Automation

887 mods

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

★ 9GuardsAutomation

voice-compact

Tekkiiiii/the-agency

Startup token diet: rewrites the long CAVEMAN / PONYTAIL MODE ACTIVE hook-context injections into ~150-token compact rules (level kept, pointer to /caveman or /ponytail)

★ 9Automation

md-prompt

nogu66/md-prompt

Paints Markdown onto Claude Code's prompt box as you type: fenced code becomes a syntax-highlighted card (even before you close the fence), and inline code, bold, italic, lists, task lists, quotes, tables, links and headings are styled. Paint only, your text is never changed.

★ 9CommandsPromptAutomation

sysinit-output

roshbhatia/sysinit

One-pass local response cleanup without agent retries

★ 8Automation

cueloop

mmurakaru/cueloop

Claude Mod for cueloop Threads: plan, reply, prototype, diff, review, and refine

★ 8GuardsTools & agentsAutomation

public-repo-guard

Szotasz/claude-mods

Push guard: before a git push to a public GitHub repo (or making one public) it scans what would go out for Supabase project IDs, keys, tokens, emails, local paths, private repo names and .env files, and asks in a one-key popup. /pushor toggles. Hungarian or English.

★ 8GuardsCommandsAutomation

recall-cue

arasovic/claude-code-mods

Points the model, out of the user's sight, at saved notes whose words match the prompt: auto-memory files and any folders you add

★ 72 postsPromptAutomation

cc-restart

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。

★ 7GuardsTools & agentsAutomation

dispatch-gate

wdsewdser-bit/claude-code-mods

A soft gate on the main session: reminds it, then refuses once per stretch, to hand work to a subagent; and refuses one Claude subagent per hour past three.

★ 7GuardsPromptAutomation

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.

★ 7GuardsTools & agentsAutomation

ptc-run

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.

★ 7GuardsPromptTools & agents

read-dedup

wdsewdser-bit/claude-code-mods

Re-reading a file already in the context returns a one-line notice if unchanged, or only a diff if changed, saving context tokens.

★ 7GuardsAutomation

web

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...

★ 7GuardsTools & agentsAutomation

idle-compact

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.

★ 7Automation

agentjournal

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.

★ 7GuardsPromptAutomation

meter

PiPercentHuman/agentjournal

Changes nothing. Writes every request's token counts and every compaction to .meter/log.jsonl.

★ 7Automation

plain-cut

PiPercentHuman/agentjournal

Answers compaction with plain code: the first message and the last few steps, nothing summarised.

★ 7Automation

honmoon-redact

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.

★ 7GuardsPromptAutomation

bash-history

Plagemes/claude-mods

/bash-history lists recent shell commands Claude ran, with exit status and duration.

★ 7GuardsCommandsAutomation

big-read-guard

Plagemes/claude-mods

Stops full reads of huge files and nudges toward offset/limit or grep.

★ 7GuardsAutomation

bookmark

Plagemes/claude-mods

/bookmark saves the last answer; /bookmarks lists and reuses them.

★ 7CommandsAutomation

branch-namer

Plagemes/claude-mods

/git-branch creates a well-named git branch from a short task description.

★ 7CommandsPromptAutomation

cheatsheet

Plagemes/claude-mods

/cheat shows a quick reference for git, docker, regex, tmux and more, offline.

★ 7CommandsAutomation

cloud-cost-warn

Plagemes/claude-mods

Warns before commands that create expensive cloud resources like GPU instances or large databases.

★ 7GuardsPromptAutomation