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 noizu-labs-ml/NoizuPromptLingo --skill prompt_engineer_skillgit clone --depth 1 https://github.com/noizu-labs-ml/NoizuPromptLingoWrote 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/noizu-labs-ml/noizupromptlingo/prompt_engineer_skill)<a href="https://agentmods.dev/skills/noizu-labs-ml/noizupromptlingo/prompt_engineer_skill"><img src="https://agentmods.dev/badge/skills/noizu-labs-ml/noizupromptlingo/prompt_engineer_skill/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/noizu-labs-ml/noizupromptlingo/prompt_engineer_skill"><img src="https://agentmods.dev/badge/skills/noizu-labs-ml/noizupromptlingo/prompt_engineer_skill.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 | $0.00230 | $0.02457 |
| Opus 5 | $0.00115 | $0.01229 |
| Sonnet 5 | $0.00046 | $0.00491 |
| Haiku 4.5 | $0.00023 | $0.00246 |
Grade A, and why
prompt-engineer 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 3d 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 — 125 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Prompt Engineer
Single skill for the full prompt lifecycle: author → audit → compress/restyle → evaluate → tune → harden, with first-class Noizu Prompt Lingua (NPL) support and a vendored research corpus (arXiv-grade papers with page-anchored digests) backing its security and optimization guidance.
Overview
- Author prompts from natural-language intent — freeform or formal [email protected] syntax — assembling the minimal syntax preamble a target system needs (via the NPL MCP service:
NPLLoad/NPLSpec). - Audit existing prompts (freeform,
<npl-*>blocks,⌜NPL@…⌝fenced) for structural and semantic correctness; fix in place. - Compress and restyle prompts against explicit token budgets on a 0–5 compactness scale, ledgering every dropped fact, and transforming between equivalent-behavior formats (YAML meta-prompt, NPL element set, checklist, pointer-index, shorthand).
- Evaluate prompt variants against an eval corpus (rubric + dataset), promoting the best via the
.promptfile-mode convention (spec file, variants dir, best-eval symlink/pin). - Tune for the target model — prompt-shape preferences, sampling hyperparameters, and reasoning/thinking budgets differ per model family; adapt rather than assume.
- Harden against adversarial input — threat-model the prompt surface, recognize injection and poisoning patterns, and apply layered defenses drawn from the vendored research corpus.
Core Philosophy
- Behavior is the invariant. Compression, restyling, and tuning may change everything except required behavior; every transformation is checked against the declared requirements.
- Loss is ledgered, never silent. Anything dropped or weakened during compression is recorded — what, why, and where it can be recovered.
- Variants are measured, not preferred. Taste loses to the eval corpus; the best-eval variant is promoted, and the baseline is retained forever.
- Structure beats cleverness. Deliberate syntax (NPL families, delimiters, instruction hierarchy) is the primary defense against ambiguity and injection alike.
- Claims cite the corpus. Security and optimization recommendations point at the vendored papers with page anchors, not folklore.
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.
- 3d ago First seen · 125 lines · 230 tokens per session scan A b24670e9b270
prompt-engineer is a skill published in the GitHub repository noizu-labs-ml/NoizuPromptLingo (13 stars, last pushed yesterday), licensed MIT. It adds 230 tokens to every session and 2,457 once invoked, about $0.0011 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 2026-09-08.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
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…
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…
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…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…