jr-nudges 0.1.0
At the end of a turn, one toast when the code Claude wrote added debug statements (console.log, print, debugger) or TODO/FIXME/HACK lines.
jrlprostInstall
/plugin marketplace add jrlprost/claude-code-mods /plugin install jr-nudges@claude-code-mods
Run both lines inside Claude Code.
Hooks into
- Tool calls
- Toasts
Also in jrlprost/claude-code-mods
-
jr-outputs
0.1.1
/jroutputs: every file this session created or changed, newest first, with + and - line counts from git.
jrlprost in Panes, updated
0
-
jr-dictation
0.1.0
Fixes what dictation mishears ("cloud code" → Claude Code) before Claude reads your prompt, and shows each fix in your prompt row: red struck, green added.
jrlprost in Prompt, updated
0
-
jr-commit-coach
0.1.1
Nudges you toward small atomic commits: when uncommitted changes pass a threshold, a band and a toast suggest a split by folder.
jrlprost in Git, updated
0
-
jr-done-check
0.1.0
Flags replies that claim something was tested or verified when nothing was run in the turn to check it: a warning under the message and a toast.
jrlprost in Guardrails, updated
0
-
jr-context
0.3.0
A context bar above the prompt: what fills the window, category by category, in a stacked colour bar with a legend, free space and the compaction point.
jrlprost in Themes, updated
0
-
jr-limits
0.1.0
Plan limits above the prompt: the 5-hour and 7-day windows as gradient gauges with reset countdowns, a toast at 80 % and 95 %, and /jrlimits for the detail.
jrlprost in Panes, updated
0
-
jr-cache-clock
0.1.0
A prompt-cache countdown above the prompt: how long the cache stays warm after Claude's last reply, going green to red, the last cache hit rate, and a toast 30 seconds before it goes cold.
jrlprost in Prompt, updated
0
-
jr-next-cost
0.1.0
What the next prompt costs before you send it: the context it resends, at the current model's price, read from a warm cache or written to a cold one, at API rates.
jrlprost in Usage & cost, updated
0
-
jr-quota
0.1.0
Balances of the other paid APIs you use (OpenRouter, Firecrawl, DeepSeek), checked every 10 minutes: /jrquota shows them all, a band and a toast appear only when one runs low.
jrlprost in Panes, updated
0
-
jr-read-cap
0.1.0
Stops Claude from reading a long file whole: a Read of a file over 1,000 lines without a range is refused with a hint to grep first and read only the lines it needs. Saves context and tokens.
jrlprost 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
249.8k
-
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
150.9k
-
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
74.7k
-
openviking-memory
0.7.11
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
39.9k
-
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
32.7k