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 LeoLin990405/r-analytics-skill --skill lobstrgit clone --depth 1 https://github.com/LeoLin990405/r-analytics-skillWrote 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/leolin990405/r-analytics-skill/lobstr)<a href="https://agentmods.dev/skills/leolin990405/r-analytics-skill/lobstr"><img src="https://agentmods.dev/badge/skills/leolin990405/r-analytics-skill/lobstr.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00021 | $0.00487 |
| Opus 5 | $0.00010 | $0.00244 |
| Sonnet 5 | $0.00004 | $0.00097 |
| Haiku 4.5 | $0.00002 | $0.00049 |
Grade A, and why
lobstr 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 4d 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.
What it actually says
lobstr
Visualize R data structures.
Object Size
library(lobstr)
# Object size
obj_size(x)
# Multiple objects
obj_size(x, y)
# Shared memory
obj_size(x, y) # May be less than obj_size(x) + obj_size(y)
Object Address
# Memory address
obj_addr(x)
# Check if same object
obj_addr(x) == obj_addr(y)
Reference Counting
# Reference count
ref(x)
# Track references
x <- 1:10
y <- x
ref(x) # Shows 2 references
AST (Abstract Syntax Tree)
# View expression tree
ast(f(x, y))
# Complex expression
ast(
if (x > 0) {
sqrt(x)
} else {
-sqrt(-x)
}
)
Object Tree
# View object structure
sxp(x)
# List structure
sxp(list(a = 1, b = 2))
Memory Tracking
# Track memory changes
x <- 1:1e6
obj_size(x)
y <- x
obj_size(x, y) # Same memory (copy-on-modify)
y[1] <- 0L
obj_size(x, y) # Now separate
Compare Sizes
# Compare object sizes
sizes <- c(
"vector" = obj_size(1:1000),
"list" = obj_size(as.list(1:1000)),
"df" = obj_size(data.frame(x = 1:1000))
)
sizes
Memory Efficiency
# Integer vs double
obj_size(1:1000) # Integer
obj_size(as.double(1:1000)) # Double (2x size)
# Character interning
x <- rep("hello", 1000)
obj_size(x) # Efficient due to interning
Tree Visualization
# View call tree
tree(quote(f(g(x), h(y, z))))
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.
- 4d ago First seen · 117 lines · 21 tokens per session scan A 29bbc5070a47
lobstr is a skill published in the GitHub repository LeoLin990405/r-analytics-skill (5 stars, last pushed 5mo ago), licensed MIT. It adds 21 tokens to every session and 487 once invoked, about $0.0001 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 2026-09-03.
Other skills, from other repositories
wax-performance-audit
Benchmarking and performance auditing for the Wax repo. Use when running or interpreting Wax benchmarks, diagnosing CPU, memory, or I/O bottlenecks, or investigating Swift 6.2 concurrency issues such as Sendable, actor isolation, @unchecked Sendable, task-group fan-out, and data races.
alibaba-observability-incident-responder
Respond to Alibaba Cloud incidents using CloudMonitor alarms, SLS log analytics, ARMS APM distributed tracing, and alert governance for ECS, RDS, ACK, and network services.
azure-cosmosdb-performance-investigator
Use this skill for Azure Cosmos DB performance investigation, especially RU spikes, query latency, throttling, hot partitions, indexing inefficiency, partition-skew analysis, request-charge profiling, diagnostic-log review, and evidence-driven remediation planning.
azure-observability-investigator
Use this skill for Azure Monitor, Log Analytics, Application Insights, alerting, KQL triage, telemetry-gap analysis, workbooks, or operator-grade incident and posture investigations.
azure-resource-health-incident-triage
Use this skill for Azure Resource Health, Service Health, activity-log alert, and first-pass incident triage when the question is whether Azure platform health is part of the problem.
aws-observability-incident-responder
Investigate broad AWS incidents and observability gaps using CloudWatch metrics, logs, alarms, traces, EventBridge events, service health, runbooks, timelines, blast radius, root-cause discipline, and post-incident actions. Prefer RDS/Aurora investigator for database-specific performance incidents.