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 Devdannnny/chisel --skill prompt-architectgit clone --depth 1 https://github.com/Devdannnny/chiselWrote 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/devdannnny/chisel/prompt-architect)<a href="https://agentmods.dev/skills/devdannnny/chisel/prompt-architect"><img src="https://agentmods.dev/badge/skills/devdannnny/chisel/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.
<a href="https://agentmods.dev/skills/devdannnny/chisel/prompt-architect"><img src="https://agentmods.dev/badge/skills/devdannnny/chisel/prompt-architect.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 | $0.00156 | $0.02049 |
| Opus 5.5 | $0.00062 | $0.00820 |
| Sonnet 5.5 | $0.00031 | $0.00410 |
| Haiku 4.5 | $0.00016 | $0.00205 |
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 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 — 192 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Prompt Architect
This skill turns a rough human prompt into a professionally structured one using a single, scalable framework called the Prompt Architecture Standard (PAS).
The same framework works for a non-technical request ("write me a birthday speech") and a complex technical/agentic task ("refactor this service, don't touch the API"). It scales by adding or dropping sections — the structure never changes, only the depth.
The job
Given a rough prompt, produce a clean structured prompt. Do not execute the task in the rough prompt — restructure it. The deliverable is a better prompt, not the answer to it.
Workflow
Follow these steps in order.
1. Extract intent
Read the rough prompt fully. Identify, in your own notes: the real goal, the implied audience/executor (a human? an AI agent? a coding tool?), any constraints stated or implied, and any concrete details that must be preserved verbatim (file names, values, names, URLs, exact wording).
2. Classify the task
Pick one:
- Simple / non-technical — a single creative or informational ask (write, summarize, explain, brainstorm). Use Tier 1 sections.
- Technical / agentic — a multi-step task with constraints, a defined target, or code/file changes. Use Tier 1 + Tier 2 sections.
- High-stakes / complex — agentic work where mistakes are costly, scope creep is a risk, or output must be auditable. Use all tiers.
When in doubt, go one tier higher — extra structure rarely hurts.
3. Map content into sections
Place every piece of the rough prompt into the correct PAS section (defined below). Nothing from the original should be silently dropped. If the user listed specific values, statuses, or replacements, preserve them exactly inside the relevant section.
4. Fill gaps and flag assumptions
Rough prompts are usually missing a role, an explicit output format, or success criteria. Add sensible defaults, but never invent constraints the user didn't imply. Mark anything you inferred so the user can correct it.
What ships with it
1 file 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.
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 · 192 lines · 156 tokens per session scan A baec6b698be2
prompt-architect is a skill published in the GitHub repository Devdannnny/chisel (3 stars, last pushed 3mo ago), licensed MIT. It adds 156 tokens to every session and 2,049 once invoked, about $0.0006 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.
Other skills, from other repositories
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.
ai-wrapper-product
Expert in building products that wrap AI APIs (OpenAI, Anthropic, etc. ) into focused tools people will pay for. Not just "ChatGPT but different" - products that solve specific problems with AI.
ai-product
Every product will be AI-powered. The question is whether you'll build it right or ship a demo that falls apart in production.
kermt-pretrain-scratch
Pretrain a fresh KERMT model from scratch on a user-provided corpus. Builds a new vocabulary from the corpus, instantiates the model architecture from defaults, and launches pretrainddp.py inside the kermt container (detached for long runs). Unlike kermt-continue-pretrain, no starting checkpoint is loaded — the model…
llm-application-dev-ai-assistant
Design conversational assistants with context management, response generation, and LLM integration. Use when building chatbots or planning assistant application architecture.
llm-application-dev-prompt-optimize
Evaluate and improve LLM prompts using examples, structured instructions, and measured comparisons. Use when refining prompt reliability, output quality, or model-specific behavior.