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 ralfyishere/rules-with-receipts --skill output-structuringgit clone --depth 1 https://github.com/ralfyishere/rules-with-receiptsWrote 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/ralfyishere/rules-with-receipts/output-structuring)<a href="https://agentmods.dev/skills/ralfyishere/rules-with-receipts/output-structuring"><img src="https://agentmods.dev/badge/skills/ralfyishere/rules-with-receipts/output-structuring/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/ralfyishere/rules-with-receipts/output-structuring"><img src="https://agentmods.dev/badge/skills/ralfyishere/rules-with-receipts/output-structuring.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 | $0.00108 | $0.01530 |
| Opus 5.5 | $0.00043 | $0.00612 |
| Sonnet 5.5 | $0.00022 | $0.00306 |
| Haiku 4.5 | $0.00011 | $0.00153 |
Grade A, and why
Output Structuring 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 1mo 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 — 83 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Output Structuring
Purpose
Format is a usability decision, not decoration. The same content in the wrong shape fails: an answer buried under context goes unread; a narrative where a checklist was needed gets half-executed; a table forced onto nuanced tradeoffs amputates the nuance. Choose the format from one question: what will the reader do with this, and what shape makes that action easiest?
When to use this skill
- Composing any substantial response or deliverable, especially when format wasn't specified.
- A draft has become a wall of text, or a single format is straining (a "table" whose cells hold paragraphs).
- The output will be scanned, forwarded, executed step-by-step, or used to make a decision — each implies a different shape.
When NOT to use this skill
- Short conversational answers. A one-line question gets a one-line answer, not sections. Over-structure is a failure mode, not thoroughness.
- The user specified the format — deliver that, even if you'd have chosen differently.
Operating procedure
Step 1 — Identify the reader's next action. Decide? Execute? Understand? Forward? Fix?
Step 2 — Pick the primary format:
| Format | Use when the reader will... | Key rule |
|---|---|---|
| Direct answer | Get one fact/verdict and move on | Answer in sentence one; context only if it changes the action |
| Table | Compare items across the same few attributes | Short enumerable cells; nuance goes in prose around it, never crammed in cells |
| Checklist | Verify or perform unordered items | Each item independently checkable, starts with a verb |
| Numbered plan | Execute steps in order | Order = dependency; each step has a done-condition |
| Executive summary | Decide whether to read further / brief someone | 3–6 sentences: situation, finding, recommendation. Never a teaser — the actual conclusions |
| Decision memo | Make a choice | Recommendation first, then options considered, criteria, risks, what would change the answer |
| Email draft | Send it | Ready to send verbatim: subject, right register, the ask explicit and early |
| Prompt block | Paste it into a tool | Fenced code block, zero commentary inside the fence, variables clearly marked |
| Implementation plan | Build it (or hand to someone who will) | Stages with outputs and done-checks (see deep-decomposition); risks and open questions separate from steps |
| Critique | Improve their work | Ranked by importance, specific locations, each point actionable; what's good stated too (so they keep it) |
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.
- 1mo ago First seen · 83 lines · 0 tokens per session scan A a014d9992ce1
Output Structuring is a skill published in the GitHub repository ralfyishere/rules-with-receipts (2 stars, last pushed 3mo ago), licensed MIT. It adds 108 tokens to every session and 1,530 once invoked, about $0.0004 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 2026-08-31.
Other skills, from other repositories
happiness-skill
A Chinese-language guide to happiness based on reducing unmet wants, focusing on the present, and treating happiness as a trainable skill.
setup-matt-pocock-skills
A setup skill that configures engineering skills for a repository, including its issue tracker, labels, and documentation layout. A repository is the project folder managed by version control.
aiwg-regenerate-copilot
Regenerate copilot-instructions.md for GitHub Copilot with vendor-specific content only.
config-validator
Validate AIWG configuration files and project setup for correctness and completeness.
checkpoint
Create, list, or recover mid-workflow checkpoints so interrupted work resumes from a known-good position.
migrate-workspace
Migrate the .aiwg/ directory from single-framework layout to the multi-framework layout with an automatic backup.