Claude Code Mods

wdsewdser-bit/claude-code-mods

Observes prompt-cache usage, keeps the session's and its finished subagents' caches warm, and runs 5m/1h TTL A/B experiments.

partalemre/MODZ

A Claude Code mod that keeps the one-hour prompt cache warm during breaks and holds a cold send, after a break or a model change, on a card with its estimated rewrite cost. Warming uses model requests and costs tokens. Requires Claude Code 2.1.287+.

ahmadhammoud56/MOAA

strata at a glance: context against the handoff threshold, canary hits and misses, memory waiting for extraction, engine pause, and the Obsidian vault

bendrucker/claude

Warn the model mid-turn as the 5-hour or 7-day limit nears

ucsandman/Agnostic-AI

Permission override, subagent visibility, agent.spawn model rewrite, turn.step routing, prompt context injection

arasovic/claude-code-mods

Blocks shell commands you pick in /config: Cloudflare cf writes, attribution lines in commits and PRs, claude/ branch names. All rules start off

Szotasz/claude-mods

Snake in the side pane while Claude works: opens when you send a prompt, pauses when the turn ends, keeps your best score. /jatek be|ki. Hungarian or English.

MongLong0214/jev-gate

Task-aware extractive compaction with bounded Jev dependency selection and the native recent tail; on by default.

KilimcininKorOglu/claude-code-mods

Asks a council of models about a hard problem, when the model calls its tool or you run /council <question>: Claude models, and Gemini models when gemini-core has a key, answer in parallel, and the model of the session writes one verdict from their answers.

mishgoldenberg/claude-mods

Before a vague prompt is sent, suggests a sharper rewrite; you choose: send improved, send yours, or edit the suggestion. Never rewrites silently.

VedantAndhale/claude-pro-kit

Stops Claude re-reading a file it already read in this conversation, with Read or a plain cat, sed -n, head, tail or Get-Content, when the file has not changed since; a deliberate second attempt still goes through.

whyashthakker/awesome-claude-code-mods

Run a 25-minute focus countdown with pause, reset, and a toast.

mako-code/gobworks

Measures a command: warmup and timed runs, median/p95/stddev and outliers, two commands compared or a saved baseline per project, and a pane with a block distribution plot. Bounded, one at a time, never during Claude's turn unless Claude asked.

hacksurvivor/claude-mods

Paste a link with a short question and Claude's answer opens with a verdict for your projects: use it, later or skip, the effort, the cost and one line why

Heuwzen/claude-runway

A quiet reminder in the status line and a toast when uncommitted work piles up in the chat's project

tridha643/claude-composio-mods

Standup pane, seen-this-before error lookup and agent-busy Slack status, through the Composio CLI

Xabilimon1/emcc-claude-code-mods

EMCC's shared base: the $.emcc noun (evidence of tests, builds, lints and edits; badges; profile; kill switch) and one status band above the prompt.

Akeuuh/claude-mods

Jev decides when to compact, on every turn and on demand, and picks where the live work starts

robinalexandre/claude-code-kit

Learn while working: Claude ends a reply with a short, precise point on the security, architecture or pattern behind the code at hand. /learn off|brief|normal|deep per session, shown in the status line as and the level.

cjavdev/mods

Links in the bar under the prompt to the artifacts and pull requests mentioned most recently in the conversation.

cpeaustriajc/cj-stack

Ends a turn after N forced Stop-hook continuations so a looping goal hook cannot burn your usage

musingfox/cc-plugins

[Experimental] Every ```mermaid block Claude writes drawn as plain box art in place in the transcript — flowchart, sequence, class, state and xychart; CJK labels aligned (Claude Mod fork of claude-mermaid; needs Claude Code 2.1.287+)

iuliandita/mods

Desktop notification when the agent finishes or waits on a permission prompt or other input, titled with the repo and harness, the branch in the text, and an optional sound. Uses notify-send on Linux and osascript on macOS; makes no network or model calls.

ShriD5/claude-mods

Approve or deny Claude Code's permission prompts from Telegram, with the terminal prompt as the fallback.

joeldg/claude-mods

/second-opinion asks Fable (or the model you set) for a candid senior review of your recent commits, branch, uncommitted diff or a plan file, in the background without switching the session's model. Each run is one paid model call against your usage; the review opens in a pane, is saved under ~/.claude/second-opinions/, and can be handed to Claude with your next prompt.

