Agent Context File Writer

Agent Context File Writer is a skill for Claude Code, Codex from Notysoty/openagentskills. It costs 45 tokens per session (1,692 once invoked), scanned A, original, MIT.

A tool that writes a project instruction file for a coding agent, such as CLAUDE.md, .cursorrules, or .windsurfrules. The file records the project’s technologies, conventions, constraints, and past agent mistakes.

In plain words
What is it for?
Use it to create or improve the instruction file for a frontend app, API, command-line tool, or other software project.
Why use it?
It gives the agent important context in one place, reducing wrong assumptions and repeated explanations.

Skill for Claude CodeCodex

Which agent this was written for is unclear — built for cline. Also seen: mentions CLAUDE.md; mentions Claude Code; mentions Codex.

Good fit Use it to create or improve the instruction file for a frontend app, API, command-line tool, or other software project.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/notysoty/openagentskills/agent-context-file-writer
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 Notysoty/openagentskills --skill agent-context-file-writer
Clone the repo
git clone --depth 1 https://github.com/Notysoty/openagentskills

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 Agent Context File Writer

README.md
[![agentmods](https://agentmods.dev/badge/skills/notysoty/openagentskills/agent-context-file-writer/github.svg)](https://agentmods.dev/skills/notysoty/openagentskills/agent-context-file-writer)
Your own site
<a href="https://agentmods.dev/skills/notysoty/openagentskills/agent-context-file-writer"><img src="https://agentmods.dev/badge/skills/notysoty/openagentskills/agent-context-file-writer/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.

agentmods 80×15 button for Agent Context File Writer

Your own site · 80×15
<a href="https://agentmods.dev/skills/notysoty/openagentskills/agent-context-file-writer"><img src="https://agentmods.dev/badge/skills/notysoty/openagentskills/agent-context-file-writer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 45 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,692 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.
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 $0.00045 $0.01692
Opus 5 $0.00023 $0.00846
Sonnet 5 $0.00009 $0.00338
Haiku 4.5 $0.00005 $0.00169

Measured 10d ago against content hash ce4dc067dfdd, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

Agent Context File Writer 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 10d 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/agent-context-file-writer/SKILL.md · 189 lines

How it starts

The opening of the file, as written. The whole thing — 189 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent Context File Writer

What this skill does

This skill writes the context file that tells a coding agent how to work in your project — CLAUDE.md for Claude Code, .cursorrules for Cursor, .windsurfrules for Windsurf, or .codebuddy for others. A well-written context file is the highest-leverage thing you can do to improve agent quality. It prevents the agent from making wrong assumptions, using the wrong patterns, or re-explaining things you've already decided.

How to use

Claude Code / Cline

Copy this file to .agents/skills/agent-context-file-writer/SKILL.md in your project root.

Then ask:

  • "Use the Agent Context File Writer to create a CLAUDE.md for this project."
  • "Write a .cursorrules file for our Next.js + Prisma + tRPC codebase."

Provide:

  • Tech stack (framework, language, key libraries)
  • Project type (API, frontend app, CLI tool, etc.)
  • Any strong conventions (naming, file structure, testing approach)
  • Anything agents have done wrong in the past

Cursor / Codex

Describe your project and provide any existing README or architecture notes alongside these instructions.

The Prompt / Instructions for the Agent

When asked to write an agent context file, explore the codebase first, then produce the file with all of these sections:

Step 1 — Explore the codebase

Before writing, read:

  • package.json / pyproject.toml / go.mod — to identify the stack
  • Directory structure (top 2 levels) — to understand layout
  • One or two key files — to understand coding style
  • Existing README — for project purpose

Step 2 — Produce the context file

The file must contain all of these sections:


Section 1: Project overview (3–5 sentences)

What the project does, who uses it, and what matters most about it. Not a marketing pitch — a technical brief for an agent.

## Project Overview
SimplyUtils is a multi-tool web app with 72+ browser-based utilities built on React + Express + PostgreSQL.
Most tools run entirely client-side for privacy. The project is deployed on Vercel (frontend) + EC2 (API).

Read the full file on GitHub · 189 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. 10d ago First seen · 189 lines · 45 tokens per session scan A ce4dc067dfdd

Subscribe to this mod's changes

Agent Context File Writer is a skill published in the GitHub repository Notysoty/openagentskills (9 stars, last pushed 26d ago), licensed MIT. It adds 45 tokens to every session and 1,692 once invoked, about $0.0002 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

comprehensive-enrichment

Enrich any person or company from any identifier — email, name, LinkedIn URL, domain, company name, Twitter/X handle. Use when asked to enrich, look up, or research a lead, contact, person, or company.

gooseworks-ai/goose-skills · 53 tokens

create-workflow-diagram

Create FigJam/Miro-style workflow diagrams as high-quality PNG images from plain-text workflow descriptions. Renders beautiful HTML diagrams with connected nodes, arrows, and labels, then screenshots them for sharing.

gooseworks-ai/goose-skills · 45 tokens

data-charts-tako

Search and visualize the world's data - get charts, insights, and embeddable knowledge cards for finance, economics, demographics, sports, and more.

gooseworks-ai/goose-skills · 35 tokens

email-finder-hunter

Email finder and verifier - find emails, verify deliverability, discover companies.

gooseworks-ai/goose-skills · 20 tokens

lead-discovery

Orchestrator that runs first for lead generation requests. Gathers business context via website analysis or questions, identifies competitors, builds ICP, and routes to signal skills with pre-filled inputs.

gooseworks-ai/goose-skills · 41 tokens

meta-ad-scraper

Scrape competitor ads from Meta's Ad Library (Facebook, Instagram, Messenger, Threads, WhatsApp). Search by company name, Facebook Page URL, or keyword. Returns ad creatives, spend estimates, reach, impressions, and campaign details. Use for competitive ad research, messaging analysis, and creative inspiration.

gooseworks-ai/goose-skills · 67 tokens