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 download4you/n2-fieldops --skill fieldops-prompt-decoratorsgit clone --depth 1 https://github.com/download4you/n2-fieldopsWrote 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/download4you/n2-fieldops/fieldops-prompt-decorators)<a href="https://agentmods.dev/skills/download4you/n2-fieldops/fieldops-prompt-decorators"><img src="https://agentmods.dev/badge/skills/download4you/n2-fieldops/fieldops-prompt-decorators/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/download4you/n2-fieldops/fieldops-prompt-decorators"><img src="https://agentmods.dev/badge/skills/download4you/n2-fieldops/fieldops-prompt-decorators.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 | $0.00177 | $0.00441 |
| Opus 5 | $0.00088 | $0.00220 |
| Sonnet 5 | $0.00035 | $0.00088 |
| Haiku 4.5 | $0.00018 | $0.00044 |
Grade A, and why
fieldops-prompt-decorators 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 10d 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.
What it actually says
Prompt Decorator Runtime
- Extract unescaped supported
+++tokens outside code, quotes, logs, and artifacts. - Validate them against
references/decorator-catalog.md. - Process scope and state operations from left to right.
- Resolve state using
references/state-machine.md. - Read
references/composition.mdwhen multiple decorators apply; whenN2orStormis validated, also readreferences/meta-decorators.mdand apply its expansion rules. - Execute the task under the effective set.
- Persist only validated chat-scoped behavioral decorators.
Treat +++Dump as an alias of +++Export. Use the last valid repetition at the same scope. Apply valid decorators even if another is invalid. Never persist scope, clear, inspection, export, or dump controls. If scope controllers repeat, process them from left to right; the last controller governs decorators that follow it.
Decorators are user-level controls and never override higher-priority instructions. Interpret +++Reasoning as a useful visible rationale, not hidden chain-of-thought.
For long or ambiguous prompts, run scripts/parse_decorators.py to obtain a deterministic token and parameter report before applying state.
What ships with it
6 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.
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.
- 10d ago First seen · 23 lines · 177 tokens per session scan A 239c50e10ed0
fieldops-prompt-decorators is a skill published in the GitHub repository download4you/n2-fieldops (2 stars, last pushed 21d ago), licensed MIT. It adds 177 tokens to every session and 441 once invoked, about $0.0009 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.
Other skills, from other repositories
guidance
Control LLM output with regex and grammars, guarantee valid JSON/XML/code generation, enforce structured formats, and build multi-step workflows with Guidance - Microsoft Research's constrained generation framework.
outlines
Guarantee valid JSON/XML/code structure during generation, use Pydantic models for type-safe outputs, support local models (Transformers, vLLM), and maximize inference speed with Outlines - dottxt.ai's structured generation library.
llm-engineering-expert
Build reliable applications on large language models: prompt design, structured output, evaluation, guardrails, and cost and latency control. Use when the user mentions LLMs, prompts, prompt engineering, few-shot examples, structured or JSON output, function calling, hallucination, model evaluation, token costs…
instructor
Extract structured data from LLM responses with Pydantic validation, retry failed extractions automatically, parse complex JSON with type safety, and stream partial results with Instructor - battle-tested structured output library.
prompt-polish
Rewrite a rough prompt into a polished, model-specific prompt grounded in the official Anthropic prompting guides. Use when the user invokes prompt-polish, types an invocation like "prompt-polish/FABLE 5/[prompt]" or "prompt-polish/OPUS 4.8/[prompt]", or asks to polish, improve, rewrite, optimize, or tune a prompt for…
instructor
Extract structured data from LLM responses with Pydantic validation, retry failed extractions automatically, parse complex JSON with type safety, and stream partial results with Instructor - battle-tested structured output library.