All mods
1,830 mods. Every one passed the check.
- token-ledger 0.1.0 A per-turn cost and token ledger: a pinned status line with the session cost, the last turn's tokens and the cache hit ratio, and /ledger for a table of the recent turns with their model, tokens, cache reads and writes, duration and cost. 4
- vercel-deploy-status 1.0.1 Pins the Vercel deploy queue of the linked project under the prompt: every deploy queued, building or just finished, with its phase and elapsed time 4
- whats-agent-doing 0.4.3 A small box above the prompt that always says what the agent is doing right now (reading, thinking, writing, running a tool, waiting for you) and expands to show what it has done. 4
- 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. 4
- typing-speed 0.2.0 A live typing speedometer above the prompt, offline spell check in your system language, a result card after each prompt (WPM, CPM, accuracy, typos, personal bests) and a /typing stats pane 4
- screen-guard 0.1.0 Masks sensitive names, orgs and secrets in the transcript for screen sharing; /mask toggles, click a mask to reveal 4
- cache-panel 0.1.0 Passive 50-minute prompt-cache reminder with a keyboard/mouse panel: keep warm, ping once, or compact, with live cost estimates. 4
- session-wrapped 0.1.0 A /wrapped pane summarizing the session: turns, tools, files, cost, peak context, longest and busiest turns. 4
- todo-bar 0.2.0 The task list's progress in a band above the prompt, read from the todo and task tools' own calls: no tool, no prompt, no tokens 4
- cache-ttl-statusline 1.6.0 mod + skill Native Claude Code status-line mod with configurable widgets for cache TTL, model, cost, context, API rate limits, git, and Headroom stats 4
- catalyst-statusline 0.5.7 Multi-line status HUD above the prompt over data families (hooks/data/*.ts pure collectors, one core subscription per event), with the /statusline-mod pill panel: live preview, six tabs (layout, elements, per-element settings, view axes, themes, number formats). Based on konsta95/ClaudeCodeMods s... 3
- coordinator-handoff 1.0.0 Auto-submits /coordinator-handoff when a dotfiles coordinator session's context reaches the configured limit, with a visible status-line heartbeat 3
- bad-reads-ledger 0.1.0 Fixture: must fail Check 77a rule 'tasks.json'. 3
- fnhook-fixture-valid 1.0.0 Valid function-hook gate fixture 3
- fnhook-fixture-untyped 1.0.0 Untyped function-hook fixture 3
- bad-destructured-http 0.1.0 Fixture: must fail Check 77a rule 'destructure'. 3
- forged-consent-sample 0.0.1 Self-hostable, model-agnostic AI workstation and coding harness. Run any model (frontier or local) behind one OpenAI-compatible surface, run a gated coding agent over your folders, and keep a proof receipt you can re-check offline. Verified-inference loop, receipt-wrapped tool calls, composed lan... 3
- bad-destructured-model 0.1.0 Fixture: must fail Check 77a rule 'destructure'. 3
- context-tracker 0.1.0 Live pane tracking the context window: colored category breakdown, a timeline of growth spikes, and per-skill growth attribution. 3
- pomegr 0.8.3 mod + skill Configure and report bounded, repository-specific coding-agent signals to the local Pomegr observer. 3
- bad-bracket-http 0.1.0 Fixture: must fail Check 77a rule 'bracket-http'. 3
- bad-tool-call-hook 0.1.0 Fixture: must fail Check 77a rule 'tool.call'. 3
- ailang-brand 0.1.0 AILANG look for Claude Code: the AILANG version beside the prompt hint, compiler-flavoured spinner words (Unifying…, Inferring effects…), and /ailang for a pane with the logo. 3
- unowned-dirty 0.1.0 Warns when a git add/stash/checkout/restore/reset may sweep dirty files this session did not write (shared checkouts have several agents). A toast for the person, a note in the model's context; never blocks. Port of the pi extension of the same name. 3
- claude-mermaid 0.3.1 Mermaid diagrams in Claude Code: every ```mermaid block Claude writes is drawn as box art, in colour, right where the fence was in the transcript. Needs function hooks (early access) and an interactive terminal. 3
- bad-global-fetch 0.1.0 Fixture: must fail Check 77a rule 'fetch'. 3
- bad-tool-check-hook 0.1.0 Fixture: must fail Check 77a rule 'tool.check'. 3
- claude-fnhook-fixture-reserved 1.0.0 Reserved-prefix plugin name: validate must reject it (#1496) 3
- workflow-gates-rows 0.1.0 Draws the transcript row of an answer the workflow-gates mod sent as the question it answered and the answer, instead of Claude Code's framing. 3
- fnhook-fixture-parse-error 1.0.0 Parse-error function-hook fixture 3