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/mpazik/binder/binder-importnpx skills add mpazik/Binder --skill binder-importgit clone --depth 1 https://github.com/mpazik/BinderWrote 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/mpazik/binder/binder-import)<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>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 | $0.00062 | $0.02093 |
| Opus 5 | $0.00031 | $0.01046 |
| Sonnet 5 | $0.00012 | $0.00419 |
| Haiku 4.5 | $0.00006 | $0.00209 |
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.
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
.mdfiles where each file becomes one or more records (frontmatter fields + body content)
Process Overview
- Sample the source to understand structure
- Inspect the target schema
- Analyze gaps between source data and schema
- Propose mapping and present to user
- Check for duplicates against existing records
- Generate transactions in batches
- 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
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.
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.
- 3d ago First seen · 240 lines · 62 tokens per session scan A c4aa291b23ab
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.
Other skills, from other repositories
embed-repo
Generate semantic embeddings for a repository's code symbols.
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…
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.
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.
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".
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…