lsp-first 0.5.3
Makes Claude actually use the TypeScript LSP: the LSP tool is loaded up front, the system prompt says when to prefer it, and symbol-shaped Greps over TS/JS get a nudge.
nbotondInstall
/plugin marketplace add nbotond20/claude-mods /plugin install lsp-first@my-mods
Run both lines inside Claude Code.
Hooks into
- Tool calls
- Toasts
- Slash commands
- System prompt
Also in nbotond20/claude-mods
-
budget-guard
0.16.1
Keeps token spend down: Opus capped at medium effort, compaction at 200k, context guard, subagent cap, image/generated-file read guard, and a budget HUD above the prompt (with LiteLLM key spend).
nbotond in Usage & cost, updated
0
-
usage-analytics
0.16.1
Records every model request, tool call, prompt, context breakdown, compaction and rate-limit reading from every profile into one store in the mods data folder, with a live dashboard, a weekly digest, shareable summaries, mod impact verdicts and a statistical advisor.
nbotond in Usage & cost, updated
0
-
lean-tools
0.5.3
Cuts what tool calls put into the context: caps huge shell output (full log kept on disk), bounds git log, and nudges toward parallel/batched calls, ranged reads, Edit over Write and no re-reads.
nbotond in Git, updated
0
-
no-attribution
0.3.3
Claude never credits itself: no Co-Authored-By, no 'Generated with Claude Code', no Claude author, in commits, PRs, files or tool calls
nbotond in Git, updated
0
-
timesheet
0.4.1
mod + skill
NetSuite-ready timesheets from your Claude Code and OpenCode sessions, git and GitHub history and Google Calendar: the timesheet CLI and web app, the timesheet skill, and /timesheet.
nbotond in Git, updated
0
-
observability
0.1.8
A free, local observability platform for Claude Code: Grafana with trace waterfalls, logs, metrics and dashboards (spend, latency, where time goes, errors, tools, hooks, MCP) for every profile, fed by Claude Code's own OpenTelemetry. Runs in Docker on 127.0.0.1; nothing leaves the machine.
nbotond in Usage & cost, updated
0
More guardrails mods
-
blast-radius
0.1.0
See what a risky command would change before it runs.
deepseek-ai in Guardrails, updated
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...
Anthropic in Guardrails, updated
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
ruvnet in Guardrails, updated
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.
OpenViking in Guardrails, updated
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.
claude-code-templates in Guardrails, updated
33.1k