Skip to content
Back to search

my-claude-code-mods

MarketplaceWorks with Claude CodeGitHub

Custom Claude Code Mods that I need

Safety scan

A static text scan, not a guarantee. Select the badge to see what was scanned and every finding.

Checked today
Badge for your README
findsafeskills safety rating

Markdown

[![findsafeskills safety rating](/api/listings/yeonwoosung--my-claude-code-mods/badge.svg)](/listings/yeonwoosung--my-claude-code-mods)

HTML

<a href="/listings/yeonwoosung--my-claude-code-mods"><img src="/api/listings/yeonwoosung--my-claude-code-mods/badge.svg" alt="findsafeskills safety rating" /></a>

Install

Install instructions from the README

As written by the repo's author. findsafeskills has not verified these steps.

Use a current Claude Code CLI with Mods support (mods are enabled by default from **2.1.287**). Token Run has been verified in real terminal sessions with **2.1.296 and 2.1.301**; see each mod's README for its tested versions. Time Machine also requires `git` on your PATH.

Install all mods at once

Run this entire block in your terminal (macOS/Linux, Bash or Zsh). It adds the marketplace and installs all seventeen mods for your user account, so they are available across projects. No repository clone or `npm install` is needed.

(
  set -eu
  claude plugin marketplace add YeonwooSung/my-claude-code-mods

  for mod in agent-profiler context-inspector time-machine loop-detective pin-memo model-effort-band token-run verify-board scope-guard blast-radius decision-ledger handoff-pack command-shelf env-doctor dependency-lens assumption-tracker review-queue; do
    claude plugin install "${mod}@my-claude-code-mods" --scope user
  done
)

If you have already added the marketplace, omit the `claude plugin marketplace add` line. The block stops on the first failed command; resolve that error before installing the remaining mods.

Install individual mods

Add the marketplace once in your terminal:

claude plugin marketplace add YeonwooSung/my-claude-code-mods

Then run only the install commands for the mods you want:

claude plugin install agent-profiler@my-claude-code-mods --scope user
claude plugin install context-inspector@my-claude-code-mods --scope user
claude plugin install time-machine@my-claude-code-mods --scope user
claude plugin install loop-detective@my-claude-code-mods --scope user
claude plugin install pin-memo@my-claude-code-mods --scope user
claude plugin install model-effort-band@my-claude-code-mods --scope user
claude plugin install token-run@my-claude-code-mods --scope user
claude plugin install verify-board@my-claude-code-mods --scope user
claude plugin install scope-guard@my-claude-code-mods --scope user
claude plugin install blast-radius@my-claude-code-mods --scope user
claude plugin install decision-ledger@my-claude-code-mods --scope user
claude plugin install handoff-pack@my-claude-code-mods --scope user
claude plugin install command-shelf@my-claude-code-mods --scope user
claude plugin install env-doctor@my-claude-code-mods --scope user
claude plugin install dependency-lens@my-claude-code-mods --scope user
claude plugin install assumption-tracker@my-claude-code-mods --scope user
claude plugin install review-queue@my-claude-code-mods --scope user

Alternatively, run these slash commands **inside a Claude Code session**, replacing `pin-memo` with any mod name listed above:

/plugin marketplace add YeonwooSung/my-claude-code-mods
/plugin install pin-memo@my-claude-code-mods

The shell commands above explicitly use `--scope user`. For a project-specific installation, use `--scope project` (shared through the project's settings) or `--scope local` (only you in that project).

Load and verify

Start a new Claude Code session after installation, or run `/reload-plugins` in an already open session. Run `/plugin` to check the loaded mods and manage or disable individual ones. See the [official Mods installation documentation](https://code.claude.com/docs/en/plugins/mods/overview#install-or-update-a-mod) and each mod's README under [Mods](#mods) for commands and configuration.

What was scanned

The files the safety scan read, as written by the repository's author and shown as plain text. Lines with a finding are marked.

