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 skills/justanesta/claude-code-resources/python-data-wranglingnpx skills add justanesta/claude-code-resources --skill python-data-wranglinggit clone --depth 1 https://github.com/justanesta/claude-code-resourcesWhat 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 | $0.00065 | $0.01234 |
| Opus 5 | $0.00032 | $0.00617 |
| Sonnet 5 | $0.00013 | $0.00247 |
| Haiku 4.5 | $0.00006 | $0.00123 |
Grade A, and why
python-data-wrangling 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.
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.
Python Data Wrangling
Modern patterns for pandas and polars data manipulation.
Decision Matrix: Pandas vs Polars
| Factor | Pandas | Polars | Winner |
|---|---|---|---|
| Data size | <1GB | >1GB, especially >10GB | Polars for large data |
| Query optimization | No | Yes (lazy evaluation) | Polars |
| Ecosystem integration | Vast (sklearn, viz) | Growing | Pandas for ML/viz |
| API familiarity | DataFrame standard | Rust-inspired | Pandas for teams |
| Performance | Good | Excellent (2-10x) | Polars |
| Memory usage | Higher | Lower | Polars |
General guidance:
- Use pandas when: <1GB data, heavy ML/viz integration, team familiarity critical
- Use polars when: >1GB data, performance critical, greenfield projects
Modern Pandas Patterns
Method Chaining
Chain operations for readability
result = (
df
.assign(
total=lambda x: x["price"] * x["quantity"],
date=lambda x: pd.to_datetime(x["date"])
)
.query("total > 100")
.sort_values("total", ascending=False)
.groupby("category")
.agg({"total": ["sum", "mean"]})
.reset_index()
)
See pandas-method-chaining.md for:
- Lambda vs direct assignment
- Pipe with custom functions
- Handling complex transformations
Idiomatic Operations
# Use .loc for explicit indexing
df.loc[df["score"] > 80, "grade"] = "A"
# Use .pipe() for custom transformations
result = df.pipe(normalize_columns).pipe(remove_duplicates)
# Use .assign() for new columns
df = df.assign(
log_value=lambda x: np.log(x["value"]),
is_high=lambda x: x["value"] > x["value"].median()
)
GroupBy Patterns
# Named aggregations (pandas 0.25+)
summary = df.groupby("category").agg(
total_sales=("sales", "sum"),
avg_sales=("sales", "mean"),
num_transactions=("sales", "count")
)
See pandas-groupby-patterns.md for:
- Window functions
- Multiple grouping levels
- Custom aggregations
What ships with it
5 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 180 lines · 65 tokens per session scan A c7b80404804d
python-data-wrangling is a skill published in the GitHub repository justanesta/claude-code-resources (2 stars, last pushed 4mo ago), licensed MIT. It adds 65 tokens to every session and 1,234 once invoked, about $0.0003 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 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…