A command-line interface for Binder, a Markdown-based knowledge graph that stores connected records and their relationships. It supports reading, searching, creating, updating, and deleting records, as well as inspecting schemas and managing transactions.

Use it to search records, inspect schemas, create or update entries, import transaction files, view recent changes, and undo transactions in a Binder workspace.

It gives you one terminal tool for working with Binder data and for reviewing or undoing batches of changes. This avoids handling each record manually.

binder-cli — Skill for Claude Code and Codex by mpazik/Binder

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.

Any agent

npx skills add mpazik/Binder --skill binder-cli

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/mpazik/binder/binder-cli/github.svg)](https://agentmods.dev/skills/mpazik/binder/binder-cli)

Your own site

<a href="https://agentmods.dev/skills/mpazik/binder/binder-cli"><img src="https://agentmods.dev/badge/skills/mpazik/binder/binder-cli/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/mpazik/binder/binder-cli"><img src="https://agentmods.dev/badge/skills/mpazik/binder/binder-cli.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 60 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,945 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits

NVIDIA SkillSpector warn 7 Sept 2026

SkillSpector: 1 finding, up to medium

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

medium Excessive Agency · line 112
Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.

Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.

How audits are shown

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.

Model	Per session	Once invoked
Fable 5.1	$0.00060	$0.01945
Opus 5.5	$0.00024	$0.00778
Sonnet 5.5	$0.00012	$0.00389
Haiku 4.5	$0.00006	$0.00194

Measured 1mo ago against content hash 22f537a8f856, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

binder-cli 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.

skills/binder-cli/SKILL.md · 191 lines

How it starts

The opening of the file, as written. The whole thing — 191 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Binder CLI

Binder is a Markdown-native knowledge graph. The CLI is the primary interface for all operations.

Run binder --help or binder <command> --help for full usage details.

Quick Reference

binder read <ref>                                   # Read a record
binder search type=Task status=active               # Search records
binder schema --types Task                           # Inspect schema
binder create <Type> field=value [field=value...]    # Create a record
binder update <ref> field=value [field=value...]     # Update fields
binder delete <ref>                                  # Delete a record
binder tx import -d file.yaml                        # Dry-run a transaction file
binder tx import file.yaml                           # Apply a transaction file
binder tx log --limit 5                              # Recent transactions
binder undo [N]                                      # Undo last N transactions

Global options: -C <path> cwd, -q quiet, --format output format, -n namespace.

Reading

read

binder read <ref> [--format yaml|json] [-f fields]

Ref: id (numeric), uid (e.g. 6VI6iLYBQUg), or key (e.g. type/field keys Task, status, or a record key like example-task).

Use -f/--fields to include or traverse relations inline — same syntax as search.

search

binder search type=Task status=active       # Filter by field values
binder search "some text"                   # Full-text search
binder search type=Task -f partOf(title)    # Include fields from related records
binder search type=Task -o '!priority'      # Order by (! = descending)
binder search type=Task --limit 10          # Limit results

Options:

--format — json, jsonl, yaml, csv, tsv
-n, --namespace — record (default) or config
-f, --fields — include specific fields or traverse relations. title,status includes those fields. partOf(title,status) follows the partOf relation and includes title and status from the related record. Use relatesTo[type=Task](title) to filter relation targets by type before traversal.
-o, --orderBy — sort (prefix ! for descending)
--limit — max results

Read the full file on GitHub · 191 lines

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.

1mo ago First seen · 191 lines · 60 tokens per session scan A 22f537a8f856

Subscribe to this mod's changes

binder-cli is a skill published in the GitHub repository mpazik/Binder (40 stars, last pushed 25d ago), licensed MIT. It adds 60 tokens to every session and 1,945 once invoked, about $0.0002 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 2026-08-30.

Databases agent-memory cli knowledge-base knowledge-graph local-first lsp

slm-cache

KV cache for repeated reads — call slmcacheget(key) first; on a miss do the expensive operation then slmcacheset(key, value, ttlseconds) to store it; on a hit use the returned value directly; always fail-open (hit:false on any error, never raises); saves tokens when the same file, query result, or tool output is read…

qualixar/superlocalmemory · 86 tokens

duckdb-analyst

Use for any analytical question over ./data/.parquet. Prefer DuckDB, always show the SQL.

jin-bo/agentao · 27 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

kb-create

Operator procedure to declare and provision a new Knowledge Base GitOps-style, so it survives pod restarts; also covers authoring the KB's artifacts (skills, subagents, hooks, MCP descriptors) and the SOPS encryption flow.

BeppeTemp/cartographer · 50 tokens

graft

Persistent graph memory shared across conversations and agents. Graft is a prompter, not a cache: it hands you notes that may be close to the problem in front of you, and a close note is already a win - it gives you a starting point and reminds you what was decided before. Search it before non-trivial work, and write…

AEndrix03/Graft · 196 tokens

memoryze

Distill the current conversation (or a specified excerpt) into N high-quality graft nodes and save them. Triggered by /memoryze, "save this to memory", "ricorda questo", "memorize this", or whenever the user explicitly wants the agent to commit knowledge to the persistent graph. The user can hint at granularity…

AEndrix03/Graft · 122 tokens