tech-writer-prompts: Instructions file for Codex

AGENTS.md

tech-writer-prompts AGENTS.md is an instructions file for Codex, OpenCode from reem-sab/tech-writer-prompts. It costs 761 tokens per session, scanned A, original, MIT.

A set of instructions for a tested library of prompts for technical writers. It explains where prompts, documentation, tests, generated files, and the TypeScript command-line tool are stored.

In plain words
What is it for?
Adding or updating writing prompts, documenting their inputs and limits, creating evaluation cases, generating skills, and running the project's checks.
Why use it?
It makes the repository structure clear and requires each prompt to pass its evaluation tests before it is considered finished.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md. Also seen: mentions Claude Code; mentions AGENTS.md.

This is reem-sab/tech-writer-prompts's own configuration. It tells Codex and OpenCode how to work on tech-writer-prompts itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything tech-writer-prompts configures →

Reuse

Borrowing it

Nothing to install: this file belongs to reem-sab/tech-writer-prompts. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/reem-sab/tech-writer-prompts/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/reem-sab/tech-writer-prompts

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 tech-writer-prompts AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/reem-sab/tech-writer-prompts/agents-md/github.svg)](https://agentmods.dev/instructions/reem-sab/tech-writer-prompts/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/reem-sab/tech-writer-prompts/agents-md"><img src="https://agentmods.dev/badge/instructions/reem-sab/tech-writer-prompts/agents-md/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 tech-writer-prompts AGENTS.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/reem-sab/tech-writer-prompts/agents-md"><img src="https://agentmods.dev/badge/instructions/reem-sab/tech-writer-prompts/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 761 This file is loaded in full into every session.
When invoked 761 The same file — it is already loaded in full.
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 $0.00761 $0.00761
Opus 5 $0.00380 $0.00380
Sonnet 5 $0.00152 $0.00152
Haiku 4.5 $0.00076 $0.00076

Measured 9d ago against content hash 19639e1a242e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

tech-writer-prompts 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 9d 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 · 67 lines

How it starts

The opening of the file, as written. The whole thing — 67 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

Guidance for coding agents (Claude Code, Cursor, and similar) working in this repository.

What this repo is

tech-writer-prompts is a tested library of prompts for technical writers. Each prompt lives in prompts/<slug>/ and ships with its documentation and its tests. The core invariant of this project — the thing that makes it worth existing — is: a prompt is not done until its evals pass. Treat that as a hard rule, not a preference.

Repository map

Path What it is
prompts/<slug>/prompt.md The prompt, with YAML frontmatter.
prompts/<slug>/README.md What it does, inputs, example, limitations.
prompts/<slug>/evals.json 3–5 test cases.
prompts/<slug>/SKILL.md Generated. Do not hand-edit — run twp gen-skills.
prompts/<slug>/badge.json Generated by twp eval. Do not hand-edit.
prompts/SCHEMA.md Human-readable frontmatter schema + tag vocabulary.
runner/src/ The twp CLI (TypeScript). schema.ts is the authoritative schema.
site/build-data.mjs Walks prompts/ and emits site/prompts.json for the dashboard.
evals/results.json Generated by twp eval.

Common tasks

Add or edit a prompt. Follow CONTRIBUTING.md. After any change to a prompt.md body, bump its version, re-run its evals, and regenerate derived files:

npm run build
node runner/dist/cli.js lint <slug>
node runner/dist/cli.js eval <slug> --judge      # needs ANTHROPIC_API_KEY
node runner/dist/cli.js gen-skills
node site/build-data.mjs

Do not hand-edit any file marked Generated above — change its source and regenerate. prompts/<slug>/SKILL.md comes from prompt.md + README.md; site/prompts.json, badge.json, and evals/results.json come from the runner.

Rules that are easy to get wrong

  • Placeholders and inputs must match. Every {{PLACEHOLDER}} in a prompt body must have a matching key in frontmatter inputs, and vice versa. twp lint enforces this.
  • Tags are a closed set. Only docs-review, api, agents, release, localization, style, ia are valid. The schema rejects others.
  • Evals are the contract. If you change what a prompt outputs, the evals must still pass — or you must update them in the same change and explain why in the PR.
  • Respect each prompt's stated Limits. When applying a prompt, don't present its output as more authoritative than the prompt's own Limits section claims.

Read the full file on GitHub · 67 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. 9d ago First seen · 67 lines · 761 tokens per session scan A 19639e1a242e

Subscribe to this mod's changes

tech-writer-prompts AGENTS.md is an instructions file published in the GitHub repository reem-sab/tech-writer-prompts (4 stars, last pushed 10d ago), licensed MIT. It adds 761 tokens to every session, about $0.0038 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

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,153 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,469 tokens

deepseek-harness AGENTS.md

AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.

deepseek-ai/deepseek-harness · 3,735 tokens