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/loadgit 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 | $0.00446 |
| Opus 5 | $0.00000 | $0.00223 |
| Sonnet 5 | $0.00000 | $0.00089 |
| Haiku 4.5 | $0.00000 | $0.00045 |
Grade A, and why
load 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
System Load Analysis
Analyze system load and identify whether the system is overloaded:
-
Query system.load metrics:
- 1-minute load average (recent state)
- 5-minute load average (short-term trend)
- 15-minute load average (long-term trend)
- Historical data for last 24 hours
-
Calculate load per core:
- System has 16 cores (from CLAUDE.md)
- Load/Core ratio (should be <1.0 for healthy)
- Identify if system is CPU-bound
-
Correlate load with other metrics:
- CPU utilization (system.cpu)
- I/O wait time
- Process count (system.processes)
- Context switches (system.ctxt)
-
Analyze load patterns:
- Peak load times
- Load spikes and their causes
- Correlation with known events (e.g., 21:01 UTC spike to 2.43)
- Baseline vs current load
-
Check active processes:
- Count of processes in run queue
- system.active_processes metric
- Processes in uninterruptible sleep (D state)
-
Review CPU pressure:
- system.cpu_some_pressure
- system.cpu_full_pressure
- Scheduler latency metrics
-
Known baseline (from CLAUDE.md):
- Current: 1.16 / 1.18 / 1.21
- This is healthy for 16 cores (~7% utilization)
- Peaks observed: 2.62 at 21:01 UTC
Provide analysis:
- Overall load health (healthy/moderate/high/critical)
- Load per core percentage
- Whether CPU is a bottleneck
- Comparison to memory/swap as bottleneck
- Load forecast for next few hours
- Recommended actions if overloaded
Interpretation guide:
- Load < cores: System healthy
- Load = cores: System at capacity
- Load > cores: System overloaded
- Load >> cores: System severely overloaded
For this system: Load of 1.2 on 16 cores = 7.5% utilization (HEALTHY)
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 · 58 lines · 0 tokens per session scan A 3ce19a8db8de
load 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 446 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.