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.
curl -O https://raw.githubusercontent.com/reem-sab/tech-writer-prompts/main/AGENTS.mdgit clone --depth 1 https://github.com/reem-sab/tech-writer-promptsWrote 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.
[](https://agentmods.dev/instructions/reem-sab/tech-writer-prompts/agents-md)<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.
<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>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 | $0.00761 | $0.00761 |
| Opus 5.5 | $0.00304 | $0.00304 |
| Sonnet 5.5 | $0.00152 | $0.00152 |
| Haiku 4.5 | $0.00076 | $0.00076 |
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 2mo 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.
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 frontmatterinputs, and vice versa.twp lintenforces this. - Tags are a closed set. Only
docs-review, api, agents, release, localization, style, iaare 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.
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.
- 2mo ago First seen · 67 lines · 761 tokens per session scan A 19639e1a242e
tech-writer-prompts AGENTS.md is an instructions file published in the GitHub repository reem-sab/tech-writer-prompts (4 stars, last pushed 2mo ago), licensed MIT. It adds 761 tokens to every session, about $0.0030 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 2026-08-31.
tech-writer-prompts AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| tech-writer-prompts AGENTS.mdreem-sab/tech-writer-prompts | Instructions file | 4 | 2mo ago | MIT | A | 761 | Codex, OpenCode |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | today | MIT | A | 7,461 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 5,516 | GitHub Copilot |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | today | MIT | A | 4,680 | Codex, OpenCode |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 3,093 | GitHub Copilot |
| deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness | Instructions file | 275k | 3d ago | MIT | A | 4,313 | Codex, OpenCode |