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 rossumai/claude-marketplace --skill export-pipeline-referencegit clone --depth 1 https://github.com/rossumai/claude-marketplaceWrote 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/rossumai/claude-marketplace/export-pipeline-reference)<a href="https://agentmods.dev/skills/rossumai/claude-marketplace/export-pipeline-reference"><img src="https://agentmods.dev/badge/skills/rossumai/claude-marketplace/export-pipeline-reference/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/rossumai/claude-marketplace/export-pipeline-reference"><img src="https://agentmods.dev/badge/skills/rossumai/claude-marketplace/export-pipeline-reference.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 | $0.00115 | $0.00759 |
| Opus 5.5 | $0.00046 | $0.00304 |
| Sonnet 5.5 | $0.00023 | $0.00152 |
| Haiku 4.5 | $0.00012 | $0.00076 |
Grade A, and why
export-pipeline-reference 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 1mo 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.
What it actually says
Export Pipeline — Request Processor Reference
This skill provides the complete configuration reference for the Request Processor, Rossum's multi-stage export pipeline engine. It replaces the legacy multi-hook pipeline with a single serverless function that executes complex API workflows from pure JSON settings — no code required.
For the full configuration guide, field reference, patterns, and examples, see reference.md.
IMPORTANT — hook setup: The Request Processor runs as a single serverless function hook. Install it from the Store ("Request Processor"), or create the hook via the Rossum API (or prd2) from that hook template, then configure the settings JSON. The template (id 50) is shown only to organization groups with the ps_eng_export_pipeline visibility tag, which only Rossum can add; without it the organization cannot see the template (GET /hook_templates/50 → 404). Because it is a function hook, a copy of an existing hook's config.code (or a prd2 deploy) works without the template — prd2 then creates it with a plain POST /hooks (see rossum-reference → Store templates and visibility, prd-reference → Hooks created from Store templates). To read the exact engine behaviour for a given deployment, pull config.code off the deployed hook — that is the authoritative version for that org.
Use this knowledge when:
- Building a new export pipeline that sends data to external APIs (Coupa, SAP, NetSuite, custom REST)
- Configuring SFTP/S3 file export via the
file-storage-exportservice - Writing the
settingsJSON for a Request Processor hook (stages, auth, requests, response handlers) - Using variable templating (
{field.*},{payload.*},{property.*},{token},{sequence}) - Setting up OAuth authentication with token caching
- Configuring conditional stage execution (evaluate phase with MongoDB-style filters)
- Fetching document relations or explicit data in
get_contentphase - Extracting values from API responses using JMESPath, XPath, or regex
- Iterating over line items or lists of related documents
- Uploading files (PDF scans, email EML, attachments) via multipart or files content types
- Migrating from the legacy Pipeline v1 (multi-hook chain) to the Request Processor (single hook)
- Debugging export pipeline issues (URL not fetching, token caching, handler conditions)
- Understanding the difference between
document_relationanddocument_relation_contentsources - Diagnosing prerequisite/setup failures: TCP timeouts to external hosts, missing
rossum_authorization_token,Schema sideloading must be enablederrors, generic "Some exception occurred" export failures
Note: The rossum-reference skill covers the legacy 6-step export pipeline chain (Custom Format Templating, REST API Export, Data Value Extractor, Export Evaluator, SFTP Export). This skill covers the Request Processor, which is the modern replacement that consolidates all steps into a single configurable hook.
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.
- 1mo ago Changed 77e2f79afcfa
- 2mo ago First seen · 32 lines · 115 tokens per session scan A f43e9f502799
export-pipeline-reference is a skill published in the GitHub repository rossumai/claude-marketplace (5 stars, last pushed 5d ago), licensed MIT. It adds 115 tokens to every session and 759 once invoked, about $0.0005 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 2026-08-31.
export-pipeline-reference compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| export-pipeline-referencerossumai/claude-marketplace | Skill | 5 | 5d ago | MIT | A | 115 | Claude Code |
| imagegenopenai/codex | Skill | 135k | today | Apache-2.0 | A | 113 | Codex |
| playwright-climicrosoft/playwright | Skill | 100k | today | Apache-2.0 | A | 19 | Claude Code |
| browser-automationopenclaw/openclaw | Skill | 394k | today | MIT | A | 36 | Claude Code |
| local-ai-agentsmicrosoft/ai-agents-for-beginners | Skill | 79k | 4d ago | MIT | A | 200 | Claude Code, Codex |
| systematic-debuggingobra/superpowers | Skill | 316k | 8d ago | MIT | A | 21 | Claude Code |
| next-cache-components-adoptionvercel/next.js | Skill | 143k | today | MIT | A | 95 | Claude Code |