write-guard 0.1.0
Steers Claude to Edit instead of rewriting an existing file in full with Write: the first rewrite in a conversation goes through with a one-line note, a later one is held back once; a deliberate retry still goes through.
Install
/plugin marketplace add VedantAndhale/claude-pro-kit /plugin install write-guard@claude-pro-kit
Run both lines inside Claude Code.
Hooks into
- Status line
- Tool calls
Also in VedantAndhale/claude-pro-kit
- peek 0.1.0 Typing "status" while background shells or subagents run opens a pane with each task's exact elapsed time, the tail of its output and any percent it printed, instead of sending the prompt to Claude. /peek opens it too. No tokens spent. 4
- skill-diet 0.1.0 Lists skills you have not used lately in this project by name only, so their descriptions stop riding along on every request; the Skill tool and /name still load any of them. No model calls. 4
- agent-diet 0.1.0 Runs search-only subagents (Explore by default) on Haiku instead of your main model; a model Claude asks for still wins, and /agent-diet picks the types and the model. 4
- loop-guard 0.1.0 Holds back a shell command once when the exact same command already failed twice in a row, and tells Claude to change approach; retrying it still goes through. 4
- cmd-diet 0.1.0 Adds quiet flags to noisy shell commands before they run (git status, pytest, cargo, npm install, mvn, curl, wget, docker pull), so Claude reads short output from the start; errors, failures and warnings stay in full. 4
- compact-keeper 0.1.0 After a compaction, adds one message with exact facts from before it: your latest prompt in full, up to 4 earlier ones, the files edited, the todo list and the last failed shell command. At most 4,000 characters. No model calls. 4
- gh-account 0.1.0 Runs each git push, pull, fetch, clone and gh command as the logged-in GitHub account that owns or belongs to the repository's owner, so Claude stops switching gh accounts and retrying failed pushes. 4
- prompt-polish 0.1.1 An Improve button above the prompt (and /polish) rewrites your draft with Opus at low effort (/polish model picks another) using the prompt-master rules (MIT, nidhinjs/prompt-master); Undo puts the original back. Each press is one model call; its exact tokens are shown. 4
- turn-budget 0.1.2 Asks before a single turn uses more than +5 session points or 500,000 uncached input tokens, and stops it cleanly if you say so. Checks between requests, never mid-command. 2
- session-receipt 0.1.0 /receipt opens a pane with the exact tokens every turn of the session spent (uncached, cached, output, subagents) and the costliest turns. No tokens spent. 2
More guardrails mods
- blast-radius 0.1.0 See what a risky command would change before it runs. 245.3k
- 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... 149.8k
- ruflo-rvf 0.3.5 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 74.1k
- openviking-memory 0.7.3 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. 39.4k
- 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. 32.5k