Configurable Phrase Scanner

    1

    Scan local UTF-8 text for user-defined phrases with normalized matching, whole-word boundaries, line and column locations, severity labels, and CI-ready reports.

    $12

    Secure checkout via Stripe

    Money-back guarantee

    Converts to your local currency at checkout

    Security scanned

    Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIDeepSeekDeepSeekMuseMuse+22 more

    Configurable Phrase Scanner

    Example session with this skill installed

    Run the phrase scanner on examples/draft.md with examples/terms.json and show me every match with its line, column and severity.

    • Read your context and instructions
    • Compiled the configurable phrase scanner

    Summary

    Scanned examples/draft.md with the three terms in examples/terms.json. The scan found 3 matches: 1 error, 1 warning and 1 info.

    Command

    python3 scripts/phrase_scanner.py examples/draft.md --terms examples/terms.json
    

    Output (captured from the bundled example, examples/scan.txt)

    examples/draft.md:2:1: info: TODO: TODO
    examples/draft.md:3:22: error: temporary password: temporary password
    examples/draft.md:4:19: warning: needs review: needs review
    

    Each line is path:line:column: severity: phrase: excerpt. Line and column numbers are one-based.

    Next steps

    • Remove the temporary password text on line 3 (severity: error) before sharing the draft.
    • Review the wording flagged on line 4 and resolve the TODO on line 2.
    • In CI, add --fail-on error so the step fails when an error-level phrase is found.

    Connects securely to your tools. The creator never sees your data.

    About this skill

    Scan drafts and repositories for your own review phrases. Get stable line and column references, severity labels, optional context, JSON output, and CI exit codes. Local and read-only by design.

    Includes a Python CLI, configurable JSON vocabulary, 21 tests, synthetic examples, and setup documentation.

    What you get

    • Case-insensitive Unicode-normalized phrase matching, with optional exact case and whole-word boundaries.
    • Deterministic recursive file discovery, extension filters, and repeatable exclusions.
    • One-based line and column locations, severity labels, and configurable context excerpts.
    • Text or JSON reports, per-file size limits, and optional severity-based exit codes for CI.

    Boundaries

    The scanner reads local UTF-8 text only and never edits files. Terms are literal text, not regular expressions. It is a review aid: it does not interpret context or make policy decisions. Malformed vocabularies return status 2; unreadable or oversized files appear in the report as errors.

    Find more skills like this on the Claude Skills Marketplace, the Codex Skills Marketplace and the Gemini Skills Marketplace, or browse Claude Skills for Writing & Content.

    Literal matching only (no regular expressions). UTF-8 text only, with a per-file size limit. It does not interpret context, make policy decisions, or modify files.

    How to use

    1. 1

      Connect your agent to the Agensi MCP

      Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup

    2. 2

      Sign in to Agensi

      Your agent shows a sign-in link. Sign in and click Allow.

    3. 3

      Ask for what you need

      Your agent loads this skill and uses it on your task. It always asks before buying a skill.

    Reviews

    No reviews yet

    Be one of the first to try it. Every listed skill goes through the trust checks below.

    Security scanned

    Checked by our 8-point scan before listing

    Fresh listing

    Recently published to Agensi

    Money-back guarantee

    Doesn't do what its page promises? You get your money back.

    Trust & safety

    Security scan

    Security scan passed 1 day ago

    Software
    Python

    Permissions

    Terminal / Shell
    Read Files
    Write Files
    Listed1 day ago

    What's inside

    Frequently Asked Questions

    It is a Python script that matches your own phrases literally and reports one-based line and column locations with a severity label, so you get a repeatable report. It is a review aid: it does not interpret context or make policy decisions.

    Local UTF-8 text files such as Markdown, plain text, and source files, or whole directories. Use --extensions to limit file types. Files that cannot be read or exceed the per-file size limit (default 2,000,000 bytes) appear in the report as errors.

    Yes. --fail-on never|warning|error returns exit status 1 when a finding meets the selected severity, and --format json gives structured output. A malformed vocabulary returns status 2.

    A Python CLI (scripts/phrase_scanner.py), 21 tests, synthetic examples with captured output, a README, SKILL.md, and a LICENSE.

    No. It reads local UTF-8 files and never edits them. It uses only the Python standard library (Python 3.10 or newer); the tests use pytest.

    Terms are matched as literal text, not regular expressions. The scanner does not interpret context, make policy decisions, or modify files, and it has a per-file size limit (default 2,000,000 bytes, set with --max-bytes).

    New in Writing & Content