All Claude Code modsYeonwooSung/my-claude-code-mods
loop-detective
Detect repeated Bash failures and edit/retry cycles with evidence, live cases and investigation prompts
review UI rewrite
loop-detective reaches L0 (draws and remembers) and passed claude plugin validate on Claude Code 2.1.303.
- Events hooked: 6
- API methods referenced: 8
- Access from classified calls: L0, draws and remembers: draws
- Static scan, not a runtime test
Install hint
/plugin install loop-detective --marketplace YeonwooSung/my-claude-code-modsFrom the repository's own marketplace. Confirm the plugin name in the repository's README before installing. Mods need Claude Code 2.1.287 or later.
Access
L0 Draws & remembersdrawsValidation
Passed on Claude Code 2.1.303View the source on GitHub Back to the list
What the scan recorded
- Observed events
- every tool call
- Hooks
session.start, session.end, tool.call, turn.complete, command.run {command=loop-report}, command.run {command=loop-reset}, command.run {command=loop-pane}, ui.render {component=Pane, requestId=loop-detective}- API calls
$.clock.after, $.command.register, $.session.cwd, $.ui.invalidate, $.ui.open, $.ui.resolve, $.ui.status, $.ui.toast- Validation on 2.1.303
- Passed
- Scanned revision
82f9bf698508- Marketplace passed
- my-claude-code-mods
- UI rewrite review
- UI hook source contains control-character strings. Review any values passed to next() as rewritten props.text; the scanner does not trace whether these strings reach that call. loop-detective/hooks/core/redact.ts:12, loop-detective/hooks/core/redact.ts:19
These are the hooks and API calls reported by claude plugin validate. Access levels describe the widest reach of those calls and are not safety ratings. Validation is a static check, not a runtime test, and a passing result does not prove that a mod works or is safe. What a mod can access and how the scan works.
More from YeonwooSung/my-claude-code-mods
- agent-profilerExecution profiler for Claude Code: model wait vs tools vs subagents, live, with OTLP export
- assumption-trackerAssumption Tracker
- blast-radiusBlast Radius
- command-shelfCommand Shelf
- context-inspectorContext waste analyzer for Claude Code: what fills the window, re-reads, near-duplicate outputs, what compact…
- decision-ledgerDecision Ledger
- dependency-lensDependency Lens
- env-doctorEnv Doctor
- handoff-packHandoff Pack
- model-effort-bandShows the selected model and observed main-thread effort in a colored band above the prompt
- pin-memoPersistent pinned memos and clickable todo checkboxes above the Claude Code prompt
- review-queueReview Queue
- scope-guardScope Guard
- time-machineAgent Time Machine: a branching timeline of tool calls with shadow-git snapshots: inspect, diff, explain test…
- token-runA fully local ASCII runner game for Claude Code request failures and short breaks
- verify-boardVerify Board
Badge for your README
Authors can show the latest scan result in their README. Each badge links to this page.
[](https://mods.aidojo.si/mods/YeonwooSung--my-claude-code-mods--loop-detective/)
[](https://mods.aidojo.si/mods/YeonwooSung--my-claude-code-mods--loop-detective/)