port-lantern 0.1.0
Keeps track of the dev servers the session started: their URLs and ports from the server's own output, whether each still listens, and its latest log lines, in the status line and a /ports pane; a toast when one starts or stops
Install
/plugin marketplace add simota/claude-mods /plugin install port-lantern@simota-mods
Run both lines inside Claude Code.
Hooks into
- Pane
- Status line
- Tool calls
- Toasts
- Slash commands
Also in simota/claude-mods
- perf-delta 0.1.0 /perf runs a benchmark command several times and compares it with its baseline (saved earlier, or a git ref run in a temporary worktree): median wall time, peak memory and the spread of the runs, and whether the difference is larger than the noise 1
- assertion-guard 0.1.0 Catches edits that weaken tests to make them pass: assertions removed, expectations loosened or rewritten, tests skipped, exceptions swallowed; asks Claude for the reason beside the tool's result and keeps a band until the person has checked it 1
- negative-space 0.1.0 When an edit adds authorization, input validation or error handling, lists the refusal, invalid-input, failure and boundary-value tests that no test touched this session covers yet; a band after the turn and /negative-space 1
- mutation-tap 0.1.0 /mutate runs a mutation test limited to the lines changed since HEAD: each small change to the code (a flipped comparison, && for ||, a constant) is run against the tests, and the ones the tests did not catch are listed 1
- handoff-capsule 0.1.1 A capsule to resume from: before a compaction and at the end of a session it keeps the goal, the decisions, what is left, the commands to reproduce and the files touched; the next session (or the conversation after the compaction) chooses which parts to bring back 1
- artifact-shelf 0.1.1 A shelf of what the sessions made: CSV, PDF, HTML, video, audio, images, patches and archives, each tied to the call that made it and the request it answered; /shelf finds them by kind, word, place or time 1
- focus-hud 0.1.0 One status line that says what is going on: the goal (the request, or the todo in progress), the target (the file, page or command in hand), what is running and for how long, and what it waits on (you, a permission, an answer, a tool); /focus gives the detail 1
- side-effect-ledger 0.1.9 A ledger of what a git diff never shows: pushes, publishes, deploys, pull requests, releases, API writes and messages sent, each with its outcome, how it would be undone, and whether that undo has been checked; /ledger 1
- trust-label 0.1.0 Labels text that came from outside (web pages, search results, issues and PRs, logs, browser pages, MCP services) with where it came from, beside the tool's result, and flags candidate instructions hidden in it; a heuristic, never a judgement that a text is safe; /trust 1
- visual-diff 0.1.0 Compares the browser screenshots Claude takes of the same URL at the same size, before and after an edit: both side by side, a map of the cells that changed, the changed regions in page pixels and the files edited in between; /vdiff 1
More status line mods
- jev-auto-mode 0.1.0 A permission layer driven by a JSON policy: allow, ask or deny every tool call (Bash, edits, web, MCP, subagents, skills), every slash command or skill you type, and every skill preloaded into a subagent. Rules decide first (deny > ask > allow, compound Bash commands split); what no rule covers c... 32.7k
- secrets-veil 0.0.6 Masks secret values in tool results before the model reads them: named vendor variables, value-shape patterns, and high-entropy tokens. No reveal path. 294
- cache-clock 0.1.1 A prompt-cache line under your status line, from Claude Code's own cache figures: time left while warm, hit rate and misses, and how many tokens the next message re-caches once cold. /cache-clock setup adds it. 244
- sprint-status 0.1.0 Status line for AILANG sprint work: the most recently touched in-progress sprint under .ailang/state/sprints, its milestones passed and the next one. 35
- brewmod-plan-effort 6.8.0 Raises the main loop to the configured effort (default xhigh) while in plan mode, by rewriting each request; the session effort setting is never touched (Claude Code 2.1.287+ mod) 32