transcript-compress 0.1.0
Compresses old Claude transcripts in place to free disk space, losslessly: Windows and macOS use the file system's own compression, so /resume still works. Off by default: Claude suggests it at a natural break when a lot is waiting, or turn on Always on.
Install
/plugin marketplace add ychampion/ystack /plugin install transcript-compress@ystack
Run both lines inside Claude Code.
Hooks into
- Prompt
- Tool calls
- Toasts
- Slash commands
- Model tools
Also in ychampion/ystack
- image-theme 0.1.1 Turns a picture you choose into your Claude theme: the picture becomes the app background, softly veiled with a frosted column behind the chat, and the theme colours are taken from it. /image-theme opens a file picker. 4
- living-themes 0.1.0 Animated backdrops behind the chat in the desktop app that react to what Claude is doing (thinking, running tools, subagents, a failure, a merge) and follow your local time of day and season; /live-theme picks one. 2
- iron-rules 0.2.1 House rules on shell calls, each off until you turn it on in /config: bun instead of npm, your git commit identity, no AI attribution in commits and PRs. Always blocks nested Windows shell deletes, whose quoting breaks. 1
- verify 0.2.0 Verify gate for the main loop and every subagent: no success claim without a real check. Optional live runner of only the tests related to each edit (opt-in: it runs the project's own test scripts). 1
- brief-linter 0.1.0 Appends the missing standing requirements (real check, long output to a file, Assumptions I made, loop cap, decision inbox) to every subagent brief. 1
- assumptions-ledger 0.3.0 Logs every subagent's 'Assumptions I made' and hands them to the main Claude to triage; only product or business calls reach the owner, via the decision inbox with context. 1
- decision-inbox 0.3.0 A non-blocking ask tool for owner decisions from any session or subagent, one inbox pane to answer them in a batch, answers delivered back to whoever asked. 1
- spec-sharpener 0.1.0 On a large, open build request, has the main model ask 3-4 pointed questions before building (no side model, ~80 tokens). /sharpen on|off. 1
- review-panel 0.1.1 /review-panel: picks the specialist reviewers from the diff and has the orchestrator dispatch them on Opus in parallel, then verify findings. On demand only. 1
- context-meter 0.4.1 Keeps long sessions cheap. /handoff writes a handoff in one turn and swaps the conversation in place for it (no /clear; background agents keep reporting). Between turns it acts by itself: hands off after a push or merge on a big context or when a session is running on its own, and before the prom... 1
More prompt mods
- ruflo-ruos 0.1.2 mod + skill Run ruflo swarm agents on your own ruOS cloud desktops via the tenant-authenticated fleet MCP or per-tenant SSH; optional and removable (ADR-405) 82k
- pet 0.2.0 A virtual pet above the Claude Code prompt that grows as Claude works: passing tests, commits and edits grant XP and mood, failing tests cost mood, idling drains it; egg → baby → kid → adult → legend. Zero tokens. Split out of cc-arcade (MIT, Seza Akgün). Needs an interactive terminal. 33.9k
- plannotator 0.28.67 Interactive Plan Review: Mark up and refine your plans using a UI, easily share for team collaboration, automatically integrates with plan mode hooks. 13.1k
- vsr 0.1.10 mod + skill vSR runs a vLLM Semantic Router decision model (local CPU, local GPU or remote) inside Claude Code: routes subagents by difficulty, escalates when you push back, redacts personal data and secrets, shields against prompt injection, guards risky Bash commands, and checks answers against what Claude... 6.4k
- next-steps 1.0.0 After each turn, suggests up to three next prompts above the input. Press 1, 2 or 3 to put one in the prompt box as a draft you can edit, 0 to dismiss. 4.9k