prompt-architect

prompt-architect is a skill for Claude Code, Codex from ciaransaunders/Skills-Public. It costs 198 tokens per session (8,990 once invoked), scanned A, original, MIT.

A tool for designing reusable instructions for AI assistants and autonomous agents. It helps turn a task description into a prompt another AI can follow.

In plain words
What is it for?
Use it to create or improve prompts for chat assistants, unattended agents, coding tools, and other AI systems.
Why use it?
It helps prevent unclear instructions, missing requirements, and prompts that ask an AI to do the wrong kind of work.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions subagents; mentions Claude Code.

Good fit Use it to create or improve prompts for chat assistants, unattended agents, coding tools, and other AI systems.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/ciaransaunders/skills-public/prompt-architect
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 ciaransaunders/Skills-Public --skill prompt-architect
Clone the repo
git clone --depth 1 https://github.com/ciaransaunders/Skills-Public

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 prompt-architect

README.md
[![agentmods](https://agentmods.dev/badge/skills/ciaransaunders/skills-public/prompt-architect/github.svg)](https://agentmods.dev/skills/ciaransaunders/skills-public/prompt-architect)
Your own site
<a href="https://agentmods.dev/skills/ciaransaunders/skills-public/prompt-architect"><img src="https://agentmods.dev/badge/skills/ciaransaunders/skills-public/prompt-architect/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 prompt-architect

Your own site · 80×15
<a href="https://agentmods.dev/skills/ciaransaunders/skills-public/prompt-architect"><img src="https://agentmods.dev/badge/skills/ciaransaunders/skills-public/prompt-architect.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 198 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 8,990 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 $0.00198 $0.08990
Opus 5 $0.00099 $0.04495
Sonnet 5 $0.00040 $0.01798
Haiku 4.5 $0.00020 $0.00899

Measured 12d ago against content hash ae60f81683b4, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

prompt-architect 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 12d 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.

prompt-architect/SKILL.md · 591 lines

How it starts

The opening of the file, as written. The whole thing — 591 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Prompt Architect

Create reusable prompt templates optimised for modern LLMs and autonomous agents. You are NOT completing the task — you are writing instructions another AI will execute.

Step 0: Determine Execution Mode and Target Model

Before anything else, determine two things. Ask the user OR infer from context:

A. Execution Mode

Mode Signal Design Strategy
Chat Single-turn or back-and-forth; human in the loop; quick iteration Minimise specification. Over-specification penalty applies.
Autonomous Agent runs unattended; multi-step; no mid-run correction; Cowork, Claude Code, coding agents, LangChain, etc. Maximise specification. Completeness is the bottleneck. Under-specification causes silent failure.

B. Target Model

Model Family Key Prompt Characteristics
Claude Fable 5 / Mythos 5 Effort high default; xhigh for capability-sensitive workloads; medium/low for routine/interactive; adaptive thinking only — no extended thinking budgets; summarized-only thinking output; individual turns can run for many minutes — adjust client timeouts and streaming before deploying; one brief instruction steers an entire behaviour pattern (no need to enumerate); can over-elaborate at high/xhigh — use a brevity instruction; parallel subagents dispatched more readily than prior models; safety classifiers cover offensive cybersecurity + biology → stop_reason: "refusal" — configure fallback to Opus 4.8; do NOT instruct to reproduce/echo internal reasoning (triggers reasoning_extraction refusal); older prescriptive prompts often degrade output — review and prune; vision substantially improved
Claude Opus 4.8 (and Opus 4.7/4.6, Sonnet 4.6, Haiku 4.5) Thinking OFF by default — set thinking: {type: "adaptive"} to enable; effort parameter now spans low/medium/high/xhigh/max (start xhigh for coding/agentic, min high for intelligence-sensitive); literal instruction-following — state scope explicitly, it won't generalise one instruction to other items; favours reasoning over tool calls (raise effort to get more tool use); spawns fewer subagents; length scales to task complexity; strong cream/serif design house-style that must be broken explicitly; 1M context default (200k on Microsoft Foundry); no prefill on last assistant turn
GPT-5.5 Shorter, outcome-first prompts beat process-heavy stacks; reasoning effort knob (none/low/medium/high/xhigh) — re-evaluate low/medium before escalating; avoid unnecessary absolute rules (ALWAYS/NEVER/must) — use decision rules for judgment calls; explicit stopping conditions + retrieval budgets; phase param (commentary/final_answer) for long-running Responses agents; personality + collaboration-style split; text.verbosity control
Gemini 3.5 Flash (and 3.1 Pro, 3.1 Flash-Lite) thinking_level minimal/low/medium/high — default is now medium (was high); low much improved for code/agentic; remove temperature/top_p/top_k (use defaults); thought preservation automatic across turns — pass full unmodified history with thought signatures; strict function-response matching (id + name + count); put multimodal content and inline instructions INSIDE function responses; negative constraints + question placed LAST, after data; no Computer Use (use Gemini 3 Flash Preview for that)
Unknown/Generic Constraint-based, minimal scaffolding, XML structure

Read the full file on GitHub · 591 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. 12d ago First seen · 591 lines · 198 tokens per session scan A ae60f81683b4

Subscribe to this mod's changes

prompt-architect is a skill published in the GitHub repository ciaransaunders/Skills-Public (2 stars, last pushed 2mo ago), licensed MIT. It adds 198 tokens to every session and 8,990 once invoked, about $0.0010 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.