effort-auto
wdsewdser-bit/claude-code-mods
Adaptive thinking effort for the main conversation only: rest at low, raise it by steps when judgement is needed.
9,065 mods
wdsewdser-bit/claude-code-mods
Adaptive thinking effort for the main conversation only: rest at low, raise it by steps when judgement is needed.
proxify-dev/agentic-kit
Agentic engineering kit: seven skills (context engineering, harness engineering, skill development, agent development, evals, sandboxing, fewer faster tests), most named by a short block a hook prints at the moment it applies; an agentic-engineer agent that starts with two of them loaded; /new-plugin, which makes your own plugin in a folder you pick; and /new-agent and /new-skill, which write...
proxify-dev/agentic-kit
How a session works with you and with its subagents. Two session modes, each [on|off|status], answered with no model call, Claude told once at each switch and reminded by one line on each prompt while on, a label in the prompt footer: /orchestrate hands parts to subagents on another model (haiku · sonnet · opus); /ask answers and changes nothing, refusing Edit, Write and NotebookEdit while on...
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...
axlaser/pitwall
A pit wall for Claude Code: a live box above the prompt (context, model, effort, git, tokens), a side panel of rate limits, the session's cost and who spent it, the prompt cache, the advisor and subagents you can stop, fourteen themes that repaint Claude Code, and alert sounds
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.
Ryan-LT/claude-mods
Come back to big chats for less. When a large chat (150k+ tokens) has been idle for 25 minutes, it is compacted while the prompt cache is still warm, so picking it up later is cheap. The summary keeps your last request, open tasks, decisions, file paths, commands and errors.
Ryan-LT/claude-mods
Never get surprised by a rate limit again. An always-on band above the prompt shows your 5-hour and weekly Claude usage with live bars, reset countdowns and context-window fill. It turns red when your pace will run out before the reset, and warns you at 75%, 90% and 100%.
Ryan-LT/claude-mods
Answer Claude in one click. After each reply, pills above the prompt suggest what you'd most likely say next (Yes, No, Confirm, Check it for me, the options it offered...), and clicking one sends it.
kgaidev/kgai
Experimental kgai add-on for Claude Code with function hooks: checks each code-editing turn for a structural decision on the side, records it without a line in the transcript, and draws kgai's own tool calls as one line each. Requires the kgai plugin.
declanbx/keepwarm
Keeps an idle interactive session's prompt cache warm with one tool-less fork just before the 1-hour cache lapses; /keepwarm on|off|status per session.
h-zahran/delivery-kit
A side pane with robots: the main loop, every subagent and its tools, context, cost, rate limits and files touched
PiPercentHuman/agentjournal
A memory for long jobs: your instructions pinned word for word with their updates, one line per action, a fold made by code when the context fills, and a clear of its own when the agent finishes a topic.
PiPercentHuman/agentjournal
Changes nothing. Writes every request's token counts and every compaction to .meter/log.jsonl.
PiPercentHuman/agentjournal
Answers compaction with plain code: the first message and the last few steps, nothing summarised.
Quinnod345/ponder
Convergent deliberation loop for coding agents - multi-pass, coverage-gated, append-only ledger review and planning.
shimo4228/harness-scope
Turn global skills, rules, agents and tools on or off per repo with named profiles. Add a one-line .claude/harness-scope.json to a repo; /harness-scope shows what is off
JinHang02/claude-code-pokemon
Your Pokémon party journeys through a pixel world above the Claude Code prompt: it runs while Claude works, cheers when tests pass, faints when they fail, levels up and evolves.
scodge-24/workface
Keeps a long-running agent's working notes through every compaction: briefs the summarizer, re-attaches the notes after the summary, and shows them in a panel you can steer.
pleaseai/honmoon
Client-side secret/PII redaction hooks: keep API keys and sensitive identifiers out of Claude Code's model context by redacting Read/Bash/Grep tool output, blocking prompts that carry secrets, and denying reads of known credential files. Session-transcript scrubbing verified on Claude Code 2.1.263 (updatedToolOutput is what gets persisted); re-verify on other versions.
zhebil/claude-code-plugins
Puts the Artifact tool behind tool search, so its ~12k-token schema loads only in sessions that publish an artifact.
zhebil/claude-code-plugins
Adds a /fork-new-tab command that forks the session into a new terminal tab (Warp, cmux or iTerm).
No tracking cookies, no third-party scripts. How we handle data