.claude-plugin/marketplace.json · Manifest · 96 lines

View this file on GitHub (read at the repository's current version: the scan did not record which commit it read)

  1. {
  2. "name": "my-claude-code-mods",
  3. "owner": {
  4. "name": "YeonwooSung"
  5. },
  6. "plugins": [
  7. {
  8. "name": "agent-profiler",
  9. "source": "./agent-profiler",
  10. "description": "Execution profiler for Claude Code: model wait vs tools vs subagents, live, with OTLP export"
  11. },
  12. {
  13. "name": "context-inspector",
  14. "source": "./context-inspector",
  15. "description": "Context waste analyzer: what fills the window, re-reads, near-duplicate outputs, what compaction kept, advice"
  16. },
  17. {
  18. "name": "time-machine",
  19. "source": "./time-machine",
  20. "description": "Agent Time Machine: a branching timeline of tool calls with shadow-git snapshots — inspect, diff, explain test failures, restore, branch, compare, re-run"
  21. },
  22. {
  23. "name": "loop-detective",
  24. "source": "./loop-detective",
  25. "description": "Repeated-failure detective: evidence-backed Bash retry and edit/retry cases, live pane and investigation prompts"
  26. },
  27. {
  28. "name": "pin-memo",
  29. "source": "./pin-memo",
  30. "description": "Persistent pinned memos and clickable todos above the prompt, isolated by folder and session"
  31. },
  32. {
  33. "name": "model-effort-band",
  34. "source": "./model-effort-band",
  35. "description": "Shows the selected model and observed main-thread effort in a colored band above the prompt"
  36. },
  37. {
  38. "name": "token-run",
  39. "source": "./token-run",
  40. "description": "Fully local ASCII runner for request failures and short breaks, with jump controls and a saved best score"
  41. },
  42. {
  43. "name": "verify-board",
  44. "source": "./verify-board",
  45. "description": "Verify Board"
  46. },
  47. {
  48. "name": "scope-guard",
  49. "source": "./scope-guard",
  50. "description": "Scope Guard"
  51. },
  52. {
  53. "name": "blast-radius",
  54. "source": "./blast-radius",
  55. "description": "Blast Radius"
  56. },
  57. {
  58. "name": "decision-ledger",
  59. "source": "./decision-ledger",
  60. "description": "Decision Ledger"
  61. },
  62. {
  63. "name": "handoff-pack",
  64. "source": "./handoff-pack",
  65. "description": "Handoff Pack"
  66. },
  67. {
  68. "name": "command-shelf",
  69. "source": "./command-shelf",
  70. "description": "Command Shelf"
  71. },
  72. {
  73. "name": "env-doctor",
  74. "source": "./env-doctor",
  75. "description": "Env Doctor"
  76. },
  77. {
  78. "name": "dependency-lens",
  79. "source": "./dependency-lens",
  80. "description": "Dependency Lens"
  81. },
  82. {
  83. "name": "assumption-tracker",
  84. "source": "./assumption-tracker",
  85. "description": "Assumption Tracker"
  86. },
  87. {
  88. "name": "review-queue",
  89. "source": "./review-queue",
  90. "description": "Review Queue"
  91. }
  92. ],
  93. "metadata": {
  94. "description": "Local Claude Code mods for developer profiling, context, verification and review workflows."
  95. }
  96. }
README.md · README · 130 lines

View this file on GitHub (read at the repository's current version: the scan did not record which commit it read)

