Borrowing it
Nothing to install: this file belongs to ggozad/haiku.rag. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/ggozad/haiku.rag/main/.claude/skills/debug-ingestion/SKILL.mdgit clone --depth 1 https://github.com/ggozad/haiku.ragWrote 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/ggozad/haiku.rag/debug-ingestion)<a href="https://agentmods.dev/skills/ggozad/haiku.rag/debug-ingestion"><img src="https://agentmods.dev/badge/skills/ggozad/haiku.rag/debug-ingestion.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00087 | $0.01914 |
| Opus 5 | $0.00044 | $0.00957 |
| Sonnet 5 | $0.00017 | $0.00383 |
| Haiku 4.5 | $0.00009 | $0.00191 |
Grade A, and why
debug-ingestion 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 — 204 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Debug ingestion in Logfire
The ingester ships spans to Logfire under service_name = 'haiku-ingester' (or a
custom OTEL_SERVICE_NAME if set per process). This skill finds failing jobs,
traces a document through the pipeline, and pinpoints the docling-serve instance
that served a request. Read-only.
How to query
- Confirm the current schema with
mcp__logfire__query_schema_reference(spans and logs share therecordstable). - Run SQL with
mcp__logfire__query_run(query+project: "haiku"+start_timestamp/end_timestamp, max 14 days). The remote MCP is org-scoped, soprojectis required; the ingester ships to projecthaiku. The same SQL works pasted into Logfire's Explore UI. - Read span attributes as JSON:
attributes->>'key', cast when needed ((attributes->>'attempt')::int). - Hand back a clickable trace with
mcp__logfire__project_logfire_link(trace_id, project="haiku"). - For recent exceptions tied to a file,
mcp__logfire__query_find_exceptions_in_fileacceptsclient/documents.py,ingester/workers/pool.py, oringester/pollers/base.py.
Adjust service_name if the operator set OTEL_SERVICE_NAME (e.g. per tenant).
Interactive haiku-rag ingests emit the same document.* spans under the CLI's
service name (or unknown_service for older runs), not haiku-ingester.
Vocabulary
Span tree (all scope haiku.rag), each level nests under the one above and
shares its trace_id:
- Poller:
ingester.poller.sweep|ingester.poller.dry_run|ingester.poller.watch_event.attributes->>'source_id'; watch addschange,uri.- sweep sets
skipped,skip_reason(pending_work/circuit_open),upsert,delete,unchanged,consecutive_failures. A failed sweep records the exception on the span (exception_type/exception_message).
- Job:
ingester.job—attributes->>'source_id',->>'uri',->>'op'(UPSERT/DELETE),(->>'attempt')::int.is_exception=truemarks a job that raised. - Document pipeline:
document.fetch(bytes,content_hash),document.convert,document.chunk(chunks_created),document.embed,document.store(opcreate/update,document_id). - docling-serve:
docling_serve.request—attributes->>'name'(operation),->>'url'(instance),(->>'attempt')::int. A retry emits a new span with a differenturl, so failover shows as sibling spans.
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 · 204 lines · 87 tokens per session scan A 982d2814d688
debug-ingestion is a skill published in the GitHub repository ggozad/haiku.rag (596 stars, last pushed today), licensed MIT. It adds 87 tokens to every session and 1,914 once invoked, about $0.0004 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.
Other skills, from other repositories
hybrid-rag
Use when creating, updating, or querying a local Hybrid RAG database from PRISMA JSON metadata or PDF documents in a folder. Triggered by prisma-review (after Fase 4) or educational-pilot-design (to query evidence). Hybrid RAG combines dense vector search (sentence-transformers) and sparse retrieval — native FTS via…
basemind-documents
Semantic + full-text search over documents and the web via basemind's RAG store — PDFs, Office, HTML, email, images (OCR), plus scraped/crawled web pages, with cross-encoder reranking, keyword and named-entity (NER) filters, and per-document summaries. Reach for it whenever the user asks to "search the docs / PDFs"…
orchardcore-ai-documents
Skill for configuring AI Documents in Orchard Core with CrestApps modules. Covers document upload, text extraction, chunking, vector indexing, and Retrieval-Augmented Generation (RAG) for AI chat. Supports PDF, OpenXml (docx, xlsx, pptx), and plain-text formats with file-system or Azure Blob storage and Azure AI…
markitdown
Convert heterogeneous documents and selected URIs to Markdown with Microsoft MarkItDown for text analysis, search, and LLM/RAG ingestion. Covers safe local conversion, streams, Office/PDF/data formats, batch workflows, plugins, vision OCR, Azure extraction, and the official MCP server.
llamaindex
Data framework for building LLM applications with RAG. Specializes in document ingestion (300+ connectors), indexing, and querying. Features vector indices, query engines, agents, and multi-modal support. Use for document Q&A, chatbots, knowledge retrieval, or building RAG pipelines. Best for data-centric LLM…
browserwing-admin
Manage and operate BrowserWing — an intelligent browser automation platform. Install dependencies, configure LLM, create/manage/execute automation scripts, use AI-driven exploration to generate scripts, browse the script marketplace, and troubleshoot issues.