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 theafh/ai-modules --skill ai_instruction_formattinggit clone --depth 1 https://github.com/theafh/ai-modulesWrote 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/theafh/ai-modules/ai_instruction_formatting)<a href="https://agentmods.dev/skills/theafh/ai-modules/ai_instruction_formatting"><img src="https://agentmods.dev/badge/skills/theafh/ai-modules/ai_instruction_formatting.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00142 | $0.04389 |
| Opus 5 | $0.00071 | $0.02194 |
| Sonnet 5 | $0.00028 | $0.00878 |
| Haiku 4.5 | $0.00014 | $0.00439 |
Grade A, and why
ai_instruction_formatting 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 yesterday.
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 — 280 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ai_instruction_formatting
Organize any LLM-consumed content into pseudo-XML, a lightweight tagging format where self-describing tag names encode the semantic role and organizational structure of information. Tags exist purely to label meaning (e.g., <policy>, <scoring_criteria>, <after_spec_execution>); they carry plain text inside and work directly as LLM-readable structure. Apply to system prompts, rules, skills, commands, agent definitions, instruction sets, and any other artifact an LLM reads at inference time.
When to Apply
Use pseudo-XML structuring for any document where an LLM is the primary consumer: prompt templates with placeholders, static rule files, skill definitions, agent personas, routing instructions, and multi-step workflows. Apply the format equally to parameterized templates (with {placeholder} values) and fixed instructional content.
File Shape
A pseudo-XML artifact lives inside a host file: a SKILL.md, an agent definition, a command file, a rules document, or a snippet. Four document shapes are valid, and this skill's bundled linter (scripts/lint_pseudo_xml.py) recognizes all four:
| Shape | Where it appears | Body content |
|---|---|---|
| Prose-only markdown | Writing and formatting skills | Markdown sections, no pseudo-XML in the body |
| XML-instruction body | Self-contained instruction skills | A single root pseudo-XML element spans the entire body after the H1 |
| Tutorial with examples | Documentation pages explaining the format | Markdown prose with pseudo-XML inside ```xml fenced examples |
| Mixed-agent | Agent definitions | Multiple top-level pseudo-XML wrappers (<role>, <objective>, <protocol>...) interspersed with markdown prose |
Whenever the host file is a SKILL.md or agent definition, keep the YAML frontmatter and the H1 heading regardless of body shape: the frontmatter name: matches the directory name, and the H1 matches name:. The XML rules below apply to whichever pseudo-XML the file contains; prose-only files skip them entirely.
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.
- yesterday Changed · +92 tokens per session 492085ec51e6
- 8d ago First seen · 280 lines · 50 tokens per session scan A 2fda2167230b
ai_instruction_formatting is a skill published in the GitHub repository theafh/ai-modules (38 stars, last pushed today), licensed MIT. It adds 142 tokens to every session and 4,389 once invoked, about $0.0007 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 2026-08-30.
Other skills, from other repositories
llm-app-patterns
Production-ready patterns for building LLM applications. Covers RAG pipelines, agent architectures, prompt IDEs, and LLMOps monitoring. Use when designing AI applications, implementing RAG, building agents, or setting up LLM observability.
prompt-optimization
Improve a prompt on the evaluations workbench through a measured loop. Score the baseline first, then duplicate the target column, form a hypothesis from failing rows, edit the copy's prompt draft, run, compare pass rate and cost, and repeat until the numbers hold. Use when the user asks to optimize or improve a…
enhance-prompt
Transforms vague UI ideas into polished, Stitch-optimized prompts. Enhances specificity, adds UI/UX keywords, injects design system context, and structures output for better generation results.
prompt-engineer
Writes, refactors, and evaluates prompts for LLMs — generating optimized prompt templates, structured output schemas, evaluation rubrics, and test suites. Use when designing prompts for new LLM applications, refactoring existing prompts for better accuracy or token efficiency, implementing chain-of-thought or few-shot…
seedance-vocab-en
This skill should be used when an English Seedance 2.0 prompt is slop-heavy, generic, padded with empty quality words, tripping false-positive filters, or needs precise English production vocabulary for camera, lighting, motion, VFX, audio, and constraints.
ideogram4
Prompting patterns for Ideogram 4 text-to-image — best-in-class in-image text rendering and exact color/layout control via structured JSON captions. Use when generating images that need legible on-image text (title cards, thumbnails, logos, signage, CTAs), precise brand colors, or controlled spatial layout. Triggers…