Status line
103 mods. Entries in the status line: model, branch, cost, timers.
- tamirs-superpowers 4.12.0 mod + skill 29 bundled skills, 10 specialist agents, smart worktree hooks, statusline, and MCP server stubs — plan, implement, review, debug, multi-agent setup, and audit code from one plugin. 2
- statuspane 1.3.2 A floating status card above the Claude Code prompt — model, effort, context, 5h/week limits, cost, directory and branch, GitHub CI and deploys — with clickable settings and a progress-row API any script or mod can feed. 2
- usageline 0.2.5 A status line under the prompt: context, cache hit rate, cache TTL countdown, today's spend for this project, and why a turn missed the cache. /usage prints the project ledger. 2
- session-band 0.1.0 A status line under the prompt: agent state, the active worklog key, the work-on phase, the present page, and belt denies this session. 1
- turn-budget 0.1.2 Asks before a single turn uses more than +5 session points or 500,000 uncached input tokens, and stops it cleanly if you say so. Checks between requests, never mid-command. 1
- statusline-band Port of statuslineV4.sh to a mod: draws the same figures in two colored rows (dir, git, model, effort | duration, version, session id / rate limits, context, cost, output style | RAM) in the band above the prompt, so the Desktop Code tab gets a status line. Off in the terminal by default, where t... 1
- output-diet 0.1.0 Trims long shell output before Claude reads it: keeps the head, the tail and every error line, saves the full output to a file Claude can open. 1
- tool-diet 0.1.2 Moves tools you have not used lately behind ToolSearch, so their descriptions stop riding along on every request; core tools and anything you used in your last five sessions stay loaded. 1
- cache-clock 0.1.1 Shows how long the prompt cache stays warm, and when it expires, exactly how many tokens your next message will re-send uncached. No tokens spent. 1
- read-cap 0.1.0 Stops Claude reading a file over 1,000 lines whole and gives it an outline tool (definitions with line numbers) so it reads only the range it needs. A retry still reads it whole. 1
- token-meter 0.2.0 Shows live tokens per second, per minute and per hour in the status line 1
- decision-lens 0.2.0 See the decisions Claude made in each turn, why it made them, and steer future turns with keep and avoid rules. 1
- unslop 0.1.0 Finds AI slop in Claude's changes (dashes, comment blocks, comments that repeat the code, tests that assert nothing, filler phrases) and tells Claude to remove it. Shows what was unslopped. 1
- combo-meter 0.1.0 Fighting-game combo meter for Claude Code: every clean tool call is a hit, every error breaks the chain. Ranks D to SSS, special moves, and an all-time high score. 1
- gate 0.1.0 Runs the CI gate as a tool and a /gate command, its verdict read from the exit code and exit file; shows it in the status line; refuses piped gates, edits mid-gate and pushes without a green gate. 1
- context-bar 0.4.0 Context window breakdown and prompt-cache countdown above the prompt; /context-bar toggles it. 1
- statusline-band 0.3.0 A panel above the prompt with rate limits and their pace, context, cost and tokens, git status and switches, actions, and a Spotify card, with Clawd and Beatbot 0
- zp-ci-watch 0.1.0 After a git push or a PR merge, follows the GitHub Actions runs on that commit in the status line and toasts green or red, so a session never sleeps in a loop to find out. /ci asks once. 0
- model-router 0.1.0 Route each turn to Haiku / Sonnet / Opus with TypeSafe Jev (default: Sonnet) 0
- tripwire 0.1.0 Catches recurring agent failures from past transcripts: whole-disk find, foreground poll loops, errors masked by | tail, forgotten background shells 0
- lean-scripts 0.1.2 Scripts worth keeping: scripts-review asks Haiku whether a new script could just be typed again when needed. 0
- repo-lock 0.1.0 Blocks dependency changes with the wrong package manager or outside a repo, and shows repo, package manager and branch in the status line. 0
- Cache 0.6.0 Countdown of the 1 hour prompt-cache window, counted from the last reply. 0
- dashboard 0.1.0 The context window's fill and the main loop's tokens/s in the status line 0
- idle-compact 0.1.0 Runs /compact while the session sits idle waiting on background work, right before the prompt cache expires. 0
- global-hooks 0.1.0 User-global Claude Code hooks, loaded in place as global-hooks@skills-dir through the ~/.claude/skills symlink 0
- bespunky-browser-automation 0.5.1 mod + skill BeSpunky browser automation. `playwright` — drive a real browser headless (load, click, type, screenshot, scrape) for solo verification, bug repro, or repeatable scripts. `shared-browser` — one in-container Chromium the human watches and clicks over noVNC while Claude drives it over loopback CDP:... 0
- clawdify 0.7.0 Restyle Claude Code from /clawdify: spinner, turn footer, prompt hint, banner, status line, transcript rows and presets, or just describe what you want. 0
- agent-autopilot 0.3.0 Answers AskUserQuestion polls for you only when the assistant marked one option (Recommended) and nothing looks irreversible; default is a hint. 0
- idle-compact 0.4.0 Compacts an idle interactive session shortly before its prompt cache expires, so coming back later doesn't re-read the whole context uncached. 0