rule-promote 0.1.0
Counts what self-audit, done-gate and assertion-guard flag across sessions and offers a rule flagged again and again as a standing rule; an approved rule goes into the system prompt from the next session; /rule-promote
Install
/plugin marketplace add simota/claude-mods /plugin install rule-promote@simota-mods
Run both lines inside Claude Code.
Hooks into
- Prompt
- Toasts
- Slash commands
- System prompt
Also in simota/claude-mods
- handoff 0.1.0 Picks up where the last session in this repository left off: its last ask, open TODO(agent) items, side effects whose undo nobody checked, checks left red and unverified edits, shown above the prompt and put into it in one press; /handoff 1
- doc-preview 0.1.0 Previews the documents Claude writes in docview: the band above the prompt offers the Markdown, diagram, data or HTML file a turn changed, opens it in the browser at the edited line, and the open tab follows later edits by itself; /docview lists them 1
- review-mods 0.2.0 Three second opinions in one press: the band above the prompt reviews the current diff with claude, codex and agy in parallel (read-only), merges what they found into one list with who found each, shows the top finding and the count, and puts the findings into the prompt for Claude to fix when as... 1
- design-duel 0.1.0 A design contest in one command: /design-duel <topic> has claude, codex and agy each propose a design alone (read-only), then score each other's proposals under anonymous labels with their strongest objection; the mod tallies the scores, the band names the winner, and the winning design goes into... 1
- stack-dock 0.1.0 The repository's devrouter stack in one press: the band above the prompt says whether it is unset, stopped or up, starts it with devrouter up, shows each service's URL and health in the status line and a /stack pane, and puts doctor's findings and the failing logs into the prompt for Claude to fi... 1
- cross-check 0.1.0 A second opinion from Codex in one press: the band above the prompt reviews the current diff with codex exec (read-only), shows the top finding and the count, and puts the findings into the prompt for Claude to fix when asked; a /codex pane lists them 1
- ci-rehearsal 0.1.0 CI before the push, in one press: the band above the prompt runs the push workflows with runthrough, shows the failing job and step with the count, and puts the failures and their log tails into the prompt for Claude to fix when asked; /ci lists every job 1
- kachi 0.1.0 When a check you broke turns green after a real fix, the band above the prompt sweeps green once with a short click, and the result row keeps the score; silent the rest of the time but for one dim line on a check's first red 1
- perf-delta 0.1.0 /perf runs a benchmark command several times and compares it with its baseline (saved earlier, or a git ref run in a temporary worktree): median wall time, peak memory and the spread of the runs, and whether the difference is larger than the noise 1
- assertion-guard 0.1.0 Catches edits that weaken tests to make them pass: assertions removed, expectations loosened or rewritten, tests skipped, exceptions swallowed; asks Claude for the reason beside the tool's result and keeps a band until the person has checked it 1
More guardrails mods
- blast-radius 0.1.0 See what a risky command would change before it runs. 283.1k
- 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... 156.1k
- claude-mem 15.12.1 mod + skill Persistent memory for AI coding agents: the next session starts where the last one left off. Works with Claude Code, Codex, Cursor, OpenCode and more. 114.9k
- 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 82k
- openviking-memory 0.7.25 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. 42.4k