# AI use cases for My Claude Code Mods (YeonwooSung/my-claude-code-mods) Repo: [YeonwooSung/my-claude-code-mods](https://github.com/YeonwooSung/my-claude-code-mods) | Use cases: 4 | Page: https://dedupedai.com/use-cases/yeonwoosung-my-claude-code-mods/ A set of custom Claude Code mods (plugins) that profile sessions, catch context waste and loops, record file history, and support verification and handoff work. This file holds every use case of this repo. Each one starts with a "## " heading and ends with its URL. - Find where a Claude Code session spends time and context: https://dedupedai.com/use-cases/yeonwoosung-my-claude-code-mods/profile-session-time-and-context-waste/ - Find the edit that broke a test and restore the file: https://dedupedai.com/use-cases/yeonwoosung-my-claude-code-mods/find-the-edit-that-broke-a-test/ - Catch agent retry loops before they burn your session: https://dedupedai.com/use-cases/yeonwoosung-my-claude-code-mods/catch-repeated-failure-loops-early/ - Check verification, scope, and decisions before committing: https://dedupedai.com/use-cases/yeonwoosung-my-claude-code-mods/review-agent-changes-before-commit/ ## How to find where a Claude Code session spends time and context with My Claude Code Mods Repo: [YeonwooSung/my-claude-code-mods](https://github.com/YeonwooSung/my-claude-code-mods) | Difficulty: Intermediate | Time: 30 minutes | Basis: From the README Install two analysis mods to see time split by source and flag repeated or wasted context. **Who it is for:** A developer whose Claude Code sessions feel slow or run out of context, and who wants evidence before changing their workflow. **The problem:** Long sessions hide where time goes between model waits, tool calls, subagents, and re-reads, and what fills the context window. **The outcome:** A clearer picture of time and context use per session, with advice on what to change. ### Steps 1. Add the marketplace once with `claude plugin marketplace add YeonwooSung/my-claude-code-mods`. 2. Install both mods with `claude plugin install agent-profiler@my-claude-code-mods --scope user` and `claude plugin install context-inspector@my-claude-code-mods --scope user`. 3. Start a new Claude Code session, or run `/reload-plugins` in an open session, then run `/plugin` to confirm both mods are loaded. 4. Work through a real task, then read the agent-profiler and context-inspector READMEs linked under Mods to learn how to view each report. 5. Optionally export OTLP traces for Jaeger or Tempo, as described in the agent-profiler README. ### Prompt to paste into your agent ```text Using the repo YeonwooSung/my-claude-code-mods, install agent-profiler and context-inspector at user scope, then run a session on . Report where time went (model wait, tools, subagents, re-reads) and which context items were flagged as waste, citing the specific tool calls or files. Verify that every cited item appears in the session output before you finish. ``` ### Caveat The README says Context Inspector lacks session.append on the early-access 2.1.280 build, so use a current Claude Code CLI for full results. Risk, credentials: Profiler traces and context reports can contain session content, so check them before sharing or exporting them to a shared tracing backend. Disclaimer: Third-party repos we don't own or vouch for. AI-generated use cases can be wrong: review everything and run at your own risk. Full text: https://dedupedai.com/disclaimer/ URL: https://dedupedai.com/use-cases/yeonwoosung-my-claude-code-mods/profile-session-time-and-context-waste/ ## How to find the edit that broke a test and restore the file with My Claude Code Mods Repo: [YeonwooSung/my-claude-code-mods](https://github.com/YeonwooSung/my-claude-code-mods) | Difficulty: Intermediate | Time: 30 minutes | Basis: From the README Use Time Machine's step timeline and shadow-git snapshots to locate and undo a breaking edit. **Who it is for:** A developer whose test suite went from passing to failing during an agent session and who needs to know which change caused it. **The problem:** After many tool calls, it is hard to tell which edit introduced a failure or what the files looked like before it. **The outcome:** The specific step that broke the test, the file as it was at an earlier step, and a restored state you can re-test. ### Steps 1. Confirm git is on your PATH (inferred: `git --version`). (inferred, check the README) 2. Add the marketplace with `claude plugin marketplace add YeonwooSung/my-claude-code-mods` if you have not already. 3. Install with `claude plugin install time-machine@my-claude-code-mods --scope user`. 4. Start a new Claude Code session, or run `/reload-plugins`, then run `/plugin` to confirm time-machine is loaded. 