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
1,027 mods
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
ElirazKed/claude-code-pr-watch
Live pane tracking the GitHub PRs touched in a session: CI, review, conflicts, merge. One shared poller for every session on the machine.
Lightning-AI/skills
Agent skills for the Lightning AI platform: GPU Studios, batch jobs, deployments, sandboxes, the LLM gateway, shareable artifact links, up-front cost estimates, and billing balances and spend reports. Includes pipelines and LitData dataset workflows.
davekiss/env
Edit .env files in a pane inside Claude Code. Claude manages keys and asks you for values without ever seeing them.
luvpame/dotfiles
Shows the task tree, progress and your own prompts of a session in a pane
JasonWarrenUK/goblin-mode
A warband raids in good order or not at all. One chief, many sessions, one repo: orders read, dibs called, tribute paid, spoils counted. Coordinate several Claude Code sessions on one repository: a ledger of dibs on shared resources enforced by hooks, a /show-slate pane, tools that report, call dibs, grant and broadcast, a declaration that writes each raider's orders, and the protocol that...
mmurakaru/cueloop
Claude Mod for cueloop Threads: plan, reply, prototype, diff, review, and refine
JasonWarrenUK/goblin-mode
Coordinate several Claude Code sessions on one repository: a ledger of shared-resource slots enforced by hooks, a /mc board pane, tools that report, request, grant and broadcast, a kick-off that writes each session's brief, and the protocol that came out of running it.
zirkelc/agent-journal
A journal written by your agent, autonomously. One small markdown file per milestone, written as the work happens, in a format built to be scanned with grep and ls.
LippInc/catnap
Claude compacts its own conversation at a clean break, then carries on by itself. A gentle note at 50% context or 300K tokens, whichever comes first, a strict one at 60% or 400K, Claude Code's auto-compact at 70% or 500K as the backstop, and a compact_now tool. All the lines are settings.
Szotasz/claude-mods
Focus mode: hides tool calls, intermediate text, your prompts and command output; shows only a subtask list with progress bars and the final answer. /fokusz toggles. Hungarian or English.
arasovic/claude-code-mods
Keeps secrets out of the conversation: hides API keys and private keys before the model or the transcript sees them, and blocks reads of credential files and commands that print secrets
arasovic/claude-code-mods
Shows a live session pane (/ctx): context breakdown, usage limits with pace, tool calls and model requests; sends the model a one-time note when limits or context cross a threshold, and can let the model compact or clear on its own
wdsewdser-bit/claude-code-mods
用户离开 5 分钟未回复待确认的问题时,提示模型自行决定;模型可调用工具暂停自动推进。
wdsewdser-bit/claude-code-mods
让会话里的模型自己重启 Claude 桌面版,并在重启后唤醒同一个会话继续干活。
wdsewdser-bit/claude-code-mods
Proactive context management: a task ledger, a searchable history and zero-summary window switches.
wdsewdser-bit/claude-code-mods
Hand a task to a cheaper model (any OpenAI chat-protocol provider) through a local Anthropic-to-OpenAI proxy; /delegate manages providers, keys and models.
wdsewdser-bit/claude-code-mods
Adaptive thinking effort for the main conversation only: rest at low, raise it by steps when judgement is needed.
wdsewdser-bit/claude-code-mods
Programmatic tool calling: run_code runs a JS program that calls read/glob/grep/edit/bash in a sandbox and returns only the final value; large results spill to refs.
proxify-dev/agentic-kit
WebFetchRaw, a tool beside WebFetch: it fetches a URL and saves the page's own content to a file, with no model in between, and returns one line naming the file. WebFetch returns a small model's answer about the page. An HTML page is extracted to markdown, text or cleaned HTML by trafilatura; anything else (JSON, text, a PDF) is saved byte for byte. A Claude Mod (needs...
ExtReMLapin/tqdm-claude
Claude Code mod: live tqdm-style progress bars above the prompt for background tasks and subagents, with crash and stall detection.
xuanji86/claude-mdview
Click a .md path in the Claude Code conversation to read it rendered as markdown beside the session, pictures included, and point at any block to have Claude edit it.
HigorAlves/orc
Full-SDLC Claude Code plugin — plan → implement → QA → ship → CI → release, with root-cause debugging, incident response, and dependency care. Hook-enforced guardrails, curated skills, model/effort-tuned agents.
h-zahran/delivery-kit
A side pane with robots: the main loop, every subagent and its tools, context, cost, rate limits and files touched
No tracking cookies, no third-party scripts. How we handle data