Opus 5 | $0.00000 | $0.00202 |
| Sonnet 5 | $0.00000 | $0.00081 |
| Haiku 4.5 | $0.00000 | $0.00040 |
Grade A, and why
cpu 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 yesterday.
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.
What it actually says
CPU Analysis
Analyze CPU performance and identify bottlenecks on server-1:
-
Query system.cpu metrics:
- User CPU time
- System CPU time
- I/O wait time
- Steal time (should be 0 on bare metal)
- Idle time
- Show trends over last 3 hours
-
Check per-core CPU usage if available:
- Identify if load is balanced
- Find cores at 100% utilization
- Check for CPU affinity issues
-
Analyze system load:
- system.load (1/5/15 minute averages)
- Compare to core count (16 cores)
- Identify if system is overloaded
- Check load trends
-
Review CPU-intensive processes:
- Query app.cpu_utilization metrics
- Identify top CPU consumers
- Check for runaway processes
-
Container CPU usage:
- CPU usage per container (from cgroups)
- Identify containers consuming >100% (multi-core)
- Check for CPU throttling
- CPU pressure metrics
-
Analyze context switches and interrupts:
- system.ctxt (context switches)
- system.intr (interrupts)
- system.softirqs (software interrupts)
- High rates may indicate thrashing
-
Known high CPU consumers (from CLAUDE.md):
- maybach: 120.77% (normal for this service?)
- systemavo-db-1: 78.89% (MySQL under load)
- systemavo-systemavo-1: 4.05% (PHP app)
Provide analysis:
- Overall CPU health (healthy/loaded/critical)
- Bottleneck identification
- Optimization recommendations
- Whether CPU is a limiting factor
- Process priority adjustments needed
Note: Current average is 7.18%, so CPU is NOT the bottleneck. Focus on identifying why certain containers have high usage and if it's expected.
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.
- yesterday First seen · 54 lines · 0 tokens per session scan A 213f378b613c
cpu is a command published in the GitHub repository danielbodnar/skills (2 stars, last pushed 23d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 404 tokens. 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.
Other commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.