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 iowarp/clio-kit --skill data-cleangit clone --depth 1 https://github.com/iowarp/clio-kitWrote 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/iowarp/clio-kit/data-clean)<a href="https://agentmods.dev/skills/iowarp/clio-kit/data-clean"><img src="https://agentmods.dev/badge/skills/iowarp/clio-kit/data-clean/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/iowarp/clio-kit/data-clean"><img src="https://agentmods.dev/badge/skills/iowarp/clio-kit/data-clean.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 | $0.00044 | $0.01521 |
| Opus 5.5 | $0.00018 | $0.00608 |
| Sonnet 5.5 | $0.00009 | $0.00304 |
| Haiku 4.5 | $0.00004 | $0.00152 |
Grade A, and why
data-clean 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 — 138 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Data Cleaning
Every repair here changes the numbers that come out. Look before repairing, and say what was done.
Inspect what the requested change needs
For an explicitly specified repair, inspect the affected columns, perform that repair and verify its output. Do not expand a request for interpolation into deduplication, outlier removal, memory optimisation or a general validation audit. Use the broader checks below when the user asks for cleaning or the observed data exposes a relevant problem.
clio-pandas:profile_data — shape, types, missing values, distributions, quality
checks. On a raw CSV, clio-pandas:profile_csv answers the same first questions
using a bounded sample; its counts/statistics need not cover the whole file.
Read three things before touching anything: how much is missing and where, whether dtypes match what the columns mean, and whether ranges are physically possible.
Missing data: how it is missing decides the fix
clio-pandas:handle_missing_data takes two separate arguments, and conflating
them is the usual first failure. strategy is one of detect, impute,
remove or analyze, and defaults to detect, which only reports. method is
the imputation itself: mean, median, mode, forward_fill,
backward_fill, interpolate. Passing strategy="median" fails with "Unknown
strategy"; the call you want is strategy="impute", method="median".
The methods are not interchangeable. interpolate fills interior numeric gaps
linearly by row position: [1, missing, 3, missing, 5] becomes
[1, 2, 3, 4, 5]. Leading/trailing gaps, entirely missing columns and
non-numeric gaps remain missing; inspect the reported imputed_count and the
output. Select the intended columns. This is not time-weighted interpolation:
for irregular timestamps, use a verified time-aware calculation instead.
forward_fill propagates the previous observed value; backward_fill uses
the next observed value. Both follow row order, so sort and separate independent
series first. mode fills numeric or categorical gaps from observed values.
Mean/median operate only on numeric columns. Entirely missing columns stay
missing, and imputed_count counts actual fills. Preserve the input and assert
expected values before accepting any transformation.
If the tool chooses its own output filename, preserve the input and copy the
verified result to the user's requested destination, then verify that file.
What ships with it
1 file 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.
- 9d ago First seen · 138 lines · 44 tokens per session scan A c63617032e42
data-clean is a skill published in the GitHub repository iowarp/clio-kit (30 stars, last pushed 8d ago), licensed BSD-3-Clause. It adds 44 tokens to every session and 1,521 once invoked, about $0.0002 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 2026-10-08.
Other skills, from other repositories
bioprobench
Score an LLM's biological-protocol reasoning on the BioProBench benchmark: protocol QA, step ordering, error detection, protocol generation, and LLM-judged error reasoning; or generate the responses.
evo-memory
Manages persistent research memory across ideation and experimentation cycles. Maintains two stores: Ideation Memory MI (feasible/unsuccessful directions) and Experimentation Memory ME (reusable strategies for data processing, model training, architecture, debugging). Three evolution mechanisms: IDE (after…
raindrop-mcp
Connect Raindrop.io to your AI assistant with a simple MCP server. Use it to organize, search, and manage bookmarks with natural language.
onescience-orchestrator
A task coordinator for OneScience that turns a user’s goal into a tracked plan and assigns parts of the work to suitable specialist tools.
sota-management
4-level SOTA performance tracking for VibeCodeHPC. Use when checking or updating best performance records.
authoring-gradle-builds
Authoring and modifying Gradle build logic, including settings, plugins, dependencies, tasks, conventions, and upgrades. Activate when build files or plugins must change; use using-gradle for inspection or execution without build-definition edits.