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/processesgit 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 | $0.00382 |
| Opus 5 | $0.00000 | $0.00191 |
| Sonnet 5 | $0.00000 | $0.00076 |
| Haiku 4.5 | $0.00000 | $0.00038 |
Grade A, and why
processes 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
Process Analysis
Execute Netdata's processes function to analyze running processes on server-1:
-
Run the
processesfunction with:- Sort by Memory (descending)
- Limit to top 20 processes
- Include all columns for analysis
-
Analyze top memory consumers:
- Identify processes using >1 GB RAM
- Check for memory leaks (growing over time)
- Flag processes using swap
- Compare to expected baselines
-
Analyze top CPU consumers:
- Sort by CPU usage
- Identify runaway processes
- Check CPU context switches
- Compare user vs system time
-
Check file descriptor usage:
- Processes with high FD counts
- Approaching FD limits
- Socket vs file vs pipe breakdown
-
Review process hierarchy:
- Parent-child relationships (PPID)
- Process categories (from apps_groups.conf)
- Container process isolation
-
Identify concerning patterns:
- Zombie processes
- Processes in uninterruptible sleep (D state)
- High page fault rates
- Excessive I/O wait
-
MySQL process analysis (PID 1042433):
- Memory: RSS, Virtual, Swap
- CPU: User vs System time
- I/O: Read/write operations
- Threads: Count and state
- FDs: Open file descriptors
-
Known processes to check:
- mysqld (PID 1042433) - 6.4 GB RSS, 484 MB swap
- sshd - 79-96 threads (12.5% anomaly rate)
- containerd - CPU spikes (3.3% anomaly)
Provide recommendations for:
- Processes to investigate further
- Processes to restart
- Memory limit adjustments
- CPU affinity optimizations
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 · 55 lines · 0 tokens per session scan A 334346a8b4e3
processes 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 382 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.