5. Open the timeline, view the files as they were before the failing step, and restore that state; then re-run your test command. ### Prompt to paste into your agent ```text In the repo YeonwooSung/my-claude-code-mods, install time-machine at user scope, then after a failing run of identify the tool call that introduced the failure. Output the step number, the file changed, and the restored content for that file. Verify the result by re-running after the restore and reporting pass or fail. ``` ### Caveat The README says Time Machine needs git on your PATH and that its per-test options are ignored on the early-access 2.1.280 build. Risk, credentials: Shadow-git snapshots store file states, so any secrets in tracked files may be captured in the recorder store. Disclaimer: Third-party repos we don't own or vouch for. AI-generated use cases can be wrong: review everything and run at your own risk. Full text: https://dedupedai.com/disclaimer/ URL: https://dedupedai.com/use-cases/yeonwoosung-my-claude-code-mods/find-the-edit-that-broke-a-test/ ## How to catch agent retry loops before they burn your session with My Claude Code Mods Repo: [YeonwooSung/my-claude-code-mods](https://github.com/YeonwooSung/my-claude-code-mods) | Difficulty: Intermediate | Time: 15 minutes | Basis: From the README Detect repeated Bash failures and edit or retry cycles with evidence and investigation prompts. **Who it is for:** A developer who notices an agent retrying the same failing command or edit over and over, and wants it flagged with proof. **The problem:** Retry cycles can run for a long time before anyone notices the agent is stuck. **The outcome:** A flagged loop with its evidence, an investigation prompt to break the cycle, and a bounded history of past cases. ### Steps 1. Add the marketplace with `claude plugin marketplace add YeonwooSung/my-claude-code-mods` if you have not already. 2. Install with `claude plugin install loop-detective@my-claude-code-mods --scope user`. 3. Start a new Claude Code session, or run `/reload-plugins`, then run `/plugin` to confirm loop-detective is loaded. 4. Watch the live case pane during a session and open the evidence for any flagged case. 5. Use the investigation prompt for a flagged case to redirect the agent, then check the case history if the loop returns. ### Prompt to paste into your agent ```text Using the repo YeonwooSung/my-claude-code-mods, install loop-detective at user scope and run a session on . Report every flagged repeated Bash failure or edit/retry cycle with its evidence and the investigation prompt shown. Verify that each flagged case cites at least two matching attempts from the session before you report it. ``` ### Caveat The README verifies the Loop Detective engine suite on Claude Code 2.1.280 and live UI rendering is not separately established, so check the case pane in your own terminal. Disclaimer: Third-party repos we don't own or vouch for. AI-generated use cases can be wrong: review everything and run at your own risk. Full text: https://dedupedai.com/disclaimer/ URL: https://dedupedai.com/use-cases/yeonwoosung-my-claude-code-mods/catch-repeated-failure-loops-early/ ## How to check verification, scope, and decisions before committing with My Claude Code Mods Repo: [YeonwooSung/my-claude-code-mods](https://github.com/YeonwooSung/my-claude-code-mods) | Difficulty: Advanced | Time: 45 minutes | Basis: From the README Run the workflow mods on a local checkout to review agent changes against scope and verification. **Who it is for:** A developer about to commit agent-made changes who needs to confirm verification status, allowed paths, and the reasons behind key decisions. **The problem:** Agent edits can drift outside the intended paths, rely on stale test results, or lack a record of why choices were made. **The outcome:** Command text showing verification results, scope warnings, impact candidates, and a decision record, plus a review grouped by purpose. ### Steps 1. Clone the repository with `git clone https://github.com/YeonwooSung/my-claude-code-mods`, then change into that directory. (inferred, check the README) 2. Load a workflow mod from the checkout with `claude --plugin-dir ./verify-board`; repeat with `./scope-guard`, `./decision-ledger`, or `./review-queue` as needed. 3. Run `/verify`, `/scope`, `/decision`, and `/review-queue` in the session, using `help` to see each command's options. 4. Read the returned command text and resolve any STALE, UNKNOWN, or out-of-scope item before committing. ### Prompt to paste into your agent ```text In the repo YeonwooSung/my-claude-code-mods checkout, load verify-board and scope-guard with --plugin-dir and run /verify and /scope on the current changes for . Report each verification result as PASS, FAIL, STALE, or UNKNOWN and list any file outside the allowed paths. Verify that each reported file path exists in git status before you finish. ``` ### Caveat The README says these first workflow releases return command text and do not add live panels, and live co-loading of all ten workflow mods is unverified. Disclaimer: Third-party repos we don't own or vouch for. AI-generated use cases can be wrong: review everything and run at your own risk. Full text: https://dedupedai.com/disclaimer/ URL: https://dedupedai.com/use-cases/yeonwoosung-my-claude-code-mods/review-agent-changes-before-commit/