querying-gdl-data

querying-gdl-data is a skill for Claude Code, Codex from greppable/greppable-cc-plugin. It costs 123 tokens per session (2,809 once invoked), scanned A, original, MIT.

Instructions for searching structured business records stored in GDL text files, such as customers, orders, invoices, or products.

In plain words
What is it for?
Use them to find records by field, cross-reference related items, aggregate numeric values, or convert records to CSV or JSON.
Why use it?
They make it easier to filter records, connect related records, calculate totals, and export selected data without a separate database tool.

Skill for Claude CodeCodex

Installs and runs on its own, but its text points at files inside its plugin — anything it tells you to read at a ${CLAUDE_PLUGIN_ROOT} path is only there once the plugin is installed. Installing the plugin gets both.

Part of the greppable plugin — 8 skills, 8 commands, 3 hooks shipped together

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/greppable/greppable-cc-plugin/querying-gdl-data
Any agent
npx skills add greppable/greppable-cc-plugin --skill querying-gdl-data
Clone the repo
git clone --depth 1 https://github.com/greppable/greppable-cc-plugin

Made for: Claude Code, Codex.

Or install greppable, the plugin that ships this one along with the rest of its 8 skills, 8 commands, 3 hooks.

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 querying-gdl-data

README.md
[![agentmods](https://agentmods.dev/badge/skills/greppable/greppable-cc-plugin/querying-gdl-data.svg)](https://agentmods.dev/skills/greppable/greppable-cc-plugin/querying-gdl-data)
Your own site
<a href="https://agentmods.dev/skills/greppable/greppable-cc-plugin/querying-gdl-data"><img src="https://agentmods.dev/badge/skills/greppable/greppable-cc-plugin/querying-gdl-data.svg" alt="Measured on agentmods" height="20"></a>
Per session 123 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,809 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 $0.00123 $0.02809
Opus 5 $0.00062 $0.01404
Sonnet 5 $0.00025 $0.00562
Haiku 4.5 $0.00012 $0.00281

Measured 4d ago against content hash dae01bebf3a5, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

querying-gdl-data 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 4d 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/querying-gdl-data/SKILL.md · 302 lines

How it starts

The opening of the file, as written. The whole thing — 302 lines — stays where its author put it; the contents beside it link to each section on GitHub.

GDL Quick Reference

Available Data Files

!bash -c 'find docs/gdl -name "*.gdl" -not -name "rules.gdl" -maxdepth 3 2>/dev/null | while read f; do count=$(grep -c "^@" "$f" 2>/dev/null || echo 0); echo "- $f ($count records)"; done'

Format

@type|key:value|key:value|key:value

Every record is one line. Every field is self-describing (key:value). No schema lookup needed.

Grep Patterns

# Filter by record type
grep "^@customer" data.gdl

# Find by field value
grep "tier:enterprise" data.gdl

# Find by ID
grep "id:C001" data.gdl

# Cross-reference (find orders for customer C001)
grep "customer:C001" data.gdl

# Count records
grep -c "^@order" data.gdl

# Sum numeric field
grep "^@order" data.gdl | grep -o 'amount:[0-9.][0-9.]*' | sed 's/^amount://' | awk '{s+=$1}END{print s}'

# Latest version of a record (if appended updates)
grep "id:C001" data.gdl | tail -1

Example

@customer|id:C001|name:Acme Inc|tier:enterprise|email:[email protected]
@customer|id:C002|name:Beta Corp|tier:startup|email:[email protected]
@order|id:O001|customer:C001|amount:4500.00|status:completed|date:2026-01-15
@order|id:O002|customer:C002|amount:890.00|status:pending|date:2026-01-20

Escaping

\| = literal pipe, \: = literal colon, \\ = literal backslash.

Tool Functions

Source the helpers:

source "${CLAUDE_PLUGIN_ROOT}/scripts/gdl-tools.sh"
Function Usage What it does
csv2gdl csv2gdl TYPE FILE Convert CSV to GDL records
json2gdl json2gdl TYPE FILE Convert JSON array or JSONL to GDL records. Supports stdin via -. Requires jq.
gdl_describe gdl_describe FILE Describe record types and sample records in a GDL file
gdl_latest gdl_latest ID FILE Get latest version of a record by ID
gdl_values gdl_values TYPE FIELD FILE List unique values for a field
Function Usage What it does
gdl_about gdl_about TOPIC [dir] [--layer=L] [--exclude-layer=L] [--summary] [--regex] [--ignore-case] Search across all GDL layers for TOPIC

Read the full file on GitHub · 302 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.

  1. 4d ago First seen · 302 lines · 123 tokens per session scan A dae01bebf3a5

Subscribe to this mod's changes

querying-gdl-data is a skill published in the GitHub repository greppable/greppable-cc-plugin (3 stars, last pushed 4mo ago), licensed MIT. It adds 123 tokens to every session and 2,809 once invoked, about $0.0006 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 2026-08-31.

Related

Other skills, from other repositories

ygrep

IMPORTANT: Try ygrep FIRST for all code and file searches before using Grep, Glob, or Task explore. ygrep uses a pre-built full-text index and returns results in milliseconds. Fall back to built-in tools only if ygrep returns no results.

yetidevworks/ygrep · 55 tokens

semantic-search

Code search for this repo — pick the right Beacon tool for the question: exact symbol lookup, reference tracing, file outline, or semantic search.

sagarmk/beacon-plugin · 32 tokens

ripgrep

Use when the user needs text or regex content search with ripgrep: composing rg commands, choosing flags, glob/type filtering, multiline or PCRE2 searches, pipeline output, grep-to-rg migration, or diagnosing why rg missed a file (gitignore, hidden, binary defaults). Not for syntax-aware structural queries (ast-grep)…

bahayonghang/my-ai-cli-toolkit · 81 tokens

writing-docs

Write or restructure documentation that agents and people actually read — choosing which of the four directories it belongs in (how-to, reference, decisions, exec-plans), knowing what belongs in a failure message instead of a file, and keeping the routing table honest. Use this whenever writing a doc, a runbook, a…

WangChangxin0809/repo-agent-harness · 141 tokens

repo-index

Give a repository a code-and-docs graph an agent can query — tree-sitter symbols, import and call edges, doc-to-code edges, ranked by personalized PageRank from whatever the current task touches. Use this when an agent cannot find the relevant code in a large repo, when grep returns hundreds of hits or none, when…

WangChangxin0809/repo-agent-harness · 108 tokens

writing-checks

Build the machinery that enforces a convention instead of documenting it — PreToolUse guards that block an action before it runs, CI gates that judge the worktree, selftests that prove a check can turn red, and structural tests that enforce layering. Use this whenever a rule keeps getting violated despite being…

WangChangxin0809/repo-agent-harness · 105 tokens