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 ReachRobin/skills --skill cringe-translatorgit clone --depth 1 https://github.com/ReachRobin/skillsWrote 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/reachrobin/skills/cringe-translator)<a href="https://agentmods.dev/skills/reachrobin/skills/cringe-translator"><img src="https://agentmods.dev/badge/skills/reachrobin/skills/cringe-translator/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/reachrobin/skills/cringe-translator"><img src="https://agentmods.dev/badge/skills/reachrobin/skills/cringe-translator.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 | $0.00034 | $0.00744 |
| Opus 5.5 | $0.00014 | $0.00298 |
| Sonnet 5.5 | $0.00007 | $0.00149 |
| Haiku 4.5 | $0.00003 | $0.00074 |
Grade A, and why
cringe-translator 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 2mo 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 — 68 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Cringe Translator
Everyone gets cold LinkedIn outreach. Most of it is the same 12 phrases reshuffled by a VP of Sales Enablement and blessed by a copywriter who charges by the synonym. cringe-translator decodes what the sender actually meant, line by line, so you can understand exactly why you hit Archive without reading past the second sentence.
Inputs
A LinkedIn DM, cold email, or LinkedIn post. Pasted as plain text.
Output
A line-by-line translation. Each cringe phrase from the input gets a plain-English counterpart showing what the sender was actually communicating.
Format:
"Original phrase" -> "What it means."
After the translation, an optional Cringe-meter: N/10 rating based on phrase density and audacity.
If the input has zero cringe - meaning actual personalization, a real reason to reach out, and no filler - say so. Don't manufacture critique where none is warranted. (This will happen approximately never.)
Known patterns to decode
False personalization
"I came across your profile" -> "Your job title matches a filter." "Saw you're a thought leader in the space" -> "I scraped your last 3 posts." "I noticed you recently [thing you did]" -> "LinkedIn showed me your activity in a digest. I did not 'notice' anything."
Jargon as credibility
"We help companies like yours drive value at scale" -> "I have no idea what problem you have. Neither does my manager." "Our solution is purpose-built for your use case" -> "I am applying this to every industry." "We're in the same space" -> "We are both on LinkedIn."
Fake humility / fake brevity
"Quick question" -> "It is not a question. It is a pitch." "Just wanted to reach out" -> "My CRM told me to." "I'll keep this short" -> "I won't."
Faux urgency
"We're seeing strong adoption in your vertical" -> "Someone in a loosely adjacent industry signed up." "I'd hate for you to miss out on this" -> "This is a standard template. Nothing is expiring."
Passive-aggressive breakup messages
"Just bumping this up in case it got buried" -> "You ignored me and I'm pretending that's a logistics issue." "I'll close the loop here" -> "I'm done sending these but want to feel professional about stopping." "Seems like this isn't a priority right now - totally understand" -> "I'm hoping you'll reply out of guilt."
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.
- 2mo ago First seen · 68 lines · 34 tokens per session scan A 1d675538cff0
cringe-translator is a skill published in the GitHub repository ReachRobin/skills (2 stars, last pushed 5mo ago), licensed MIT. It adds 34 tokens to every session and 744 once invoked, about $0.0001 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.
cringe-translator compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| cringe-translatorReachRobin/skills | Skill | 2 | 5mo ago | MIT | A | 34 | Claude Code |
| writingMadaraUchiha-314/the-loop | Skill | 8 | 9d ago | MIT | A | 112 | Claude Code |
| multaialo-exp/multai | Skill | 4 | 25d ago | none | A | 415 | Claude Code |
| comparatoralo-exp/multai | Skill | 4 | 25d ago | none | A | 214 | Claude Code |
| consolidatoralo-exp/multai | Skill | 4 | 25d ago | none | A | 146 | Claude Code |
| landscape-researcheralo-exp/multai | Skill | 4 | 25d ago | none | A | 208 | Claude Code |
| solution-researcheralo-exp/multai | Skill | 4 | 25d ago | none | A | 204 | Claude Code |