All mods
3,470 mods. Every one passed the check.
- haiku-commits 0.5.1 Commit messages get a normal conventional-commit first line, then a 5-7-5 haiku about the change in the body. 1
- test-pane 0.5.1 A live side pane with the last test run (vitest, jest, pytest, go test, cargo test, bun test, claude plugin test): runner, pass, fail and skip counts, duration and first failures. Open it with /tests. 1
- neon-hud 0.1.0 A live HUD above the prompt: turn timer, active skill, subagent tree, git state, rtk token savings and one-click session checkpoints 1
- chiikawa 0.2.2 Chiikawa mode: Hachiware conducts, and the friends from Chiikawa appear as text drawings to take on tasks and talk them over (Claude subagents + Orca workers). In English, Korean and Japanese. 1
- pstack 0.15.15+claude.7 mod + skill poteto's rigorous engineering skills (poteto-mode, how/why, architect, verification), ported from Cursor and kept in sync with upstream 1
- tower 0.6.2 A web cockpit and a /tower pane over every Claude Code agent across your repos: see who needs you, approve and answer, send prompts and slash commands, start workstreams in git worktrees, and watch changes and PRs. Plus desktop notifications and a status line. 1
- slash-coverage 0.1.0 Which files each Claude Code agent has in its context, and how much of each: line ranges, tokens, re-reads, edits, and which files only a subagent it spawned has read. 1
- blocked-run 0.1.0 When auto mode blocks a command, shows it above the prompt with a button to run it yourself 1
- compact-usage-meter 0.1.0 Context, session and weekly usage meters with reset countdowns on a row under the prompt hint line 1
- usage-limits 0.3.0 Keeps the 5-hour and weekly limit windows, their burn rate, a run-out projection, context fill, session cost and prompt-cache drops in a dim line above the prompt 1
- session-models 0.5.0 Shows the main model and its effort, the live agents by model and effort, and warns about agent crowds and huge contexts 1
- subagent-limits 0.3.1 mod + skill Keeps subagents small: tells the main agent how to size and split work, asks a growing subagent to checkpoint, and refuses its tools past a hard limit so a fresh agent takes over 1
- dag-workflow 0.1.0 mod + skill Dependency-ordered DAG workflows of Claude Code subagents, with a live DAG pane 1
- model-pick 0.2.2 Fuzzy-pick a model + effort combo, with favorites, aliases and recents: /pick 1
- secret-guard 0.4.0 Hides secrets in tool results before Claude reads them: the secret values of every .env and .env.* from your session's folder up to the drive root, and anything that looks like a secret (KEY=VALUE under a secret name, passwords in URLs, private keys, JWTs, AWS keys, Kubernetes Secrets); tells Cla... 1
- plan-meter 0.3.0 A band above the prompt with how far your plan file is (phases and steps done, what is in progress, what is next) and Claude's own task list, kept current as files change. Starts off: /plan-meter on turns it on 1
- done-gate 0.3.0 Notices when Claude marks a task done while code it changed has not been tested since, and tells Claude and you; a band shows the last test run. It warns, it never blocks. Starts off: /done-gate on turns it on 1
- ambient-spanish-hover 0.3.2 Hover a Spanish word in a reply to see its English in the band above the prompt. 1
- copy-command 0.2.0 An icon-only copy button beside every shell command in Claude's replies. 1
- clear-view 0.1.0 Live session dashboard: what Claude is doing now, turn timing, tool stats, files touched, errors and token usage in one pane. 1
- status-dash 0.3.0 Band above the prompt with gradient gauges (context, 5-hour and weekly limits) and toasts for finished turns, notifications and a full context. 1
- row-polish 0.3.0 Korean wording for the spinner, the turn-end line and the background hint, and a readable Bash tool row with status, elapsed time and highlighted command. 1
- cost-guard 0.1.0 Watches session and daily spend, warns when the context grows large, and holds a prompt once when the prompt cache has expired on a big context. 1
- pre-push-review 0.1.0 Reviews unpushed commits against REVIEW_GUIDELINES.md before Claude runs git push 1
- harness 0.2.0 Shows and drives Herdr-Jev role plans inside Claude Code: the advisor is the session, and the implementer, reviewer and reader models come from herdr-jev models list. 1
- sdd-pipeline 5.3.0 mod + skill Specification-Driven Development pipeline (SWEBOK v4): 21 skills, 5 hooks (7 event registrations) and an MCP traceability server. Greenfield, brownfield and multi-session (worktree) implementation; optional Jev (TypeSafe) bulk judgments. 1
- snob 1.0.1 A haughty, condescending persona (levels 1 to 5) for trivially easy requests. 1
- mod-store 1.4.2 An in-terminal app store: browse, search, install and update every Claude Mod from GitHub. 1
- secret-shield 1.1.1 Blocks edits and writes that would commit API keys, tokens or private keys. 1
- env-guard 1.1.1 Protects .env files, SSH keys and credential stores from being read or modified. 1