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 log-searchgit 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/log-search)<a href="https://agentmods.dev/skills/iowarp/clio-kit/log-search"><img src="https://agentmods.dev/badge/skills/iowarp/clio-kit/log-search/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/log-search"><img src="https://agentmods.dev/badge/skills/iowarp/clio-kit/log-search.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 | $0.00049 | $0.00962 |
| Opus 5.5 | $0.00020 | $0.00385 |
| Sonnet 5.5 | $0.00010 | $0.00192 |
| Haiku 4.5 | $0.00005 | $0.00096 |
Grade A, and why
log-search 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 — 95 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Log Search
Most tools on this server take the file as log_file, not file_path. The
four export tools are the exception: export_to_csv, export_to_json,
export_to_text and generate_summary_report take data, the result of a
filter, because they export findings rather than re-reading the log.
filter_by_log_level also wants log_levels, not levels.
The kit is not consistent about this across servers, so carrying the habit
over from the data-file servers produces a missing-argument error that reads
as a missing file.
The failure mode here is reading the file into context. A job log can be hundreds of megabytes; these tools exist so you never have to hold it.
Order matters: sort, then filter, then look
1. Sort if the timestamps are out of order.
Parallel output interleaves. clio-parallel-sort:sort_log_by_timestamp expects
YYYY-MM-DD HH:MM:SS. For anything large, use
clio-parallel-sort:parallel_sort_large_file, which chunks instead of holding the
file in memory.
Skip this when the log is already ordered — sorting a large ordered file is pure cost.
2. Narrow before you read.
clio-parallel-sort:filter_by_time_rangewhen you already know roughly when.clio-parallel-sort:filter_by_log_levelforERROR/WARN.clio-parallel-sort:filter_by_keywordfor a known string, with multiple keywords combined logically.clio-parallel-sort:filter_logswhen the condition needs several fields at once.clio-parallel-sort:apply_filter_presetfor the common shapes (errors_only,connection_issues) — cheaper than reconstructing them by hand.
3. Get the shape before the detail.
clio-parallel-sort:analyze_log_statistics gives temporal patterns and per-level
counts. clio-parallel-sort:detect_log_patterns finds anomalies and error
clusters. Both answer "where should I look" without reading anything.
An error cluster is worth far more than the first error: the first error in a distributed run is frequently a symptom of a rank that failed earlier.
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 · 95 lines · 49 tokens per session scan A 5f34b13bd281
log-search is a skill published in the GitHub repository iowarp/clio-kit (30 stars, last pushed 8d ago), licensed BSD-3-Clause. It adds 49 tokens to every session and 962 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
experiment-iterative-coder
Iterative code refinement through plan → code → evaluate → refine cycles. Runs lint checks (ruff), tests (pytest), and structured self-evaluation each cycle, then diagnoses failures and refines. Decomposes complex tasks into sequential phases, iterates up to 3 times per phase (10 total). Use when: the main agent…
experiment-craft
Use this skill when the user wants to debug, diagnose, or systematically iterate on an experiment that already exists, or when they need a structured experiment log for tracking runs, hypotheses, failures, results, and next steps during active research. Apply it to underperforming methods, training that will not…
interacting-with-project-runtime
Interacting with a project's JVM runtime through the Kotlin REPL to execute focused probes against project classes and dependencies. Activate when behavior must be observed by running code; use using-gradle for build inspection or task execution.
using-gradle
Using Gradle MCP tools to inspect and run existing builds, including projects, tasks, properties, dependencies, and build results. Activate for Gradle build operation and diagnosis; use authoring-gradle-builds when the build definition itself must change.
browser-debug
Debug style issues and console errors in a running web app using the kogiQA browser tools. Use when asked to investigate a layout/overflow problem, a broken page, or to collect and fix console errors.
drive-mcpjam-playground
Drive an API Playground session through MCPJam's remote MCP tools or cloud CLI, inspect browser evidence, and hand the live session to its owner. Use for agent-driven MCP server debugging with a hosted browser.