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 skills add rp1-run/rp1 --skill prompt-writergit clone --depth 1 https://github.com/rp1-run/rp1Wrote 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/skills/rp1-run/rp1/prompt-writer)<a href="https://agentmods.dev/skills/rp1-run/rp1/prompt-writer"><img src="https://agentmods.dev/badge/skills/rp1-run/rp1/prompt-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.
<a href="https://agentmods.dev/skills/rp1-run/rp1/prompt-writer"><img src="https://agentmods.dev/badge/skills/rp1-run/rp1/prompt-writer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00029 | $0.01401 |
| Opus 5.5 | $0.00012 | $0.00560 |
| Sonnet 5.5 | $0.00006 | $0.00280 |
| Haiku 4.5 | $0.00003 | $0.00140 |
Grade A, and why
prompt-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 1mo 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 — 110 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Prompt Writer
Guide for writing maximally terse agent prompts with built-in constitutional governance and epistemic stance. Combines compression-by-default authoring (tersify), governance primitives (constitution), and epistemological foundations (epistemology) into a single progressive-disclosure skill.
When to Use
- Creating new agent specifications or skill prompts
- Writing command/skill prompts with governance built in
- Drafting instruction sets for AI agents
- Applying constitutional or epistemic review to existing prompts
- Running the six-stage prompt pipeline via
/build-prompt
Core Principles
Structure-First: Start with skeleton, not prose. Choose section pattern, fill minimally.
Compression-by-Default: Every word must earn its place. Remove before adding.
Preserve Exactness: Normative language (MUST/SHOULD/MAY), literals, constraints stay verbatim.
Governed-by-Design: Constitutional primitives and epistemic stance are selected upfront, not bolted on.
Skill Files
Reference Layers
| File | Purpose | When to Load |
|---|---|---|
references/tersify.md |
Compression discipline, section patterns, abbreviation policy, style rules, validation checklist | Direct /prompt-writer invocation; prompt-validation pipeline stage |
references/constitution.md |
10 governance primitives (anti-loop, output discipline, role, scope limits, orchestrator purity, error degradation, exploration bounds, anti-bias, truth constraints, transition guards) + four agent-type profiles | Constitutional-checklist pipeline stage; standalone constitutional review |
references/epistemology.md |
Six epistemic stances (Fallibilist Empirical, Interpretivism, Phenomenology, Constructivism, Pragmatism, Compare-Mode) with composable contracts | Epistemic-stance pipeline stage; standalone epistemic review |
references/budget.md |
15% aggregate governance cap, per-stage budget allocations, line classification rules, enforcement protocol | Pipeline execution (Stage 6 budget enforcement); standalone budget review |
What ships with it
12 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- PATTERNS.md 5.3 KB
- pipeline/confidence-schema.md 5.0 KB
- pipeline/constitutional-checklist.md 3.4 KB
- pipeline/epistemic-stance.md 3.8 KB
- pipeline/fallibilist-overlay.md 5.0 KB
- pipeline/popper-patterns.md 11 KB
- pipeline/prompt-validation.md 18 KB
- references/budget.md 1.7 KB
- references/constitution.md 13 KB
- references/epistemology.md 7.7 KB
- references/tersify.md 6.3 KB
- TEMPLATES.md 5.2 KB
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.
- 1mo ago First seen · 110 lines · 29 tokens per session scan A 08062f11e02b
prompt-writer is a skill published in the GitHub repository rp1-run/rp1 (38 stars, last pushed 3d ago), licensed Apache-2.0. It adds 29 tokens to every session and 1,401 once invoked, about $0.0001 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 2026-08-30.
Other skills, from other repositories
pi-prompting
Internal guidance for composing prompts that Pi runs (DeepSeek by default) handle reliably for coding, review, diagnosis, and research tasks.
ai-engineering-toolkit
Overview of six AI engineering workflows: prompt evaluation (8-dimension scoring), context budget planning, RAG pipeline design, agent security audit (65-point checklist), eval harness building, and product sense coaching.
agent-evolution
A guide to making an AI agent improve from its past runs. It covers how to judge results, extract reusable lessons, and decide whether to store them as knowledge, instructions, code, or model training.
post-training-strategy
A guide to choosing and planning ways to improve an AI model after its initial training. It explains when to add knowledge, teach a response format, use trial-and-error training, or use a smaller model to learn from a larger one.
prompt-master
Generates optimized prompts for AI tools. Activates only when the user explicitly asks to write, fix, improve, or adapt a prompt for a specific AI tool (LLM, Cursor, Midjourney, image AI, video AI, coding agents, etc.). Does not activate for general conversation, coding tasks, document writing, or other…
kv-cache-prefix-optimizer
Expert guide for deterministic prompt prefix engineering, KV-cache locking for Gemini 4 Pro / Claude 5.5 / GPT Astra 6, canonical tool sorting, and achieving 90%+ prompt cache hit rates / Panduan ahli rekayasa prefix prompt deterministik, penguncian KV-cache untuk Gemini 4 Pro / Claude 5.5 / GPT Astra 6, pengurutan…