MichaelP17/claude-mods

Passes prompts from a planning session to the session that does the work and its answers back, without copy and paste

DarkSawOktay/claude-mods

Usage tracking for Claude Code: 5-hour and weekly quota left, context, session cost, run-out forecast, saving tips, 7-day history and shared themes for every mod. French or English.

NateCC0902/NeonCoat

Draws a test or type-check run's output as one count line with its failures under it, the passing tests folded away (terminal)

Ankitrai97/rai-claude-mods

Your Claude plan usage inside Claude Code: session (5h) and weekly limits with reset countdowns in the status line, a /tally pane with bars, and warnings at 75% and 90%.

lemomo-ai/lemo-mod

换皮：消息加编号 T01、T02，回复标注「回复 T03」，工具行和耗时行使用风格样式 / Skin: messages numbered T01, T02, replies marked "Reply T03", tool rows and turn lines use the style

promptadvisers/claude-mods-starter-kit

Coral, ink and cream reskin of Claude Code with risk-coded tool rows. Toggle with /skin.

ersinkoc/claude-mods

KOZMOS Switchboard: an MCP observatory sidebar. Every MCP server in the session with its tools, calls, errors, average and p95 latency, last call and a status lamp (healthy, erroring, idle, busy); servers with no calls yet too, and per-tool rows on expand. On the desktop a patch bay with glowing cables to the active servers. /switchboard toggles it.

hoobnn/hoobnn-agent-mods

A line from Hitokoto (一言) in a band above the prompt, refreshed on a timer, per session, per prompt or once a day

charlie947/mod-maker

Find what you ask Claude again and again, then build a mod that does it for you: /mod-audit, /mod-build, /mod-check and a habit spotter

Singh-AP/awesome-claude-mods

Defuses prompt injection in tool output: strips invisible Unicode that hides text from you but not from the model, and flags web pages, files and command output that carry instructions aimed at Claude.

FynnXland/fynn-mods

Claude Code's own next-message suggestion as a button above Clawd; click it, type 1 in the empty prompt, or send just 1 to send it. With /replies more on, a fork of the session fills up to four places in total. /replies help shows all commands and settings as a table.

oMaN-Rod/claude-code-widgets

Which of the commands and edits Claude has made in this project would stop for permission or be refused right now, asked of the engine's own permission check without running anything

theonly1me/claude-code-mods

Tanjiro, Nezuko, Zenitsu, and Inosuke take turns against demons up to Muzan as you and Claude work, and spar between strikes. The story continues every session.

Hula-Hoop-AI/supermods

Band above the prompt that shows the context window as a tide: a fill bar, the trend per turn, a sparkline of recent turns and how many turns are left before compaction.

T-AI-Labs/claude-code-mods

One row above the prompt: how much of the 5-hour and weekly usage limits is used, in percent, with the time until each resets.

IT-Shelter-Labs/Claude-Mods

A Claude Code mod from IT-Shelter-Labs/Claude-Mods.

OneWave-AI/claude-code-mods

Race Claude Code sessions on a task: live split-screen race track scoreboard

whyashthakker/awesome-claude-code-mods

Save reusable prompts and put one into the composer as a draft.

bengous/claude-code-plugins

A grill where you answer before you see Claude's recommendation: Claude writes each round of questions in its reply, the chat hides every recommendation, and a pane beside it collects your answers and shows a recommendation only when you peek at it

mutlumehmet/claude-plugins

Refuses a shell write to a shared file (STATUS.md, CLAUDE.md, MEMORY.md, or the files you name) that this session has not read, or that another session changed since

ucsandman/Agnostic-AI

GUARDIAN: executable policy that protects lab/demos/protected/** from Write/Edit/Bash, whatever CLAUDE.md says

bendrucker/claude

GitLab workflow best practices and glab CLI usage

lemomo-ai/lemo-mod

音效：调用工具、一轮结束、限时中止时播放提示音 · 默认关闭，在「安全」页开启 / Sounds: plays sounds on tool calls, turn ends and time-limit stops · off by default, switch on in Safety