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 arbazkhan971/godmode --skill pipelinegit clone --depth 1 https://github.com/arbazkhan971/godmodeWrote 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/arbazkhan971/godmode/pipeline)<a href="https://agentmods.dev/skills/arbazkhan971/godmode/pipeline"><img src="https://agentmods.dev/badge/skills/arbazkhan971/godmode/pipeline/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/arbazkhan971/godmode/pipeline"><img src="https://agentmods.dev/badge/skills/arbazkhan971/godmode/pipeline.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Tool Misuse · line 120 Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).Fix: Validate all tool parameters against an allowlist. Reject dangerous parameter values (shell=True, --force, -rf /) and use safe defaults.
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 | $0.00020 | $0.00972 |
| Opus 5 | $0.00010 | $0.00486 |
| Sonnet 5 | $0.00004 | $0.00194 |
| Haiku 4.5 | $0.00002 | $0.00097 |
Grade A, and why
pipeline 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 8d 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 — 132 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Activate When
/godmode:pipeline, "build a data pipeline", "ETL"- "data flow", "sync data", "data quality"
- Move, transform, or load data between systems
Workflow
1. Data Flow Specification
ls dags/ dbt_project.yml dagster.yaml 2>/dev/null
grep -r "airflow\|dagster\|prefect\|kafka" \
requirements.txt package.json 2>/dev/null
Name: <pipeline>
Type: batch | streaming | micro-batch | CDC
Schedule: cron | event-triggered | continuous
SLA: <max latency>
Sources: <name>: <type> (<format>, <volume/day>)
Transforms: 1. <step> (input -> output)
Destinations: <target>: <type> (<write method>)
Idempotent: yes/no
Error handling: skip | fail | dead-letter | retry
2. Pipeline Pattern
- Batch: Extract -> Stage -> Transform -> Validate -> Load (Airflow+dbt, Dagster, Prefect)
- Streaming: Source -> Processor -> Sink (Kafka+Flink, Spark Streaming)
- CDC: Source DB -> CDC tool -> Target (Debezium, AWS DMS)
- ELT: Extract -> Load raw -> Transform in warehouse (Fivetran/Airbyte + dbt)
IF data changes hourly: batch with cron. IF sub-second latency needed: streaming (Kafka). IF already using PostgreSQL: CDC with Debezium.
3. Implement Components
Extraction: track watermarks, retry with backoff, log metrics. Patterns: API pagination with rate limit, DB incremental by updated_at, file dedup.
Transformation: pure functions only -- no DB calls,
no side effects. Composable via .pipe().
Loading strategies:
- UPSERT: insert/update by key (dimensions)
- SWAP: staging + atomic rename (full refresh)
- APPEND: insert only (fact/event tables)
- SCD Type 2: historical tracking with dates
4. Data Quality Checks
Every pipeline needs these (not optional):
- Row: not_null, unique, range, pattern, referential
- Dataset: row count (min/max/threshold), completeness
- Cross-pipeline: source-target count reconciliation
IF quality < 95%: alert and investigate. IF count change > 50%: block load and alert.
5. Observability
Structured logging at every stage. Metrics: duration_seconds, rows_processed/rejected, last_success, data_freshness, quality_score. Alert: failure, 2x duration, quality < 95%, no data > 2 hours.
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.
- 8d ago First seen · 132 lines · 20 tokens per session scan A 67d2117956b0
pipeline is a skill published in the GitHub repository arbazkhan971/godmode (26 stars, last pushed 13d ago), licensed MIT. It adds 20 tokens to every session and 972 once invoked, about $0.0001 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 2026-09-03.
Other skills, from other repositories
LQF_Machine_Learning_Expert_Guide
LQF Machine Learning Expert Guide - Routed skill for ML/Statistical Modeling with Critical Discussion Mode. Triggers on: machine learning, modeling, prediction, training, classification, regression, clustering, deep learning, neural network, model evaluation, feature engineering, hyperparameter tuning, overfitting…
nowait-reasoning-optimizer
Implements the NOWAIT technique for efficient reasoning in R1-style LLMs. Use when optimizing inference of reasoning models (QwQ, DeepSeek-R1, Phi4-Reasoning, Qwen3, Kimi-VL, QvQ), reducing chain-of-thought token usage by 27-51% while preserving accuracy. Triggers on "optimize reasoning", "reduce thinking tokens"…
traction-eos
Implement the Entrepreneurial Operating System (EOS) to align vision and execution across a company. Use when the user mentions "EOS", "Entrepreneurial Operating System", "V/TO", "quarterly rocks", "Level 10 meetings", "accountability chart", "IDS process", "my company feels chaotic", "we keep having the same…
atlassian
Manage Jira issues and Confluence wiki pages in Atlassian Cloud. Use when: (1) searching/creating/updating Jira issues with JQL, (2) searching/reading/creating Confluence pages with CQL, (3) managing Jira workflows, transitions, and comments, (4) browsing Confluence spaces and page hierarchies. Supports OAuth 2.1 via…
om-auto-fix-issue
Fix or implement a tracker issue end to end from a single command — takes an issue id or a plain problem description (filed first via om-prepare-issue), classifies, then drives the bug autofix chain (om-verify-in-repo, om-root-cause, om-fix, om-open-pr, om-auto-review-pr, om-auto-qa-pr for UI fixes) or the feature…
schedule-forecaster
Predict project completion dates using ML models. Forecast schedule delays based on current progress, historical patterns, and risk factors.