Claude profanity

Skill oliverbenns/claude-profanity/claude-profanity

Search through Claude Code conversation history for prompts containing profanity. Use when the user wants to find or audit profanity in their past Claude conversations.

Install

npx -y skills add oliverbenns/claude-profanity --skill claude-profanity

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

2 things to look at

no licenseNo license file was found in the repository. Code published without one is not open source by default, so using it at work is a question for whoever answers licensing questions where you are.
1 stars1 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

What its author says it does

Copied from the file, not written here

Search through Claude Code conversation history for prompts containing profanity. Use when the user wants to find or audit profanity in their past Claude conversations.

The file declares its own license as MIT. That is the author’s claim about this one file, and it is not the same thing as the license GitHub reports for the repository, which is listed with the other numbers below.

SKILL.md

2.6 KB, 553 tokens by cl100k_base, as published. Nobody here has run it

Profanity Check Skill

Search through the user's Claude Code conversation history and project files for prompts that contain profanity.

Data sources to search

History file: ~/.claude/history.jsonl - contains all conversation prompts across projects
Project session files: ~/.claude/projects/*/ - contains detailed session data

Default profanity word list

Search for these words (case-insensitive, word-boundary matched):

fuck, shit, damn, ass, bitch, crap, bastard, dick, piss, bullshit, wtf, stfu, goddamn, asshole, dumbass, dipshit, shitty, fucking, fucked, bitchy, crappy, dammit, hell

If the user passed additional words via $ARGUMENTS, add those to the search list as well.

Scope

If the user specifies a project name (e.g. "check profanity in my-app"), filter results to only entries whose project field contains that project name.
If the user says "this project" or "current project", filter results to entries whose project field matches the current working directory.
Otherwise, search across all projects (global).

Instructions

Use Grep to search ~/.claude/history.jsonl for the profanity word list (case-insensitive, word-boundary matching). Each line in this file is a JSON object with a display field containing the user's prompt, plus project and sessionId fields.
If a project scope was specified, filter results to only matching entries.
For each match found:
- Extract the display field (the user's actual prompt text)
- Extract the project field to identify which project it came from
- Identify which profane word(s) were matched
Present results in a markdown table with columns:
- # (row number)
- Project (short project name extracted from the path, e.g. bcb-apps from /Users/oliver/Code/bcb-apps)
- Prompt (the user's message, with the profane word(s) bolded)
- Word(s) (which profane words were found)
End with a brief summary: total count, most-used word, which project had the most matches.

Important

Only report on USER prompts/messages, never on assistant responses.
The history.jsonl file contains one JSON object per line with display as the prompt text.
Keep the output concise and fun - this is a lighthearted audit.

What ships with it

Read from the repository

Just SKILL.md. No reference files, no scripts.