binder-import

binder-import is a skill for Claude Code, Codex from mpazik/Binder. It costs 62 tokens per session (2,093 once invoked), scanned A, original, MIT.

A guide for importing CSV, TSV, JSON, YAML, and Markdown data into Binder, a knowledge graph that stores structured records and links. It maps the incoming data to Binder's existing schema and creates transaction files for the changes.

In plain words
What is it for?
Use it to load files or Markdown folders, inspect the target schema, propose field mappings, check for duplicates, generate transactions, and apply imports in batches.
Why use it?
It helps move external data into the right record fields while checking the schema and possible duplicates first. Dry runs let you review batches before applying them.

Skill for Claude CodeCodex

Install

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.

agentmods
npx agentmods add skills/mpazik/binder/binder-import
Any agent
npx skills add mpazik/Binder --skill binder-import
Clone the repo
git clone --depth 1 https://github.com/mpazik/Binder

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for binder-import

README.md
[![agentmods](https://agentmods.dev/badge/skills/mpazik/binder/binder-import.svg)](https://agentmods.dev/skills/mpazik/binder/binder-import)
Your own site
<a href="https://agentmods.dev/skills/mpazik/binder/binder-import"><img src="https://agentmods.dev/badge/skills/mpazik/binder/binder-import.svg" alt="Measured on agentmods" height="20"></a>
Per session 62 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,093 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00062 $0.02093
Opus 5 $0.00031 $0.01046
Sonnet 5 $0.00012 $0.00419
Haiku 4.5 $0.00006 $0.00209

Measured 3d ago against content hash c4aa291b23ab, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

binder-import 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 3d 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.

skills/binder-import/SKILL.md · 240 lines

How it starts

The opening of the file, as written. The whole thing — 240 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Binder Import

Import external data into a Binder knowledge graph by mapping source structure onto the existing schema, then generating transaction files.

Supported Sources

  • Tabular: CSV, TSV (rows become records, headers become field candidates)
  • Structured: JSON array, YAML list (objects become records, keys become field candidates)
  • Single Markdown: one file with repeating structure (tables, heading-delimited sections, lists)
  • Markdown directory: folder of .md files where each file becomes one or more records (frontmatter fields + body content)

Process Overview

  1. Sample the source to understand structure
  2. Inspect the target schema
  3. Analyze gaps between source data and schema
  4. Propose mapping and present to user
  5. Check for duplicates against existing records
  6. Generate transactions in batches
  7. Dry-run and apply each batch

Step 1: Sample the Source

Do not read the entire source upfront. Sample enough to understand structure and value patterns.

Tabular files (CSV, JSON, YAML):

  • Small (< 200 rows): read the whole file
  • Large (200+ rows): read the first 50 rows. Note total row count. Ask the user if the structure is uniform throughout

Single Markdown file:

  • Small (< 300 lines): read the whole file
  • Large (300+ lines): read the first 200 lines. Ask the user if the pattern continues or if there are structurally different sections later

Markdown directory:

  • List all files: find <dir> -name '*.md' | head -100
  • Count total: find <dir> -name '*.md' | wc -l
  • Read 3-5 files chosen for variety (different sizes, different subdirectories, first and last alphabetically)
  • Note if files have frontmatter, consistent heading structure, or freeform content

Report what you found: number of items, identified columns/fields, sample values, any inconsistencies.

Step 2: Inspect Target Schema

binder schema
binder schema -n config

Identify which types and fields already exist. Pay attention to:

  • Field data types and constraints
  • Required fields and defaults
  • Relation fields and their targets
  • Option fields and their allowed values

Read the full file on GitHub · 240 lines

Files

What ships with it

2 files 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.

Changes

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.

  1. 3d ago First seen · 240 lines · 62 tokens per session scan A c4aa291b23ab

Subscribe to this mod's changes

binder-import is a skill published in the GitHub repository mpazik/Binder (40 stars, last pushed 11d ago), licensed MIT. It adds 62 tokens to every session and 2,093 once invoked, about $0.0003 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.

Related

Other skills, from other repositories

embed-repo

Generate semantic embeddings for a repository's code symbols.

juice094/devbase · 13 tokens

engraphis-memory

Give the agent durable, scoped, explainable memory across sessions and repositories through the Engraphis MCP tools. Use when you learn a convention, decision, bug cause/fix, or user preference worth keeping; when prior context would help before you answer or act (to avoid re-asking or re-deriving); when asked "why is…

Coding-Dev-Tools/engraphis · 134 tokens

deeprefine

Agent-native DeepRefine refinement loop — same control flow as DeepRefine.refine(), graphify search instead of FAISS, session LLM, dry-run review before approved graph writes.

HKUST-KnowComp/DeepRefine-Skill · 42 tokens

deeprefine

Claude Code adapter for the DeepRefine agent-native refinement loop. Use when the user invokes /deeprefine, or asks to refine, diagnose, review, or apply changes to a Graphify / LLM-Wiki knowledge graph. Must follow the canonical DeepRefine skill rules and stop for review before graph writes.

HKUST-KnowComp/DeepRefine-Skill · 68 tokens

remnic-entities

Browse entities in the Remnic knowledge graph and surface their facts and relationships. Trigger phrases include "tell me about the entity", "look up", "what do we know about".

joshuaswarren/remnic · 41 tokens

encyclopedia-writing

Encyclopedic neutral-reference writing craft — NPOV (attribute facts not opinions, due weight, neutral faction labels, verdict restraint), summary style and Coatrack avoidance, wikilink conventions (link density, first-mention, slug alias, abbreviation glossing). Use when writing or reviewing a neutral…

alfadur7/llm-wiki-newsroom · 95 tokens