action-log 0.1.0
Writes one line per tool call, from every session including scheduled runs, to ~/Developer/claude-mods/logs before the call runs (no log, no run), plus how it ended. /log shows today. Paths and commands only; keys masked. Uses no AI.
Install
/plugin marketplace add ccbuildalot23/claude-mods /plugin install action-log@chris-mods
Run both lines inside Claude Code.
Hooks into
- Tool calls
- Slash commands
Also in ccbuildalot23/claude-mods
- bridge-inbox 0.1.0 /bridge-inbox reads new Grok-bridge messages to Claude Code, gives each a three-line summary, flags anything that needs your yes, and acks or archives by the bridge protocol. Reports only; never acts on a message's ask. One small AI call per new message. 0
- crew 0.1.0 Gives every subagent a name, its own color and a character, and shows live what each one is doing and how far along it is, above the prompt and in a /crew panel. Uses no AI. 0
- lightweek 0.1.0 /lightweek tells every Claude session on this Mac (Rig seats and scheduled runs included) to keep to essentials for seven days, or the days you give; a quiet line shows it's on. /lightweek off ends it. Uses no AI. 0
- needs-you 0.1.0 A desktop notification when Claude finishes a long turn or is waiting on you (permission or idle prompts). Silent during quiet hours from config/clock.json; what came in is summed up once they end. /needsyou on|off. Uses no AI. 0
- outbox 0.1.0 Holds anything that leaves the Mac in your name (messages, replies, posts, comments, invites, shares, deploys, git push, asset approvals) until you type /outbox release <id>. Drafts pass. Uses no AI. 0
- privacy-preflight 0.1.0 Checks every write headed somewhere shared (grok-bridge, the LaBeau site, Airtable, Notion, Drive, posts, email) for private names on your list, private-life words, keys, future bridge timestamps and bad bridge file names, and blocks it before it lands. /preflight allow <id> lets one through. Use... 0
- blast-radius 0.1.1 Stops risky commands (deletes, hard resets, force pushes) and shows what they would hit before a person presses Proceed; hard-blocks writes to Chris's pen-rule folders. 0
- brain-dump 0.1.0 Catches long, messy voice brain dumps before Claude reads them and offers to tidy them into a clear prompt (task, why, guardrails, done looks like, open questions). Off until /braindump on; tidying uses one small AI call. 0
- browser-peek 0.1.1 The terminal-browser mod: /peek URL takes a headless Chrome screenshot of a page (a site Claude built, a pull request) and shows it in a panel beside the chat, so you review without leaving Claude Code. Fresh Chrome profile, no logins. Uses no AI. 0
- cache-clock 0.1.0 Shows how long until this chat's prompt cache goes cold, warns before a cold message re-reads the whole chat at full price, and /keepwarm pings it cheaply while you step away (up to 2 hours). 0
More guardrails mods
- blast-radius 0.1.0 See what a risky command would change before it runs. 269.9k
- agents-md 0.1.0 AGENTS.md as project instructions, by one option. Under claude-md-or-agents-md a project with no instruction files of its own gets its AGENTS.md files instead: a prompt.context hook asks $.fs.ancestors for every AGENTS.md and .claude/AGENTS.md from the filesystem root down to the working director... 154.3k
- ruflo-rvf 0.3.7 mod + skill RVF format for portable agent memory, session persistence, and cross-platform transfer. As a mod (ADR-445): a write guard that keeps secrets out of memory, sessions and transfers, /rvf-mod, and a status file the console shows 80.7k
- openviking-memory 0.7.21 mod + skill Long-term semantic memory for Claude Code, powered by OpenViking. Auto-recall relevant memories at session start and capture important information during conversations. 41.4k
- tool-timing-badge 0.2.0 Times every tool call and wraps the engine's ToolUse rendering with a colored duration badge from the surface's own element table, on the terminal, Desktop and mobile. Hooks tool.call and ui.render using JSX. 33.1k