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 ruthless-editorgit 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/ruthless-editor)<a href="https://agentmods.dev/skills/ralfyishere/rules-with-receipts/ruthless-editor"><img src="https://agentmods.dev/badge/skills/ralfyishere/rules-with-receipts/ruthless-editor/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/ruthless-editor"><img src="https://agentmods.dev/badge/skills/ralfyishere/rules-with-receipts/ruthless-editor.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 | $0.00093 | $0.01315 |
| Opus 5 | $0.00046 | $0.00658 |
| Sonnet 5 | $0.00019 | $0.00263 |
| Haiku 4.5 | $0.00009 | $0.00131 |
Grade A, and why
Ruthless Editor 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 9d 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 — 82 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Ruthless Editor
Purpose
Cut everything that doesn't serve the reader; strengthen everything that remains. Most drafts are 20–40% padding: throat-clearing openings, repeated points, hedges stacked on hedges, abstract nouns where verbs belong. The reader pays for every word — this skill makes each one earn its place. Ruthless means aggressive about words, conservative about meaning: nothing true gets cut into falsehood.
When to use this skill
- Before delivering any prose artifact someone will read under time pressure: emails, memos, docs, summaries, blurbs.
- On explicit request: "tighten this", "make it punchier", "this is too long".
- On your own outputs: any answer running long, any report, any explanation — you are your own first editing client.
- On prompts: instruction text especially rewards precision (every ambiguous word is a behavior bug).
When NOT to use this skill
- Legal, contractual, or compliance text where redundancy and qualifier stacking may be deliberate.
- Voice-preserving edits: if the user wants their style kept, edit for errors and clarity only — don't transplant your voice.
- Substance problems: editing can't fix a wrong argument. Fix content first (
adversarial-verify), polish second. - Don't strip calibration: uncertainty labels from
verification-disciplineare content, not fluff.
Operating procedure
Run four passes, in order. On short pieces they collapse into one read; on long ones, keep them separate.
Pass 1 — Structure. Get the skeleton right before touching sentences.
- Lede first: the answer/ask/conclusion goes in the opening lines, not after the buildup. Readers act on the first paragraph.
- One point per paragraph; sections in the reader's priority order, not the order you thought of them.
- Kill the on-ramp: openings like "In today's fast-moving landscape..." or "I wanted to reach out because..." — start where the content starts.
Pass 2 — Cut. Delete without mercy:
- Repetition (the same point in intro, body, and conclusion counts once).
- Filler phrases: "it's worth noting that", "in order to", "the fact that", "basically", "very", "really".
- Hedge stacks: "might possibly perhaps" → pick one, or none if you actually know.
- Explanations of the obvious to this audience; scaffolding sentences that only announce other sentences ("Now let's discuss X").
- Target: 20–40% shorter, unless the draft was already tight.
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.
- 9d ago First seen · 82 lines · 0 tokens per session scan A 48435988ee35
Ruthless Editor is a skill published in the GitHub repository ralfyishere/rules-with-receipts (2 stars, last pushed 1mo ago), licensed MIT. It adds 93 tokens to every session and 1,315 once invoked, about $0.0005 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
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.
frontend-design
A design guide for building polished web interfaces such as pages, dashboards, forms, navigation, and reusable UI components. It covers HTML, CSS, JavaScript, and common frontend frameworks.
alterlab-cobrapy
Build and analyze genome-scale constraint-based metabolic models with COBRApy — flux balance analysis (FBA), flux variability analysis (FVA), gene and reaction knockouts, flux sampling, and SBML model I/O. Use when simulating metabolic networks, predicting growth or knockout phenotypes, or running systems-biology and…
alterlab-depmap
Query the Cancer Dependency Map (DepMap) for cancer cell line gene dependency scores (CRISPR Chronos), drug sensitivity data, and gene effect profiles. Use when identifying cancer-specific genetic vulnerabilities, finding synthetic lethal interactions, checking whether a gene is essential in given cell lines, or…
alterlab-qutip
Simulates open quantum systems with QuTiP, the Quantum Toolbox in Python, solving Lindblad master equations (mesolve), Monte Carlo trajectories (mcsolve), and unitary dynamics (sesolve). Use when studying master-equation or Lindblad dynamics, decoherence, dissipation, quantum optics, cavity QED, or open-system time…