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 skills/eslider/2dph/etl-handlernpx skills add eSlider/2dph --skill etl-handlergit clone --depth 1 https://github.com/eSlider/2dphWhat 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 | $0.01101 |
| Opus 5 | $0.00000 | $0.00550 |
| Sonnet 5 | $0.00000 | $0.00220 |
| Haiku 4.5 | $0.00000 | $0.00110 |
Grade A, and why
etl-handler 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 2d 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 — 114 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill: etl-handler — canonical Go ETL extraction pattern
Use when implementing file-type handlers, extractors, decoders or transforms for the corpus pipeline. Mandatory before writing such code (AGENTS.md, code standards #8–#11).
Core idea: any format may nest any other format (.eml → zip → .eml → pdf). One handler per type; a central registry recurses; results are typed trees of URL-addressable nodes.
Contracts
// Blob is an addressable unit of content flowing through the pipeline.
type Blob struct {
SHA256 string // integrity + idempotency key
Name string // sanitized filename
MIME string // declared × sniffed (mismatch wins for safety)
Size int64
Open func(ctx context.Context) (io.ReadCloser, error) // lazy
}
type Attachment = Blob // child inside a Result
type Result struct {
MIME string // resolved type of this node
Meta Meta // typed per-handler metadata (struct, not map)
Text []byte // extracted text/markdown when applicable
Children []Attachment // nested parts — recurse via Registry
}
type Handler interface {
Match(declaredMIME string, sniff []byte) bool
Handle(ctx context.Context, src Blob) (*Result, error) // sync, ctx-first
}
- Node identity: URL
scheme://platform/thread/msg/path-segments[#anchor](e.g.mail://gmail/T42/M17/body/p[3]/table[0]#r2,c5); node ID =sha256(URL)[:16]; separatesha256(body)for integrity. - Parts reference each other only via URLs; href/src become
LINKS_TOedges. - Content splits granularly BEFORE insertion: html/md/pdf yield mime-typed blocks (paragraph / table / image / link / page).
Walker safety (hard limits)
- Max depth 10; per-item size cap; total-size and file-count caps;
- zip-ratio guard: uncompressed/compressed > N → refuse;
- reject names with
.., absolute paths, null bytes, control chars, length > 255; collisions get-<hash8>suffix; - large payloads spool to
var/tmp(cleaned after processing);Body []byteonly under the small-size threshold (~1 MB); - per-child errors are collected — never fatal to the whole tree.
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.
- 2d ago First seen · 114 lines · 0 tokens per session scan A 237341fec475
etl-handler is a skill published in the GitHub repository eSlider/2dph (2 stars, last pushed 3d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,101 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 2026-08-31.
Other skills, from other repositories
potpie-source-ingestion
Use when the user explicitly asks to ingest, refresh, or deeply understand a repository, PR, issue, ticket, runbook, incident report, document, or web link into Potpie. The harness performs todo-driven discovery, uses local/GitHub/integration tools and read-only subagents when available, builds evidence-backed…
moss-search
Sub-10ms semantic search for Zo via Moss. Create indexes, add documents, and query them with semantic and keyword search. Use when users want to search through documents, knowledge bases, or any text content.
open-ontologies
AI-native ontology engineering using 50+ MCP tools backed by an in-memory Oxigraph triple store. Build, validate, query, and govern RDF/OWL ontologies with a generate-validate-iterate loop. Use when building ontologies, knowledge graphs, RDF data, SPARQL queries, BORO/4D modeling, SHACL validation, clinical…
mcp-local-rag
Searches, saves, and maintains a local document index through a local RAG MCP server. Use when user says "search my docs", "save this page", "read around that chunk", "sync my index", or invokes npx mcp-local-rag.
ontology-engineering
Build, validate, and govern RDF/OWL ontologies using the Open Ontologies MCP server. Use when the user asks to create, modify, query, or manage ontologies, knowledge graphs, or RDF data.
ontology-bootstrap
Build a trustworthy first ontology from an empty or near-empty ontology-atlas vault using only Atlas MCP evidence. Use when the user asks to analyze a codebase, bootstrap/fill its ontology, extract product meaning from a repository, or when a requested ontology task finds only starter nodes. Separate observed…