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 atretyak1985/swarmery --skill engineering-prompts-and-outputgit clone --depth 1 https://github.com/atretyak1985/swarmeryWrote 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/atretyak1985/swarmery/engineering-prompts-and-output)<a href="https://agentmods.dev/skills/atretyak1985/swarmery/engineering-prompts-and-output"><img src="https://agentmods.dev/badge/skills/atretyak1985/swarmery/engineering-prompts-and-output/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/atretyak1985/swarmery/engineering-prompts-and-output"><img src="https://agentmods.dev/badge/skills/atretyak1985/swarmery/engineering-prompts-and-output.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 | $0.00118 | $0.01362 |
| Opus 5 | $0.00059 | $0.00681 |
| Sonnet 5 | $0.00024 | $0.00272 |
| Haiku 4.5 | $0.00012 | $0.00136 |
Grade A, and why
engineering-prompts-and-output 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 7d 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 — 100 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Engineering Prompts and Output
Overview
Best-practice reference for the prompt-and-output layer: explicit criteria in system prompts, few-shot construction, schema-enforced output, validation/retry, batch processing, and review pipelines. Each reference module states the correct pattern, the named anti-patterns, and ends with an Audit Checklist of verifiable conditions.
When to use
- Writing or reviewing a system prompt, few-shot set, output schema, or an automated review pipeline
- Debugging: inconsistent verdicts, invalid JSON, false-positive floods, hallucinated values, missed defects on self-review
- Deciding: severity criteria vs confidence filtering,
tool_choicemode for extraction, retry strategy, batch vs real-time
Not for tool interface design itself (use designing-tools-and-mcp) or human-review calibration (use managing-context-reliability).
Quick reference
| Module | Read when the question is about |
|---|---|
references/4-1-system-prompts-with-explicit-criteria.md |
Explicit severity criteria, the false-positive trust problem |
references/4-2-few-shot-prompting.md |
Constructing examples, hallucination reduction, false-positive control |
references/4-3-structured-output-with-tool-use.md |
The three tool_choice modes, what tool_use does not guarantee, schema design |
references/4-4-validation-retry-and-feedback-loops.md |
Retry-with-error-feedback, its limits, schema vs semantic errors |
references/4-5-batch-processing-strategies.md |
Message Batches API, result matching, SLA maths, failure handling |
references/4-6-multi-instance-and-multi-pass-review.md |
Why self-review fails, multi-pass architecture, confidence-based routing |
How to audit
- Match the pipeline under review to modules in the table; read those files.
- Run each module's Audit Checklist item by item against the actual prompts/schemas/code.
- Report every unchecked item as a finding with
file:lineevidence and the module's recommended fix.
What ships with it
7 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.
- checklists.md 7.2 KB
- references/4-1-system-prompts-with-explicit-criteria.md 5.4 KB
- references/4-2-few-shot-prompting.md 7.5 KB
- references/4-3-structured-output-with-tool-use.md 6.8 KB
- references/4-4-validation-retry-and-feedback-loops.md 7.1 KB
- references/4-5-batch-processing-strategies.md 7.6 KB
- references/4-6-multi-instance-and-multi-pass-review.md 8.5 KB
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.
- 7d ago Changed · +36 tokens per session 024c1f941109
- 12d ago First seen · 100 lines · 82 tokens per session scan A 241847911d34
engineering-prompts-and-output is a skill published in the GitHub repository atretyak1985/swarmery (6 stars, last pushed yesterday), licensed Apache-2.0. It adds 118 tokens to every session and 1,362 once invoked, about $0.0006 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
gws-modelarmor-create-template
Google Model Armor: Create a new Model Armor template.
gws-modelarmor-sanitize-prompt
Google Model Armor: Sanitize a user prompt through a Model Armor template.
gws-modelarmor
Google Model Armor: Filter user-generated content for safety.
prompt-engineering
Provides workflows to write, debug, and optimize prompts for LLMs, including few-shot example selection, chain-of-thought structuring, system prompt design, and template composition. Use when the user asks to write or improve a prompt, wants help with few-shot examples, chain-of-thought, system prompts, prompt…
langchain4j-tool-function-calling-patterns
Provides and generates LangChain4j tool and function calling patterns: annotates methods as tools with @Tool, configures tool executors, registers tools with AiServices, validates tool parameters, and handles tool execution errors. Use when building AI agents that call tools, define function specifications, manage…
cloudflare-workers-ai
Cloudflare Workers AI for serverless GPU inference. Use for LLMs, text/image generation, embeddings, or encountering AIERROR, rate limits, token exceeded errors.