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 shdennlin/agent-plugins --skill prompt-buildergit clone --depth 1 https://github.com/shdennlin/agent-pluginsWrote 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/shdennlin/agent-plugins/prompt-builder)<a href="https://agentmods.dev/skills/shdennlin/agent-plugins/prompt-builder"><img src="https://agentmods.dev/badge/skills/shdennlin/agent-plugins/prompt-builder/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/shdennlin/agent-plugins/prompt-builder"><img src="https://agentmods.dev/badge/skills/shdennlin/agent-plugins/prompt-builder.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 | $0.00067 | $0.01768 |
| Opus 5.5 | $0.00027 | $0.00707 |
| Sonnet 5.5 | $0.00013 | $0.00354 |
| Haiku 4.5 | $0.00007 | $0.00177 |
Grade A, and why
prompt-builder 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.
How it starts
The opening of the file, as written. The whole thing — 148 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Prompt Builder
Build the prompt; never do the work it describes. The deliverable is a block of text the user will carry away (usually into a fresh session after a rewind that wipes this conversation). If the user asks you to also execute it, tell them to paste it after rewinding instead.
Input: the argument — a topic, a messy multi-task request, or an existing draft prompt. Empty input is fine: the conversation is the source material.
Step 1: Detect mode and announce it
- Input reads as an existing prompt draft (already imperative/structured) → Critique mode.
- The session has real history relevant to the request → Context-extract mode (the default mid-session).
- Neither → Interview mode.
Announce: "Context-extract mode — mining this conversation." A hybrid is normal: extract what the conversation has, interview only for what it lacks.
Step 2: Gather the five components
Checklist — for each, mark found / asked / deliberately omitted:
| Component | What to capture |
|---|---|
| Role | Only when it changes vocabulary or depth; most repo tasks need none |
| Context | Decisions already made, file paths, commit hashes, prior findings — everything the fresh session cannot know |
| Task | One primary verb per task; normalize typos silently |
| Constraints | What to include/skip/avoid; explicit values, never "something like" — name the thing or explicitly delegate the choice |
| Output format | Files, structure, destination |
- Context-extract: mine the conversation; cite where each item came from.
- Interview: ask only the components this task type needs, ONE question per message, concrete options preferred.
- Critique: map the draft onto the table; gaps become the diagnosis.
Step 3: Decompose multi-task input
- Split into discrete tasks. Keep the user's explicit ordering words ("first"); order the rest by dependency.
- List every ambiguous referent ("corresponding commit", "each section"). Each one either resolves from context (say which evidence) or becomes a question. An ambiguity that changes the work is never shipped inside the final prompt as an embedded assumption — it gets asked in Step 4.
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.
- 12d ago Changed · +29 lines 144e537c9fc5
- 1mo ago First seen · 119 lines · 67 tokens per session scan A cbd44ef8a334
prompt-builder is a skill published in the GitHub repository shdennlin/agent-plugins (2 stars, last pushed today), licensed MIT. It adds 67 tokens to every session and 1,768 once invoked, about $0.0003 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 2026-09-11.
Other skills, from other repositories
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…