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 lukas-grigis/ralphctl --skill ralphctl-humanizergit clone --depth 1 https://github.com/lukas-grigis/ralphctlWrote 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/lukas-grigis/ralphctl/ralphctl-humanizer)<a href="https://agentmods.dev/skills/lukas-grigis/ralphctl/ralphctl-humanizer"><img src="https://agentmods.dev/badge/skills/lukas-grigis/ralphctl/ralphctl-humanizer/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/lukas-grigis/ralphctl/ralphctl-humanizer"><img src="https://agentmods.dev/badge/skills/lukas-grigis/ralphctl/ralphctl-humanizer.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 | $0.00100 | $0.01745 |
| Opus 5.5 | $0.00040 | $0.00698 |
| Sonnet 5.5 | $0.00020 | $0.00349 |
| Haiku 4.5 | $0.00010 | $0.00175 |
Grade A, and why
ralphctl-humanizer 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 — 138 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Humanizer
Concept from blader/humanizer (MIT), which builds on Wikipedia's "Signs of AI writing" guide. The pattern catalogue below is written fresh for ralphctl, not copied. Adapted for ralphctl's harness contract.
Generated prose defaults to whatever suits the most readers, so the same safe moves recur in every text. Someone writing for a particular reader makes particular choices. This skill strips the defaults and keeps the content.
How this runs here
- Apply it while writing the prose your output signal carries. The signal gets only the final text — no draft, no list of patterns found, no commentary about the edit.
- The prompt's output contract wins: keep its required headings, sections, field formats, and literal values. Leave code, commands, paths, identifiers, and link targets exactly as they are.
- Add nothing. No fact, name, number, date, or claim that is not in your source material. If a sentence only works with a detail you don't have, simplify the sentence instead.
When this applies
- Create PR — the title and the description body.
- Refine — the prose around the requirements. Plain wording never costs a criterion its precision; a testable predicate stays testable.
Method
- Spot the patterns. Go through the full draft and mark each pattern listed below. They also show up across sentences and paragraphs: a contrast spread over two sentences counts, and so does every section ending on an identical wrap-up line.
- Rewrite each point plainly. State it directly. When a paragraph is awkward, restructure it from its central point instead of patching phrases. Let sentence length vary.
- Check the result. Nothing added, nothing lost. Then look once more for the tells that survive a rewrite most often: contrasts, closers, threes, dashes, and bold labels.
Patterns, strongest first
Staging instead of saying
- Contrast with a claim nobody made. "This isn't just X — it's Y", "rather than X", a "No, it's not…" sentence followed by the real point, a trailing "— no X needed". The negative half inflates the positive one. A contrast earns its place if it fixes a misconception your reader really has, or if each side tells them something.
- Closers that restate. A last short line repeating the paragraph ("That's the whole point."), a string of fragments for drama, emphasis by capitals or dotted words. Cut it unless it adds a fact.
- Borrowed depth. "At its heart", "the real question is", "X is the currency of Y". Drop the aphorism and state the concrete point.
- Run-ups. Announcing what comes next ("Here's the thing", "Let's walk through it", "Quick note"). Start with the content.
- Answering no one. "To be clear", "This doesn't mean", "You might think". Remove the defence unless the objection is real in context.
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 First seen · 138 lines · 100 tokens per session scan A a62b509391de
ralphctl-humanizer is a skill published in the GitHub repository lukas-grigis/ralphctl (24 stars, last pushed today), licensed MIT. It adds 100 tokens to every session and 1,745 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 2026-10-18.
Other skills, from other repositories
save-learning
Saves user instructions as persistent learnings for future sessions. Use when the user says 'remember this', 'always do X', 'from now on', 'never do Y', or gives any instruction they want persisted across sessions. Proactively suggest when the user states a preference, convention, or rule they clearly want followed in…
review
Review local code changes for bugs, regressions, missing tests, and pragmatic improvements. Use when the user asks to review the current changes from git status, or to review a specific backlog task by id such as task-65 or TASK-65. Also trigger when the user says things like "review", "review current changes", "check…
web-access
A method for handling difficult web tasks across search, page fetching, and a real browser. It covers sites that need login sessions, dynamic pages, anti-bot handling, or exploration before their structure is understood.
skill-creator
A skill for creating or improving reusable instructions for an agent. It covers capturing the intended workflow, writing a draft, testing it, and refining its trigger description.
repo
Repository operating rules for verified Mythos edits.
ce-work
Execute a plan or concrete work prompt end-to-end. Use when implementing from docs/plans, a spec path, or a clear build request; use ce-debug for open-ended bugs.