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 agentmods add commands/marcosd4h/deepextractruntime/pipelinegit clone --depth 1 https://github.com/marcosd4h/DeepExtractRuntimeWrote 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/commands/marcosd4h/deepextractruntime/pipeline)<a href="https://agentmods.dev/commands/marcosd4h/deepextractruntime/pipeline"><img src="https://agentmods.dev/badge/commands/marcosd4h/deepextractruntime/pipeline.svg" alt="Measured on agentmods" 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 | $0.00000 | $0.00853 |
| Opus 5 | $0.00000 | $0.00426 |
| Sonnet 5 | $0.00000 | $0.00171 |
| Haiku 4.5 | $0.00000 | $0.00085 |
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 4d 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 — 101 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Pipeline
Overview
Run, validate, or inspect headless batch analysis pipelines from YAML
definitions. Wraps the pipeline_cli.py CLI for interactive use within a
Cursor session.
Usage:
/pipeline run config/pipelines/security-sweep.yaml-- execute a pipeline/pipeline run config/pipelines/quick-triage.yaml --dry-run-- preview without executing/pipeline run config/pipelines/full-analysis.yaml --modules appinfo.dll,consent.exe-- override modules/pipeline validate config/pipelines/security-sweep.yaml-- validate without executing/pipeline list-steps-- show available pipeline steps
For YAML schema details and example pipeline files, see
docs/pipeline_guide.md and
config/pipelines/.
Execution Context
IMPORTANT: Invoke
pipeline_cli.pyfrom the workspace root:python .claude/helpers/pipeline_cli.py <subcommand> <args> --json
Always pass --json when parsing output programmatically.
Steps
Step 0: Preflight Validation
For run and validate subcommands, verify the pipeline YAML file path
exists and is readable before invoking the CLI. For list-steps, skip
validation.
1. Invoke pipeline CLI
Run the appropriate subcommand:
# List available steps
python .claude/helpers/pipeline_cli.py list-steps --json
# Validate a pipeline definition
python .claude/helpers/pipeline_cli.py validate <pipeline_file> --json
# Execute a pipeline (with optional flags)
python .claude/helpers/pipeline_cli.py run <pipeline_file> [--dry-run] [--modules M] [--output DIR] --json
Parse JSON stdout for the result payload.
2. Present results
For list-steps: present available steps as a table with columns: name,
kind, description, and supported options.
For validate: present pipeline name, resolved modules, rendered output
path, step summary, and any warnings.
For run --dry-run: present the planned execution (modules x steps) without
running any analysis.
For run: present a summary table:
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.
- 4d ago First seen · 101 lines · 0 tokens per session scan A 879ec2673fdf
pipeline is a command published in the GitHub repository marcosd4h/DeepExtractRuntime (19 stars, last pushed 4mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 853 tokens. 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.
Other commands, from other repositories
git
Git operations with intelligent commit messages and workflow optimization.
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.