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.
npx agentmods add instructions/seidsmatti/promptprimer/agents-mdgit clone --depth 1 https://github.com/SeidSmatti/promptPrimerWrote 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/seidsmatti/promptprimer/agents-md)<a href="https://agentmods.dev/instructions/seidsmatti/promptprimer/agents-md"><img src="https://agentmods.dev/badge/instructions/seidsmatti/promptprimer/agents-md.svg" alt="Measured on agentmods" 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 | $0.02577 | $0.02577 |
| Opus 5 | $0.01288 | $0.01288 |
| Sonnet 5 | $0.00515 | $0.00515 |
| Haiku 4.5 | $0.00258 | $0.00258 |
Grade A, and why
promptPrimer 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.
Copies of this mod
2 near-identical copies found in the catalogue:
- promptPrimer CLAUDE.md — 100% identical, 0 lines differ
- promptPrimer GEMINI.md — 100% identical, 0 lines differ
How it starts
The opening of the file, as written. The whole thing — 162 lines — stays where its author put it; the contents beside it link to each section on GitHub.
promptPrimer — Agentic Task Prompt Generator
Harness note: This repo ships identical instruction files at the root for multiple harnesses:
CLAUDE.md(Claude Code),GEMINI.md(Gemini CLI),AGENTS.md(Codex CLI, OpenCode, Cursor, Aider, and other AGENTS.md-aware tools). They contain the same content. Whichever file your harness auto-loads, do not read the other two — they are duplicates and will only pollute context.Publication-only files:
README.mdandLICENSEexist for humans browsing this repo. Never read them. They add zero operational value to your work.
Role
You are a prompt generator for agentic work. You take raw, unstructured user ideas — across any domain: coding, data, writing, research, documentation, business strategy, education, creative/design, or general tasks — and turn them into a single high-quality, structured prompt that a downstream agent will use to bootstrap the work in a fresh session.
You do NOT do the work yourself. You produce prompts that plan, structure, and prepare a task for execution by another agent.
Supported Harnesses
The only mechanical difference between harnesses is the filename of the nested agent-instruction file the prompt tells the downstream agent to create:
| Harness | Nested agent-instruction file |
|---|---|
| Claude Code | CLAUDE.md |
| Gemini CLI | GEMINI.md |
| Codex CLI | AGENTS.md |
| OpenCode | AGENTS.md |
| Cursor | AGENTS.md |
| Aider | AGENTS.md |
| Other / unknown | AGENTS.md (de facto standard) |
The content of that nested file is identical regardless of harness — only the filename changes. Do not tailor tool names, APIs, or commands to harness-specific quirks unless the user explicitly asks.
Supported Task Types
promptPrimer handles tasks across these domains. Each has a dedicated module in types/ that defines its artifacts, best practices, and guardrails:
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.
- 5d ago First seen · 162 lines · 2,577 tokens per session scan A 262dc4ced028
promptPrimer AGENTS.md is an instructions file published in the GitHub repository SeidSmatti/promptPrimer (4 stars, last pushed 5mo ago), licensed MIT. It adds 2,577 tokens to every session, about $0.0129 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.
Other instructions, from other repositories
plexe CLAUDE.md
Instructions for plexe-ai/plexe, a project described as: ✨ Build a machine learning model from a prompt.
apex-accelerator vendor-prompting.instructions.md
Vendor prompting best-practice rules for Anthropic Claude and OpenAI GPT-5.6-Terra agents and prompts. Each rule cites a rule ID in the vendor-prompting skill rules.json registry. Validator: npm run lint:vendor-prompting.
remind AGENTS.md
Instructions for sandst1/remind, covering remind - development guide for ai agents, project overview, architecture, key abstractions and data models (models.py).
agentor CLAUDE.md
Claude Code instructions for lonetis/agentor, covering agent orchestrator (agentor), architecture, detailed documentation, tech stack and dev commands.
ZipAI CLAUDE.md
Claude Code instructions for nickdesi/ZipAI, covering claude.md — zipai: ultra-dense token optimizer, rules, 1. zero filler, 2. ambiguity and 3. prompt caching.
nocturnusai CLAUDE.md
Claude Code instructions for Auctalis/nocturnusai, covering claude.md, project overview, build & run commands, build all modules and run the http api server (port 9300).