Toasts

Verbatim Jev-guided compaction for Claude Code sessions.

Two cuelume sounds for Claude Code: ready when a long turn ends, attention when a permission prompt waits.

Verbatim Jev-guided compaction for Claude Code sessions.

Trim long Bash output with Jev before the model sees it (Claude Code plugin)

Solo PM conveyor for Claude Code: orchestrator agents, lane playbooks, onboard and resume commands.

A calibrated context sieve for Claude Code. Every large tool result is judged by a System One model before it enters context; irrelevant blocks are replaced with a summary and a recall key.

Writing and git rules: replaces em dashes in prose, and asks before git commit --amend, an unformatted push, or personal info in notes and commits.

Jev decides when the session compacts, inside a 280k–400k token band; Claude's own summary does the compacting.

Harness Mod layer: heartbeat/canary, native usage, rewrite explanations, measured subagent accounting, supervisor routing, secret redaction. Modes per guard in ~/.claude/mods/mods-config.json (classic | shadow_mod | mod).

GUARDIAN: executable policy that protects lab/demos/protected/** from Write/Edit/Bash, whatever CLAUDE.md says

Spike: safe-boundary handoff (bundle written at turn.complete from the runtime bus) and $.turn.abort semantics

Cheap, fast, typed AI judgments inside Claude Code via the jevctl CLI (verify, screen, find, classify, extract, rerank, match, route, ask, batch), plus verbatim Jev-guided context compaction that replaces the built-in summary.

Probability-scored guardrails for Claude Code: deny rule-breaking edits and unasked-for deploys, route your own docs into each prompt, and check the final answer against the turn's own evidence.

Gives the model a Gemini advisor tool it calls by itself: Gemini reads the whole conversation and the model's message and answers with a second opinion. Off until /gemini-advisor on; gemini-core holds the key, tier, model and thinking level.

Moves compaction from Claude to Gemini: in summary mode Gemini summarizes the conversation and the newest messages stay verbatim, in prune mode every message stays and Gemini keeps, cuts or drops older tool calls. Off until /gemini-compact on; gemini-core holds the key, tier, model and thinking level.

Has Gemini review each plan before the approval dialog, from the plan and the conversation, and sends a plan with a blocking finding back to the model, at most twice. Off until /gemini-plan-review on; gemini-core holds the key, tier, model and thinking level.

Has Gemini review every git commit the model runs, from the staged diff and the conversation, and stops a commit with a blocking finding: a bug, data loss, a security hole or a committed secret. Off until /gemini-review on; gemini-core holds the key, tier, model and thinking level.

Replaces Claude Code's compaction with a structured handoff: a fork of the session writes it from the prompt cache, and the conversation continues from exactly that handoff.

Saves each compaction's summary, with the files edited before it, to ~/.claude/handoffs so the context before /compact can be recovered

Tells the model, out of the user's sight, to stop when the same call fails twice with the same error

Detects a session that was cut off mid-turn (restart, crash) and drafts the standard pick-up prompt; /resume-here sends it.

Keeps secrets, email addresses and IP addresses out of the session transcript: swaps each one for a stable placeholder on the way in, and puts the real value back on the way into a tool call

Deterministic local compaction for Claude Code: replaces the stock compaction summarizer with the local UltraCompress binary (no model call, no API cost per compaction) and serves a recall tool over the raw session transcript.

Notices when Claude is going in circles (the same command failing again and again, the same code rewritten over and over) and tells Claude to step back and rethink, and tells you too.