Claude Code mod
sieve
Keeps unnecessary tool output out of context in Claude Code and Copilot CLI, with a shared local strands-decider for close calls.
Install
git clone https://github.com/trsdn/sieve.git
claude --plugin-dir ./sieve/.The repo has no marketplace file, so load the plugin folder directly with --plugin-dir.
What it can access
- Reach
- L3Network: network, runs processes, writes files, drives Claude, reads files, reads env vars, persists state, draws
- Sees
- mcp__sieve__search calls, every tool call, compaction, every prompt
- Hooks
session.startcommand.runtool.callsession.compactprompt.composeturn.stepprompt.submit
From a static scan of the mod's code by awesome-claude-code-mods. It shows what the code asks for, not a security review.
How Claude Code mods work
- A mod is a plugin with a JavaScript or TypeScript module that runs inside Claude Code (version 2.1.287 or later). It can draw panes beside the transcript, a band above the prompt, buttons and toasts, restyle the spinner and tool rows, and watch or rewrite tool calls and prompts.
- It installs like any plugin: add its marketplace with /plugin marketplace add owner/repo, then /plugin install name@marketplace.
- Check what a mod can reach before installing: it runs with your permissions. Reach goes from drawing only, to reading files, to writing files or running processes, to the network. Run claude plugin validate on a clone to list its hooks and calls without running it.
- Turn one off from the Installed tab in /plugin, or start Claude Code with --safe-mode to skip every customization for a session.
Details
- Repository
- trsdn/sieve
- Folder
.- Last updated
- 5 October 2026
- Listed in
- awesome-claude-code-mods
FAQ
What is sieve?
Keeps unnecessary tool output out of context in Claude Code and Copilot CLI, with a shared local strands-decider for close calls. It is a mod for Claude Code, from trsdn/sieve on GitHub.
What can the sieve mod access?
Its widest reach is "network" (network, runs processes, writes files, drives Claude, reads files, reads env vars, persists state, draws). It sees mcp__sieve__search calls, every tool call, compaction, every prompt. Like any mod, it runs with your permissions.
How do I install sieve?
Clone trsdn/sieve and start Claude Code with --plugin-dir pointing at the mod's folder (.).
More context & usage mods
sidechat
gabedeluna/claude-mods
A side panel for questions about the current session: it reads the conversation from cache, looks things up read-only, recaps, says what the main thread is doing, draws diagrams as artifacts and sends a note to main.
sisomewhere-usage
shissncg/claude-mods
Saves Claude Code's plan limits (5-hour and weekly) to a local file for the SI Somewhere agent
show-work
five82/claude-mods
Shows what Claude is running and adding to the model's context, the way pi does: every tool call on its own row, the end of Bash output, how long each call took, injected context, and a spinner naming the running call.
skill-counter
ganbaroff/ai-guardrails-kit
Counts every skill expansion (typed /name, the Skill tool, a preload) in the plugin store, across sessions; /skill-usage shows the table. Observe-only: never changes what the model reads. No files, no network. English by default, Russian by a one-line switch.
shouldnt-you-know
shihchengwei-lab/cc-mod-shouldnt-you-know
After Claude edits code, a side look at the task and the change shows one plain-language structural note above the prompt; it never enters Claude's context.
skill-map
vuon9/cc-mods
Pane showing which skills are loaded into the main conversation, how big they are, and where in the context window they landed
Browse the most popular Claude Code mods, all context & usage mods, or the skills and MCP server directories.