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 josefbacik/systing --skill systing-analyzegit clone --depth 1 https://github.com/josefbacik/systingWrote 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/josefbacik/systing/systing-analyze)<a href="https://agentmods.dev/skills/josefbacik/systing/systing-analyze"><img src="https://agentmods.dev/badge/skills/josefbacik/systing/systing-analyze/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/josefbacik/systing/systing-analyze"><img src="https://agentmods.dev/badge/skills/josefbacik/systing/systing-analyze.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00100 | $0.06831 |
| Opus 5.5 | $0.00040 | $0.02732 |
| Sonnet 5.5 | $0.00020 | $0.01366 |
| Haiku 4.5 | $0.00010 | $0.00683 |
Grade A, and why
systing-analyze 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 9d 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 — 300 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Analyzing systing traces
Systing stores traces in DuckDB. The systing-analyze MCP server exposes structured tools to query them. This skill tells you which tool to reach for and how the data is laid out.
Recommended workflow
trace_info— Always start here. Pass thepathto the.duckdbfile. Returns trace IDs, time range, per-trace system/platform info (kernel, arch, hypervisor, cpufreq driver, sampling event/period), non-empty tables with row counts, and the top 25 processes by thread count. This also caches the DB so later calls can omitpath.list_tables/describe_table— Discover schema for ad-hoc queries.- High-level tools for common questions — see below.
query— For anything the high-level tools don't cover, write SQL. Results cap at 10k rows (truncated: truewhen hit); useLIMIT/OFFSETfor more. The DB is opened read-only.
Tool cheatsheet
| Question | Tool | Notes |
|---|---|---|
| What's in this trace? | trace_info |
First call; pass path |
| Where is CPU time going? | flamegraph |
stack_type="cpu" (default); optionally pid/tid |
| Why is the process blocked / off-CPU? | flamegraph |
stack_type="uninterruptible-sleep" (D) or "interruptible-sleep" (S), or "all-sleep" |
| Is the scheduler oversubscribed? Latency? | sched_stats |
no filter = whole-trace ranking; pid = per-thread breakdown; tid = single thread with end-state distribution |
| Which CPUs are busy / idle? | cpu_stats |
per-CPU utilization, idle%, IRQ/softIRQ time, runqueue depth p50/p90/p99 |
| How does the scheduler behave overall? Compare two schedulers/hosts? | sched_aggregate |
one summary per capture: wakeup latency (ran on previous CPU / migrated), preempt wait, slice length, switch + migration rates, migrate-event counts, time-weighted runqueue length, per-CPU load vectors (incl. placement) + imbalance metrics, log2 histograms, tail threads; percentiles within ~6%; per-CPU runqueue exact on traces with sched_migrate (meta.placement_exact), approximate before |
| What's the network doing? | network_connections |
per-connection bytes, retransmit % |
| Interface-level network? | network_interfaces |
per-interface, per-protocol breakdown |
| Both sides of a connection (multi-node)? | network_socket_pairs |
matched socket pairs, within or across traces |
| Memory / allocations? | query |
no dedicated tool — see memory schema below |
| What ran on the TPU? Duty cycle? HBM? | query |
no dedicated tool — see TPU schema below |
| Anything else | query |
raw SQL; see schema below |
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.
- 9d ago Changed · +11 lines c33b5c71eef7
- 11d ago Changed · +21 lines 30f4dcfd6b2b
- 25d ago Changed 3214603a3250
- 1mo ago Changed 035b7432f7cb
- 1mo ago Changed · +23 lines 6bf7e08b9081
- 1mo ago Changed · +2 lines 717469d95220
- 1mo ago Changed c47ec6072095
- 1mo ago Changed · +22 lines 61b003545ed4
- 1mo ago Changed d51f02adc658
- 1mo ago First seen · 221 lines · 100 tokens per session scan A 4f8a470d1d98
systing-analyze is a skill published in the GitHub repository josefbacik/systing (181 stars, last pushed 2d ago), licensed MIT. It adds 100 tokens to every session and 6,831 once invoked, about $0.0004 per session on Opus 5.5. 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
debug-optimize-lcp
Guides debugging and optimizing Largest Contentful Paint (LCP) using Chrome DevTools MCP tools. Use this skill whenever the user asks about LCP performance, slow page loads, Core Web Vitals optimization, or wants to understand why their page's main content takes too long to appear. Also use when the user mentions…
systematic-debugging
Use when debugging a failing test, build error, or runtime issue that isn't immediately obvious. Guides a 4-phase root cause analysis instead of random fix attempts.
log-error-digest
Analyze log files to troubleshoot errors, identify peak error periods, and produce error clustering, frequency statistics, and time distribution reports. Supports JSON, syslog, and Nginx formats with automatic detection. Use when a user uploads a .log file and asks to analyze errors, find patterns, debug issues, or…
deck-retro
Run a fully local agent-deck retrospective over the user's own transcripts, Recall index and logs. Use when a user wants to find recurring failures or take their own finding from investigation through synthetic reproduction, a user-filed issue, a test-first fix and contributor PR handoff. Also use for weekly usage…
cwv-optimizer
Diagnose and fix Core Web Vitals issues on AEM Edge Delivery Services pages. Goes deeper than generic CWV advice by understanding EDS-specific performance patterns including the 100KB LCP budget, E-L-D loading phases, block rendering behavior, and third-party script impact. Produces specific fixes for LCP, CLS, and…
incident-response-incident-response
Coordinate production incident triage, mitigation, investigation, recovery, and follow-up. Use when responding to outages or other incidents that require structured operational coordination.