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 pryrgit 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/pryr)<a href="https://agentmods.dev/skills/leolin990405/r-analytics-skill/pryr"><img src="https://agentmods.dev/badge/skills/leolin990405/r-analytics-skill/pryr/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/leolin990405/r-analytics-skill/pryr"><img src="https://agentmods.dev/badge/skills/leolin990405/r-analytics-skill/pryr.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00023 | $0.00726 |
| Opus 5 | $0.00012 | $0.00363 |
| Sonnet 5 | $0.00005 | $0.00145 |
| Haiku 4.5 | $0.00002 | $0.00073 |
Grade A, and why
pryr 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 8d 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 — 180 lines — stays where its author put it; the contents beside it link to each section on GitHub.
pryr
Tools for computing on the language.
Object Information
library(pryr)
# Object size
object_size(x)
object_size(x, y) # Combined size
# Compare sizes
compare_size(x, y)
# Memory address
address(x)
# References to object
refs(x)
Memory Tracking
# Track memory changes
mem_used()
# Memory change from expression
mem_change(x <- 1:1e6)
# Track allocations
track_copy(x)
Object Types
# Type of object
otype(x) # base, S3, S4, RC, R6
# Is object...
is_s3_generic(f)
is_s3_method(f)
# Function type
ftype(f) # primitive, internal, closure, special
Environments
# Where is object defined
where("mean")
# Parent environments
parenvs(e)
# Environment as list
env2list(e)
Function Inspection
# Function body
body(f)
# Function arguments
fargs(f)
# Function environment
environment(f)
# Unenclose function
unenclose(f)
Promises
# Check if promise
is_promise(x)
# Promise info
promise_info(x)
Calls and Expressions
# Standardize call
standardise_call(quote(mean(x, na.rm = TRUE)))
# Modify call
modify_call(call, new_args)
# Call tree
call_tree(quote(f(g(x), h(y))))
Active Bindings
# Create active binding
make_active_binding("x", function() runif(1), .GlobalEnv)
# Check if active binding
is_active_binding("x")
Partial Application
# Partial function application
f <- function(x, y, z) x + y + z
g <- partial(f, x = 1)
g(y = 2, z = 3) # Returns 6
# With dots
h <- partial(f, x = 1, .lazy = FALSE)
Composition
# Compose functions
f <- function(x) x + 1
g <- function(x) x * 2
fg <- compose(f, g) # f(g(x))
fg(5) # Returns 11
Substitution
# Substitute in expression
subs(x + y, list(x = 1))
# Substitute with quoting
subs_q(x + y, list(x = quote(a)))
Bytecode
# Check if bytecode compiled
is_bytecode(f)
# Disassemble bytecode
disassemble(f)
Performance
# Compare object sizes
object_size(1:1000)
object_size(as.numeric(1:1000))
# Memory efficient operations
# Use pryr to understand memory behavior
x <- 1:1e6
address(x)
x[1] <- 0L
address(x) # Same address (modify in place)
y <- x
address(y) # Same address (copy on modify)
y[1] <- 1L
address(y) # Different address (copied)
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.
- 8d ago First seen · 180 lines · 23 tokens per session scan A b27216cffce6
pryr is a skill published in the GitHub repository LeoLin990405/r-analytics-skill (5 stars, last pushed 5mo ago), licensed MIT. It adds 23 tokens to every session and 726 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
bio-applied-molecular-evolution
Test Hardy-Weinberg equilibrium, simulate Wright-Fisher drift/selection, and compute dN/dS, Tajima's D, and Fst with NumPy/SciPy. Use for neutral theory, molecular clock divergence time, selection scans, or effective population size (Ne) questions.
advanced-string-structures
Build tries, Aho-Corasick, and suffix arrays with Kasai LCP to index DNA/text and match many patterns in one pass. Use for genome motif scanning, k-mer indexing, longest-repeat search, or BWA/FM-index groundwork.
ai-science-esm2-embeddings
Generate ESM2 protein embeddings (fair-esm/transformers) and predict structure with ESMFold. Use when embedding sequences, scoring mutations zero-shot, annotating protein function, or doing fast MSA-free structure prediction.
ai-science-geneformer-scgpt
Tokenize scRNA-seq via Geneformer gene-rank or scGPT expression-bin encoding; annotate cell types, simulate in-silico knockouts. Use for foundation-model cell annotation, Geneformer/scGPT tokenization, or perturbation prediction.
ai-science-zero-shot-mutation
Score protein point mutations zero-shot with ESM-1v/ESM-2 masked-LM log-odds, ensembled, benchmarked on ProteinGym DMS. Use when predicting mutation effects, ranking missense variants, scoring VUS fitness with no labels.
bio-applied-advanced-ngs
Assemble genomes de novo: greedy OLC, de Bruijn graph/Eulerian path, N50/L50/NG50 stats, SPAdes/Flye/hifiasm CLI usage. Use when choosing k-mer size, picking an assembler for Illumina/ONT/HiFi reads, or scoring contiguity.