  1. # My Claude Code Mods
  2. [Claude Code Mods Overview](https://code.claude.com/docs/en/plugins/mods/overview) [Create Claude Code Mods](https://code.claude.com/docs/en/plugins/mods/create)
  3. ## Mods
  4. - [agent-profiler](agent-profiler/README.md): shows where a session's time goes (model wait, tools, subagents, re-reads) and exports OTLP traces for Jaeger/Tempo.
  5. - [context-inspector](context-inspector/README.md) ([한국어](context-inspector/README_KR.md)): analyzes context waste in Claude sessions, including what fills the window, re-reads, near-duplicate outputs, and what compaction kept, providing advice.
  6. - [time-machine](time-machine/README.md) ([한국어](time-machine/README_KR.md)): records every tool call on a branching timeline with shadow-git snapshots, so you can see the files as they were at any step, explain which edit broke a test, restore, branch, compare runs and re-run steps.
  7. - [loop-detective](loop-detective/README.md) ([한국어](loop-detective/README_KR.md)): detects repeated Bash failures and edit/retry cycles, with evidence, investigation prompts, a live case pane and bounded history.
  8. - [pin-memo](pin-memo/README.md) ([한국어](pin-memo/README_KR.md)): pins memos and clickable todos above the input, restoring them when the same folder/session is resumed.
  9. - [model-effort-band](model-effort-band/README.md) ([한국어](model-effort-band/README_KR.md)): shows the selected model and observed main-thread effort in a colored band above the prompt.
  10. - [token-run](token-run/README.md) ([한국어](token-run/README_KR.md)): a fully local ASCII runner for request failures and short breaks, with jump controls and a saved best score.
  11. - [verify-board](verify-board/README.md) ([한국어](verify-board/README_KR.md)): Revision-aware verification results: PASS, FAIL, STALE and UNKNOWN.
  12. - [scope-guard](scope-guard/README.md) ([한국어](scope-guard/README_KR.md)): Allowed-path warnings with rename and pre-existing-change awareness.
  13. - [blast-radius](blast-radius/README.md) ([한국어](blast-radius/README_KR.md)): Local reverse-import impact and related test candidates.
  14. - [decision-ledger](decision-ledger/README.md) ([한국어](decision-ledger/README_KR.md)): Explicit decisions with rationale, rejected alternatives and file references.
  15. - [handoff-pack](handoff-pack/README.md) ([한국어](handoff-pack/README_KR.md)): Resumable Markdown previews of goals, tasks, changes and evidence.
  16. - [command-shelf](command-shelf/README.md) ([한국어](command-shelf/README_KR.md)): Successful-command history with explicit permission-aware replay.
  17. - [env-doctor](env-doctor/README.md) ([한국어](env-doctor/README_KR.md)): Project runtime requirements and environment-variable presence checks.
  18. - [dependency-lens](dependency-lens/README.md) ([한국어](dependency-lens/README_KR.md)): Direct and transitive npm dependency changes and install-script markers.
  19. - [assumption-tracker](assumption-tracker/README.md) ([한국어](assumption-tracker/README_KR.md)): Evidence-backed assumption states with retained transition history.
  20. - [review-queue](review-queue/README.md) ([한국어](review-queue/README_KR.md)): Purpose-grouped file review with staged/unstaged freshness checks.
  21. ## Local workflow-mod preview
  22. The ten new workflow mods can be loaded from this checkout before the branch is published to the marketplace. Choose a mod directory, for example:
  23. ```sh
  24. claude --plugin-dir ./verify-board
  25. ```
  26. Commands: `/verify`, `/scope`, `/blast`, `/decision`, `/handoff`, `/shelf`, `/env-doctor`, `/deps`, `/assume`, `/review-queue`. Each accepts `help`. These first releases return command text; they do not add live panels.
  27. ## Installation
  28. Use a current Claude Code CLI with Mods support (mods are enabled by default from **2.1.287**). Token Run has been verified in real terminal sessions with **2.1.296 and 2.1.301**; see each mod's README for its tested versions. Time Machine also requires `git` on your PATH.
  29. ### Install all mods at once
  30. Run this entire block in your terminal (macOS/Linux, Bash or Zsh). It adds the marketplace and installs all seventeen mods for your user account, so they are available across projects. No repository clone or `npm install` is needed.
  31. ```sh
  32. (
  33. set -eu
  34. claude plugin marketplace add YeonwooSung/my-claude-code-mods
  35. for mod in agent-profiler context-inspector time-machine loop-detective pin-memo model-effort-band token-run verify-board scope-guard blast-radius decision-ledger handoff-pack command-shelf env-doctor dependency-lens assumption-tracker review-queue; do
  36. claude plugin install "${mod}@my-claude-code-mods" --scope user
  37. done
  38. )
  39. ```
  40. If you have already added the marketplace, omit the `claude plugin marketplace add` line. The block stops on the first failed command; resolve that error before installing the remaining mods.
  41. ### Install individual mods
  42. Add the marketplace once in your terminal:
  43. ```sh
  44. claude plugin marketplace add YeonwooSung/my-claude-code-mods
  45. ```
  46. Then run only the install commands for the mods you want:
  47. ```sh
  48. claude plugin install agent-profiler@my-claude-code-mods --scope user
  49. claude plugin install context-inspector@my-claude-code-mods --scope user
  50. claude plugin install time-machine@my-claude-code-mods --scope user
  51. claude plugin install loop-detective@my-claude-code-mods --scope user
