Automation

887 mods

cache-guard

mgstegmaier/claude-plugins

When a send would re-write a cold prompt cache, a dialog shows the estimated cost with Proceed and Start new session buttons. Adapted from Karan Bansal's cache-tax (MIT). Needs Claude Code 2.1.287 or later.

★ 0PromptAutomation

subagent-router

ekinertac/claude-code-mods

Picks a model for each subagent from its task: small models for lookups, big models for hard work, while the main thread keeps its own model

★ 01 postsCommandsAutomation

loop-breaker

joaosavi/cockpit

Notices when the agent goes in circles (repeated fix attempts on one file, the same error coming back, the same call repeated) and tells it to stop and change approach; refuses nothing.

★ 0GuardsAutomation

panel

joaosavi/cockpit

A local web page with a card for every Claude Code session on this machine: whether it waits for you, what it needs, what it is doing, with a summary from claude -p every few minutes and a refresh button.

★ 0CommandsAutomation

pipefail

joaosavi/cockpit

Adds set -o pipefail to a command that pipes a test, typecheck or lint run into tail, head or grep, so a failing run cannot exit 0 and read as a pass.

★ 0GuardsAutomation

recall

joaosavi/cockpit

Searches the ai-memory server for the words of each request and adds the best matching memory pages to it, as the hook's suggestions, without a model. Reaches the server through the ai-memory CLI, or through an MCP gateway when that fails.

★ 0PromptAutomation

secret-guard

joaosavi/cockpit

Hides every secret value in tool output as before the agent reads it, MCP and subagent output included, and writes the real value back when the agent puts the placeholder into a .env or secrets file.

★ 0GuardsAutomation

skill-loader

joaosavi/cockpit

Loads the right skill at the right moment, so CLAUDE.md needs no load-this-skill rules: typescript-best-practices for .ts, writing-for-agents for SKILL.md, AGENTS.md and CLAUDE.md, domain-modeling for CONTEXT.md and ADRs, technical-writing for READMEs, commits and PRs, and a diagnosing-bugs reminder when you paste an error.

★ 0GuardsPromptAutomation

todo

joaosavi/cockpit

Keeps the native task list in front of the agent: the open tasks at session start and right after each compaction, a reminder that a new request becomes a task before any other work, completed tasks logged to an archive, and the app's task panel kept in line with the task files.

★ 0GuardsPromptAutomation

monitor-rearm

nnemirovsky/cc-monitor-rearm

Keeps Claude Code's long Monitor watches running past the 30-minute cap, so their expiry no longer wakes Claude or spends a turn

★ 0GuardsPromptAutomation

deferred-answers

0langa/claude-code-mods

Keeps 'later', 'not yet' and 'after X' answers to Claude's questions open: the question and your answer are attached to every later message until the item is done or dropped, so you never have to remind Claude.

★ 0GuardsCommandsPrompt

no-ai-trailers

0langa/claude-code-mods

Keeps the Claude co-author trailer and the Generated-with footer out of your commits and pull requests: the model is told not to write them, and any that slip into a git commit or gh pr command are removed.

★ 0GuardsCommandsPrompt

studio-state

0langa/claude-code-mods

Gives Claude a studio_state tool for a studio-layout video repository: one compact answer on where a video project stands, instead of a dozen file reads. Silent in every other folder.

★ 0GuardsTools & agentsAutomation

tool-output-diet

0langa/claude-code-mods

Trims shell output before Claude reads it: colour codes, overwritten progress-bar frames and long runs of identical lines. Nothing else is touched.

★ 0GuardsCommandsAutomation

compact-brief

Gooner44/ClaudeMods

Tells Claude Code's compaction what to keep: your own words near verbatim first, then what changed, then findings, with tool output described in a few words

★ 0Automation

compact-tail

Gooner44/ClaudeMods

Automatic compaction summarizes only the older part of the conversation and keeps the latest part word for word; a reopen tool brings back anything summarized, from a local archive

★ 0GuardsTools & agentsAutomation

jev-tool-gate

m2ai-portfolio/claude-mods

Log-only Jev judgment of risky tool calls (destructive? requested by fetched content?). Never changes a decision; hosted calls off by default.

★ 0GuardsCommandsPrompt

verify-gate

alanrsoares/claude-mods

Asks before git commit or gh pr create while edited code has not passed a check command since its last edit.

★ 0GuardsAutomation

long-turn-notify

wonjangcloud9/wj-mods

2분 넘게 걸린 작업이 끝나거나 선택 창·권한 확인 창이 뜨면 맥 알림과 세션 이름 음성으로 알려 준다

★ 0GuardsPromptAutomation

long-turn-notify-team

wonjangcloud9/wj-mods

2분 넘게 걸린 작업이 끝나거나 선택 창·권한 확인 창이 뜨면 맥 알림과 세션 이름 음성으로 알려 준다. 조직 계정에서도 권한 확인 창을 세션 기록으로 알아낸다 Team·Enterprise 계정용이다.

★ 0GuardsAutomation

plain-korean

wonjangcloud9/wj-mods

결론부터 쓰고 흐름은 글자 그림으로 보여 주는 해요체 한국어 답변 스타일, 영어로 새는 답변 경고, 가독성 mod 3개, claude-warm 테마를 한 번에 설치한다

★ 0PromptAutomation

plain-summary

wonjangcloud9/wj-mods

보고서처럼 긴 답변 아래에 작은 모델이 쓴 두 줄 쉬운 요약을 붙인다

★ 0Automation

dev-kit-jev

vitoliu93/harness-dev-plugins

Optional Claude Mod: contextual skill recommendations through Jev.

★ 0PromptAutomation

git-guard

alokm3hta-star/Claude-Mods

Keep Claude out of your git history: no co-author trailer, no PR footer, and no push of a commit that carries one

★ 0GuardsPromptAutomation