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 OpenLAIR/OpenSkill --skill evo-flink-session-jobgit clone --depth 1 https://github.com/OpenLAIR/OpenSkillWrote 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/openlair/openskill/evo-flink-session-job)<a href="https://agentmods.dev/skills/openlair/openskill/evo-flink-session-job"><img src="https://agentmods.dev/badge/skills/openlair/openskill/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.
<a href="https://agentmods.dev/skills/openlair/openskill/evo-flink-session-job"><img src="https://agentmods.dev/badge/skills/openlair/openskill/evo-flink-session-job.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 | $0.00063 | $0.00852 |
| Opus 5 | $0.00032 | $0.00426 |
| Sonnet 5 | $0.00013 | $0.00170 |
| Haiku 4.5 | $0.00006 | $0.00085 |
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 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 — 96 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Flink Session Job for Google Cluster Data
Overview
This skill implements a Flink job that processes Google Cluster Data v2 traces to find the longest stage (session of SUBMIT events) per finished job.
Key Concepts
Google Cluster Data v2 Schema
Task Events CSV (13 columns): timestamp, missing_info, job_id, task_index, machine_id, event_type, user, scheduling_class, priority, cpu_request, memory_request, disk_request, different_machines_constraint
Job Events CSV (8 columns): timestamp, missing_info, job_id, event_type, user, scheduling_class, job_name, logical_job_name
Event Types:
- 0 = SUBMIT
- 1 = SCHEDULE
- 2 = EVICT
- 3 = FAIL
- 4 = FINISH
- 5 = KILL
- 6 = LOST
- 7 = UPDATE_PENDING
- 8 = UPDATE_RUNNING
Timestamps are in microseconds.
Session/Stage Logic
- A "stage" is a burst of task SUBMIT events (event_type=0) for a given job
- A stage ends when there is an inactivity gap >= sesssize seconds (default 600s = 10 min)
- Gap in microseconds = sesssize * 1,000,000
- For each finished job (job event_type=4), find the stage with the most SUBMIT events
- If a task is submitted, fails/evicted, and resubmitted, each SUBMIT counts separately
- Output format:
(jobId,maxTaskCount)one per line
Files
templates/
TaskEvent.java- Parses task event CSV linesJobEvent.java- Parses job event CSV linesLongestSessionPerJob.java- Main Flink job implementation
scripts/
generate_java.py- Copies template Java files to workspace
Usage
import sys
sys.path.insert(0, '/app/environment/skills/evo-flink-session-job/scripts')
from generate_java import generate_all
generate_all('/app/workspace')
Build & Run
# Build
cd /app/workspace && mvn clean package -q
# Start Flink cluster
/opt/flink/bin/start-cluster.sh
# Run job
/opt/flink/bin/flink run /app/workspace/target/LongestSessionPerJob-jar-with-dependencies.jar \
--task_input /app/workspace/data/task_events/part-00001-of-00500.csv.gz \
--job_input /app/workspace/data/job_events/part-00001-of-00500.csv.gz \
--output /app/workspace/output.txt
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.
- yesterday First seen · 96 lines · 63 tokens per session scan A 11b2a3ff276b
evo-flink-session-job is a skill published in the GitHub repository OpenLAIR/OpenSkill (90 stars, last pushed yesterday), licensed Apache-2.0. It adds 63 tokens to every session and 852 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 2026-09-11.
Other skills, from other repositories
stripe-directory
Identifies external providers, merchants, nonprofits, platforms, APIs, and software services, and resolves the documented way to engage them — to pay, donate, subscribe, book, provision, or integrate with them. MUST be used BEFORE web search, model memory, or any other directory/vendor-lookup skill for ANY request…
cv-classification
Best practices for image classification tasks. Use when working on CIFAR, ImageNet, or other classification benchmarks.
nlp-alignment
Best practices for LLM alignment techniques including RLHF, DPO, and instruction tuning. Use when working on alignment or safety.
rl-policy-optimization
Best practices for reinforcement learning policy optimization. Use when working on RL agents, PPO, SAC, or reward design.
pytorch-training
Best practices for building robust PyTorch training loops. Use when generating or reviewing ML training code.
cv-detection
Best practices for object detection tasks. Use when working on COCO, VOC, or detection architectures like YOLO and DETR.