data-wrangler-plugin AGENTS.md

data-wrangler-plugin AGENTS.md is an instructions file for Codex, OpenCode from richard-gyiko/data-wrangler-plugin. It costs 469 tokens per session, scanned A, original, MIT.

Project instructions for developing the Data Wrangler Plugin, including a workflow for writing feature specifications, planning implementation, coding, and checking the result against shared practices.

In plain words
What is it for?
Use them when adding or changing skills, documenting requirements, planning files and steps, or reviewing an implementation.
Why use it?
They provide a repeatable way to keep plugin changes focused, complete, and consistent with the project’s guidelines.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md.

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 instructions/richard-gyiko/data-wrangler-plugin/agents-md
Clone the repo
git clone --depth 1 https://github.com/richard-gyiko/data-wrangler-plugin

Made for: Codex, OpenCode.

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 data-wrangler-plugin AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/richard-gyiko/data-wrangler-plugin/agents-md.svg)](https://agentmods.dev/instructions/richard-gyiko/data-wrangler-plugin/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/richard-gyiko/data-wrangler-plugin/agents-md"><img src="https://agentmods.dev/badge/instructions/richard-gyiko/data-wrangler-plugin/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 469 This file is loaded in full into every session.
When invoked 469 The same file — it is already loaded in full.
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 5.1 $0.00469 $0.00469
Opus 5 $0.00234 $0.00234
Sonnet 5 $0.00094 $0.00094
Haiku 4.5 $0.00047 $0.00047

Measured 5d ago against content hash 105861b356df, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

data-wrangler-plugin AGENTS.md 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 5d 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.

AGENTS.md · 57 lines

What it actually says

Agent Guidelines

Skill Best Practices

While working on a skill or planning a new spec to extend or modify the skill, make sure to follow the skill best practices here

Development Workflow

Follow this workflow when creating or modifying skills:

1. Create Specs

  • Define the feature requirements and scope
  • Document expected behavior and edge cases
  • Read best practices before finalizing specs

2. Create Implementation Plan

  • Break down the work into actionable steps
  • Identify files to create or modify
  • Use Context7 tools to fetch up-to-date library/SDK documentation for any libraries being used
  • Read best practices and verify the plan aligns with them

3. Cross-Check Specs and Implementation Plan

  • Verify the plan covers all spec requirements
  • Ensure nothing is missed or over-engineered
  • Confirm alignment with best practices (conciseness, progressive disclosure, etc.)

4. Implement

  • Follow the implementation plan step by step
  • Keep changes minimal and focused

5. Validate Against Best Practices

  • Review implementation against best practices
  • Check for: conciseness, appropriate freedom levels, consistent terminology
  • Ensure progressive disclosure patterns are used correctly

6. Cross-Check Implementation with Plan

  • Verify all planned items are implemented
  • Confirm no scope creep or missing pieces

7. Create Tests

  • Write meaningful, valuable tests that cover:
    • Core functionality
    • Edge cases from specs
    • Error handling

8. Run Tests and Fix Issues

  • Execute all tests
  • Fix any failures
  • Re-run until all tests pass

Key Principle

Always consult best practices during planning phases. Before finalizing specs or implementation plans, read through claude_skills_best_practices.md to ensure alignment with:

  • Conciseness guidelines
  • Progressive disclosure patterns
  • Workflow and feedback loop recommendations
  • Template and examples patterns
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. 5d ago First seen · 57 lines · 469 tokens per session scan A 105861b356df

Subscribe to this mod's changes

data-wrangler-plugin AGENTS.md is an instructions file published in the GitHub repository richard-gyiko/data-wrangler-plugin (3 stars, last pushed 8mo ago), licensed MIT. It adds 469 tokens to every session, about $0.0023 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 instructions, from other repositories