  52. claude plugin install pin-memo@my-claude-code-mods --scope user
  53. claude plugin install model-effort-band@my-claude-code-mods --scope user
  54. claude plugin install token-run@my-claude-code-mods --scope user
  55. claude plugin install verify-board@my-claude-code-mods --scope user
  56. claude plugin install scope-guard@my-claude-code-mods --scope user
  57. claude plugin install blast-radius@my-claude-code-mods --scope user
  58. claude plugin install decision-ledger@my-claude-code-mods --scope user
  59. claude plugin install handoff-pack@my-claude-code-mods --scope user
  60. claude plugin install command-shelf@my-claude-code-mods --scope user
  61. claude plugin install env-doctor@my-claude-code-mods --scope user
  62. claude plugin install dependency-lens@my-claude-code-mods --scope user
  63. claude plugin install assumption-tracker@my-claude-code-mods --scope user
  64. claude plugin install review-queue@my-claude-code-mods --scope user
  65. ```
  66. Alternatively, run these slash commands **inside a Claude Code session**, replacing `pin-memo` with any mod name listed above:
  67. ```text
  68. /plugin marketplace add YeonwooSung/my-claude-code-mods
  69. /plugin install pin-memo@my-claude-code-mods
  70. ```
  71. The shell commands above explicitly use `--scope user`. For a project-specific installation, use `--scope project` (shared through the project's settings) or `--scope local` (only you in that project).
  72. ### Load and verify
  73. Start a new Claude Code session after installation, or run `/reload-plugins` in an already open session. Run `/plugin` to check the loaded mods and manage or disable individual ones. See the [official Mods installation documentation](https://code.claude.com/docs/en/plugins/mods/overview#install-or-update-a-mod) and each mod's README under [Mods](#mods) for commands and configuration.
  74. ## Development
  75. [Expanded workflow validation (2026-10-18)](docs/verification/2026-10-18-workflow-validation.md) documents 55 added tests, real-Git regressions and ten-adapter controlled-host composition. Individual engine suites are verified; live UI and actual combined engine loading require separate integration checks.
  76. Use Node 22.19.0 or later. Dependencies are pinned in `package-lock.json`.
  77. ```sh
  78. npm ci --ignore-scripts
  79. npm test # core logic, no Claude Code installation/account required
  80. npm run test:privacy # shared masking corpus and real-Git privacy regressions
  81. CLAUDE_BIN=/path/to/claude npm run test:adapters # full engine suites, including adapters
  82. npm run check:workflow # verify standalone runtime copies match canonical sources
  83. npm run test:workflow # real-Git and queued-session regression tests
  84. npm run typecheck # requires engine-generated declarations in each .claude-plugin/types
  85. ```
  86. `npm test` maps the core tests' `claude-code/testing` import to Node's test runner and Jest's `expect`; it does not emulate engine events. Files run sequentially so the existing performance assertions do not compete with other test processes. CI runs this independent core suite. Engine type declarations are generated locally and remain untracked; use the declarations belonging to the engine under test. See each mod's development instructions for generation/setup.
  87. | Validation target | Compatibility |
  88. |---|---|
  89. | Node core tests | Node 22.19.0; TypeScript transformation flag required |
  90. | Original three engine test suites | Verified with Claude Code 2.1.292 |
  91. | Pin Memo engine suite | Verified with Claude Code 2.1.292; render trees and Button presses on terminal/Desktop |
  92. | Loop Detective engine suite | Verified with Claude Code 2.1.280; TypeScript checks use local 2.1.292 declarations |
  93. | Model Effort Band engine suite | Verified with Claude Code 2.1.292; terminal/Desktop render trees, live pixels unverified |
  94. | Token Run engine suite | Engine tests: 2.1.296/299/300/301; real terminal 2.1.296/301 solo + 2.1.301 all seven mods; Desktop GUI unverified |
  95. | Early-access Claude Code 2.1.280 | Profiler works; Context Inspector lacks `session.append`, and Time Machine's per-test options are ignored |
  96. | Ten developer workflow mods | Verified with Claude Code 2.1.302: core, engine boundary, real-Git regressions and TypeScript checks; command text UI; live co-loading unverified |
  97. | Live terminal/desktop UI and simultaneous mods | Requires a separate interactive integration run; unit suites do not establish UI compatibility |
  98. For a controlled overhead comparison, use a disposable representative large repository at one fixed commit and the same Claude engine/model/permission settings. Run the same workload under four configurations: no mods, profiler only, Time Machine only, and all three. Load mods explicitly with `--plugin-dir` while other installed plugins are disabled; reset files and recorder stores outside the timed interval. Use a warm-up and at least five measured repetitions per configuration, alternate run order, and record wall time, tool-call count, model tokens and snapshot average. Include no-change mutating calls and actual edits. Report median/p95 and separate model latency from snapshot/hook time. The existing 20k-span/item tests bound analysis cost but do not measure combined engine overhead; no four-mode performance result is claimed here.

Ratings and comments

Sign in to rate this skill.

Sign in

Free to use. If it’s helped, pass it on.