All mods
3,429 mods. Every one passed the check.
- usage-percent 0.2.0 A row under the prompt: context, 5-hour and weekly usage; in Nx repos also memory, the session's nx serve projects and the branch's pipeline 2
- reminder-log 0.1.1 Tallies the reminders Claude Code injects for the model, per session; drops the token counter and repeated attribution blocks; /reminders prints the last 30 days 2
- mr-banner 0.1.1 A colored card with a link under each MR/PR created, merged, approved or reviewed 2
- coderabbit-band 0.1.1 A band above the prompt with the open CodeRabbit threads and nitpicks of the branch's MR 2
- redact 0.1.1 Secrets found by betterleaks reach the model as ‹secret:…› tokens; Write/Edit restore them, other tools refuse them 2
- mem-guard 0.2.0 Bash memory rules: Node commands run in claude-cmd.slice, and runs that would starve the machine are refused 2
- handover 0.2.1 mod + skill The handover sentence for a cold session, one per session: a band above the prompt, /handover-copy to copy it, after /clear it waits in the prompt, and /handover picks or drops one in a new terminal 2
- stack-down 0.2.0 On /clear and exit, stops the session repo's nx processes and brings its Compose projects down. 2
- review-walk 0.2.0 mod + skill Walk a code review's findings one at a time: the skill asks per finding, the mod draws Finding N/M with a progress bar and the decisions so far 2
- installguard 0.1.11 Looks up every new package before it installs: holds made-up names, typosquats, days-old releases and curl-into-shell for your answer, and lets the rest through. 2
- agent-fleet 0.5.0 Dashboard of running Claude sessions: context, active/idle, subagents, workflows and who messages whom 2
- autopilot 0.3.0 Run a session autonomously for a set time with a fixed role; hand off and restart itself at a context threshold 2
- dossier mod + skill Engineering workflow in one resumable DOSSIER.md: dependency-ordered tasks, invariants, drift detection, cross-repo state, a rolling status log, and scout + reviewer subagents. 2
- dashband 0.1.1 Prompt cache, context and plan limits at a glance, in the prompt footer and above the prompt 2
- let-them-talk-suggestions 0.1.0 Sends Claude Code's suggested next prompt to Let Them Talk, so its Send box shows the same suggestion, runs a Chat in IDE started from it on the model picked there, and in a background agent runs /effort status after an ultracode switch made while it works, so the app can read it. 2
- blast-radius 0.1.0 See what a risky command would change before it runs. 2
- token-weather 0.1.0 A live forecast of the context window, drawn above the prompt. 2
- replay-theater 0.1.0 Step through the last turn's edits, one diff at a time. 2
- devtools 0.2.1 A debugger for Claude Code tool calls: breakpoints, pause/continue/reject/step, a timeline, an inspector, Error Lens failure diagnosis, a Permissions view of who refused each call and why, and sanitized trace exports. 2
- meme-factory 0.12.3 Fresh from the factory. Ask Claude for a meme and three drafts cook in a side panel while you keep working. Pick one, remix it in plain words, approve it, and post it to Slack. 2
- rabe 0.6.0 Watch Claude Code's background work: subagents, Codex jobs, shells, monitors, cron jobs and workflows. 2
- git-agent-launcher A Claude Code mod that opens a pane of every git-agent skill and command; pressing one stages /git-agent:<name> in the prompt for you to run, so a misclick never commits or pushes 2
- claude-colorizer 0.1.0 Recolors the terminal tab and background by Claude Code session state (working, waiting, done, error). 2
- statusline-native 2.0.0 In-session Client TUI for statusline configuration 2
- cache-keeper 0.5.0 Observes prompt-cache usage, keeps the session's and its finished subagents' caches warm, and runs 5m/1h TTL A/B experiments. 2
- ctx-mod 0.1.0 Proactive context management: a task ledger, a searchable history and zero-summary window switches. 2
- accounts 0.1.0 Run different Claude accounts side by side: one config directory per account, bound per project, switched with /account. 2
- jev-context 0.1.2 Jev-scored context pruning for Claude Code through OpenRouter: at compaction every tool call and result is scored by TypeSafe's Jev decision model, stale ones are dropped or truncated, everything kept stays verbatim. An optional gate truncates oversized tool outputs as they arrive. 1
- jevshift 0.1.0-alpha.4 Experimental Jev-assisted model and effort selection for Claude Code: observe, pin, off, and opt-in auto. 1
- agent-diary 0.2.0 mod + skill In-terminal Stoic engineering diary pane, /diary commands, and automatic session distiller for Claude Code 1