done-gate 0.1.0
Blocks Claude from ending a turn while code under guarded paths differs from the working tree that last passed the repository's check command. Proof is a git tree id of the whole working tree, so edits through Edit, Write, Bash or a subagent all count. Blocks once, then lets the turn end with a t...
JStarInstall
/plugin marketplace add Allmight97/agents /plugin install done-gate@personal
Run both lines inside Claude Code.
Hooks into
- Tool calls
- Toasts
Also in Allmight97/agents
-
complexity-lens
0.1.4
Shows complexity, density and hotspot score for files Claude reads or edits.
JStar in Prompt, updated
0
-
session-meter
0.2.1
Session meter as one compact line above the Claude Code prompt: context-window fill, five-hour and weekly plan-limit use, and prompt-cache use with a live countdown to the cache's expiry and what to do about it (keep going, compact or clear). /meter opens a pane with context and limit bars and re...
JStar in Usage & cost, updated
0
-
nested-agents-md
0.1.1
Loads nested AGENTS.md for files Claude touches through Bash, Edit or Write, where the built-in agents-md mod loads them only on Read.
JStar in Guardrails, updated
0
-
explore-model
0.1.0
Runs the built-in Explore subagent on a chosen model and effort (default Haiku, medium) whenever the Agent call leaves them out. Keeps Anthropic's Explore prompt and read-only tools; a call that names its own model or effort keeps it. Needs function hooks (early access).
JStar in Guardrails, 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
250.6k
-
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
151.1k
-
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
75.2k
-
openviking-memory
0.7.12
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
40k
-
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