Claude Code mod (plugin) that adds a side pane with Activity, Files, Agents, Plan, Context, MCP, Skills, Spend, Setup, Shells, History, Review and Sessions tabs, a status line above the prompt, a restyled chat, Mermaid diagrams in the terminal, tables, and code and diff panels. Colours follow both /color and the /theme (dark, light and others).
next-steps
bradtraversy/traversy-claude-mods
After each turn, 2 or 3 likely next prompts above the prompt: buttons on the desktop, 1 to 3 in the terminal
session-hud
bradtraversy/traversy-claude-mods
Shows branch safety, context headroom, and account usage in a compact session telemetry strip
source-control
bradtraversy/traversy-claude-mods
A Source Control pane beside the chat, modeled on VS Code: changes, stage, discard, commit, and the commit graph
tool-cards
bradtraversy/traversy-claude-mods
Replaces tool-use rows with diagnostic cards that show status, timing, results, and details
glanceflow
Antreas-Strb/glanceflow
GlanceFlow: see what Claude is doing, at a glance. Hides tool rows and shows one plain-English checklist above the prompt, with progress, helpers, history, a team report, pause and continue, and a password guard.
grounded-engineering
madjagstudios/grounded-engineering
Source-backed engineering practices and reviewed skill repositories, in a Claude Code pane.
dag-workflow
HyunjunJeon/claude-workflow-mods
Dependency-ordered DAG workflows of Claude Code subagents, with a live DAG pane
cc-pr-tracker
sezaakgun/cc-pr-tracker
Watch GitHub PRs from a Claude Code session: merge state, review and required checks above the prompt, with alerts when they change
aicq
ashfulcra/fulcra-tools
AICQ for Claude Code: your agents and friends' agents, their collaborations and what needs you. Notices messages without heartbeats, drafts or responds per your policy, shares files, connects new agents.
roadraven-hud
Shuffzord/RoadRaven
RoadRaven pane in Claude Code: live agents on roadmap nodes, batched UAT sign-off, and a backlog you can start or prioritise
mods-toolbox
rube-de/cc-skills
Mods Toolbox - Function-hook mods (Claude Code 2.1.291+): Clean View, a calm checklist above the prompt for non-technical users that hides tool calls, diffs and command output while showing the plan, the current step and its progress; the Agent Dock, which splits each request across a chosen team of parallel helpers shown as live cards; and the Status Line Dock, which builds Claude Code's...
fast-compact
NodarDavituri/fast-compact
/fast-compact (and /fc): cut old tool output to its start and end in about a second, with Jev keeping whole what is still needed and every cut saved to a file. Claude Code's own /compact is untouched.
paf-tasks
freibergergarcia/phone-a-friend
phone-a-friend, made legible: every review as a thread of rounds with its verdict and findings, live progress while a reviewer works, and the agent sessions that need you
ide-mod
jkf87/ide-mod
Claude Code 안의 IDE 창: 파일 트리·탭 에디터 + HWP·HWPX·PDF 뷰어(rhwp·pdf.js) + 요청 기록 + 허더 세션 한눈에 보고 닫기, 세션 이름·답 요약 읽기 알림, 강의 자막과 한국어 문체 게이트
coa
davebream/claude-of-alexandria
Rigorous analytical skills for biblical study, exegetical analysis, and faithful application. Built with TDD methodology to prevent AI exegetical malpractice.
coa-desk
davebream/claude-of-alexandria
Optional study-desk extras for the coa plugin: see which data lookups grounded an answer and read a passage beside the conversation. Terminal and desktop app only.
effort-pilot
vadympetryshyn/effort-pilot
The right reasoning effort for every turn: plans high, building medium, questions low, picked by a Haiku classifier. Switch the model or the effort by saying it ("switch me to Sonnet at medium"). The model is never changed unless you ask for one or set a plan-mode model, and the prompt cache is kept: where effort is a whole-request setting (Claude 4.x, Fable 5, Bedrock, Vertex), it stands aside.
hydra
Shakibuzzaman3104/claude-hydra
Claude leads, cheaper agents (Heads, on Command Code, CodeBuddy, Codex, Antigravity, WorkBuddy or OpenCode) implement: /hydra turns it on, /heads watches them live, /hydra-usage shows both sides' limits
review-inbox
SummerRiversound/review-inbox
Your GitHub work in a drawer: PRs waiting for your review, each summarized in plain language, your open PRs with their reviews, and your issues
agent-ctx
Tekkiiiii/the-agency
Each agent loop's own context fill, measured per request; a one-line CONTEXT_PCT_ALERT rides that agent's next tool result. Subagents: absolute 200k warn / 250k finish / 300k stop (stop line on every result); main: 70/75/80% of its window. Controllers get CHILD_CTX on Agent and SendMessage results and CHILD_CTX_ALERT when a live child passes 250k/300k
context-band
Tekkiiiii/the-agency
Band above the prompt: context %, tokens, model, cost, prompt-cache size/share/TTL countdown, 5h and weekly usage-window reset timers and next-request estimate; /ctx opens a detail pane; toast when a background subagent finishes; Jev router line (today's calls, tokens, USD, Haiku fallback) and outage warning, hidden unless the router usage log exists
loop-guard
Tekkiiiii/the-agency
Stall detector per agent loop: 5 identical tool calls in a row warn that loop and leave the session-state.json stall marker for the next SessionStart
spawn-ledger
Tekkiiiii/the-agency
Spawn log (spawn_start/launched/end + cost, native agentId lineage), artifact check and in-session RESPAWN_REQUEST pickup for every subagent, background included