What is evo-flink-session-job?

A streaming-data job for finding the longest group of closely timed task submissions for each completed job in Google cluster trace data. A session is a run of events separated by no more than a chosen time gap.

Use it in Apache Flink to read compressed cluster-trace files, group task submissions by job, find the largest session, and output each completed job with its maximum task count.

It handles event-time conversion, grouping, session detection, counting, and filtering for completed jobs instead of requiring those operations to be implemented manually.

evo-flink-session-job — Skill for Claude Code and Codex by Zhang-Henry

Install

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.

Any agent

npx skills add Zhang-Henry/CoEvoSkills --skill evo-flink-session-job

Clone the repo

git clone --depth 1 https://github.com/Zhang-Henry/CoEvoSkills

Made for: Claude Code, Codex.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/zhang-henry/coevoskills/evo-flink-session-job/github.svg)](https://agentmods.dev/skills/zhang-henry/coevoskills/evo-flink-session-job)

Your own site

<a href="https://agentmods.dev/skills/zhang-henry/coevoskills/evo-flink-session-job"><img src="https://agentmods.dev/badge/skills/zhang-henry/coevoskills/evo-flink-session-job/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/zhang-henry/coevoskills/evo-flink-session-job"><img src="https://agentmods.dev/badge/skills/zhang-henry/coevoskills/evo-flink-session-job.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 67 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,020 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits

NVIDIA SkillSpector pass 7 Sept 2026

How audits are shown

Origin original No closer match found in the catalogue.

Token cost

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	$0.00067	$0.01020
Opus 5	$0.00034	$0.00510
Sonnet 5	$0.00013	$0.00204
Haiku 4.5	$0.00007	$0.00102

Measured 12d ago against content hash bec47ad81da1, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

evo-flink-session-job 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 12d ago.

The scan reads SKILL.md. This mod also ships 3 executable files (scripts/build_and_run.py, scripts/generate_java_sources.py, scripts/validate_output.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

artifacts/skills/flink-query/evo-flink-session-job/SKILL.md · 118 lines

How it starts

The opening of the file, as written. The whole thing — 118 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Flink Longest Session Per Job

This skill implements a Flink streaming job that:

Reads Google cluster trace task events and job events from gzipped CSV files
Filters task SUBMIT events (eventType=0)
Groups by jobId and applies EventTimeSessionWindows with a configurable gap (default 10 minutes)
Counts tasks per session window per job
Finds the session with the maximum task count per job
Only outputs results for jobs that have FINISH events (eventType=4)
Output format: (jobId,maxTaskCount) one per line

Key Technical Details

Data Schema (Google Cluster Trace)

Task Events CSV columns: timestamp, missingInfo, jobId, taskIndex, machineId, eventType, user, schedulingClass, priority, cpuRequest, memoryRequest, diskSpaceRequest, differentMachinesRestriction

Job Events CSV columns: timestamp, missingInfo, jobId, eventType, user, schedulingClass, jobName, logicalJobName

Event Types: 0=SUBMIT, 1=SCHEDULE, 2=EVICT, 3=FAIL, 4=FINISH, 5=KILL, 6=LOST, 7=UPDATE_PENDING, 8=UPDATE_RUNNING

Timestamp Handling

Dataset timestamps are in microseconds
Flink event time uses milliseconds
Convert: event.timestamp / 1000

Session Window Strategy

A "stage" is a period of SUBMIT events close together in event time
Gap of 10 minutes (600 seconds) with no SUBMIT events ends a stage
Uses EventTimeSessionWindows.withGap(Time.seconds(600))
Each resubmission of a task counts separately

Join Strategy

Uses KeyedCoProcessFunction to join session counts with job finish events
Registers event-time timer at Long.MAX_VALUE - 1 to emit final results
For bounded streams, this timer fires when the watermark reaches MAX_VALUE at stream end
Only emits for jobs where both session counts AND finish event exist

Project Structure

workspace/
  pom.xml                    # Do not modify
  src/main/java/clusterdata/
    datatypes/
      TaskEvent.java         # Generated by skill
      JobEvent.java          # Generated by skill
    query/
      LongestSessionPerJob.java  # Generated by skill
    utils/
      AppBase.java           # Provided skeleton

Read the full file on GitHub · 118 lines

Files

What ships with it

3 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.

Changes

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.

12d ago First seen · 118 lines · 67 tokens per session scan A bec47ad81da1

Subscribe to this mod's changes

evo-flink-session-job is a skill published in the GitHub repository Zhang-Henry/CoEvoSkills (66 stars, last pushed 22d ago), licensed Apache-2.0. It adds 67 tokens to every session and 1,020 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 2026-08-30.

Analytics and metrics Data and AI

agent-platform-rag-engine-management

Manage and query Agent Platform RAG Engine Corpora and retrieve grounded contexts using the Google GenAI SDK. Use when listing RAG corpora or files, inspecting a corpus, retrieving contexts, or generating content grounded in a RAG corpus. Do not use for standard database queries (use SQL/Spanner skills), Google…

google/skills · 85 tokens

agent-platform-model-registry

Agent Platform Model Registry Management. Use when you need to upload, list, describe, update, or delete machine learning models (and their versions) in the Agent Platform Model Registry. Don't use for model training, model deployment to endpoints, or managing non-Agent Platform models.

google/skills · 60 tokens

foundry-config-setup

Resolve missing setup caused by a hardcoded Foundry project endpoint or model in a sample. Use when a sample fails because it uses a placeholder/hardcoded projectendpoint (for example "https://your-project.services.ai.azure.com") or a hardcoded model instead of reading them from the environment.

microsoft/agent-framework · 65 tokens

google-cloud-solution-agentic-analytics-spark-knowledge-catalog

Discovers requirements and generates guidance to design and deploy a governed, secure agentic-analytics solution for data that's distributed across Google Cloud, other cloud providers, or on-premises. Data that's outside Google Cloud (such as data from Databricks, Snowflake, Salesforce, SAP, or Oracle systems) is…

google/skills · 138 tokens

training-check

Interactively monitor training metrics from the current Codex session, periodically checking WandB or fallback logs for NaN, divergence, plateaus, and broken runs.

wanshuiyin/Auto-claude-code-research-in-sleep · 35 tokens

nemo-automodel-launcher-config

Configure NeMo AutoModel job launches for interactive runs, Slurm clusters, and SkyPilot cloud execution.

NVIDIA/skills · 30 tokens