Mods
Community mods for Claude Code. Every listing shows what a mod hooks into and whether the pinned commit has been reviewed.
20 mods hooking Permission Clear filters
-
Not yet reviewed
token-optimizer
The Token Optimizer status bar on its own, for its tests. It ships inside the token-optimizer plugin.
View mod → -
Not yet reviewed
intermission
Doom deathmatch in a Ghostty or kitty pane on macOS 15+, returning you to Claude when it finishes or needs input; downloads and runs Odamex and connects to a…
View mod → -
Not yet reviewed
ruflo-console
ruflo's cockpit inside Claude Code and the one /ruflo command for every ruflo mod (function hooks, early access). Views: overview with health alerts, swarm…
View mod → -
Not yet reviewed
ruflo-mods
ruflo as a Claude Code mod (function hooks, ADR-404): in-process prompt routing, edit learning signals, tighten-only tool checks from ruflo policy, the…
View mod → -
Not yet reviewed
ruflo-protector
Project Anatole: an optional, learning watchdog for unattended agents. Deterministic OWASP-mapped rules, a per-project behavioural baseline, four modes (off…
View mod → -
Not yet reviewed
plan-progress
Live plan progress bars above the Claude Code prompt: stages, steps, a pixel fill and soft sounds for decision, error and done
View mod → -
Not yet reviewed
jev-permission-gate
Uses TypeSafe's Jev to allow or deny routine tool calls in auto mode, and hands uncertain ones to the built-in classifier
View mod → -
Not yet reviewed
flightdeck
A live agent dashboard pane with context and cost, an advisor timeline, every permission verdict, subagent cards and swimlanes, a turn receipt and a session…
View mod → -
Not yet reviewed
classifier-telemetry
Records each tool call's permission verdict and wall time so auto-mode classifier cost is measurable from the session index
View mod → -
Not yet reviewed
pokemon
Any of the 151 gen 1 Pokémon above the prompt to feed, pet and evolve, with a Poké Ball for each running subagent and 135 animated attacks.
View mod → -
Not yet reviewed
lemo-guard
限时：Claude 单轮工作超时自动中止 · 等你确认的时间不计 · 默认关闭，在「安全」页开启 / Time limit: stops Claude when a turn runs over time · time waiting for you does not count · off by default…
View mod → -
Not yet reviewed
agent-flow
/flow opens a live tree of the session's subagents and teammates beside the transcript.
View mod → -
Not yet reviewed
guardian
GUARDIAN: executable policy that protects lab/demos/protected/** from Write/Edit/Bash, whatever CLAUDE.md says
View mod → -
Not yet reviewed
probe2
Interception probe: deny, rewrite, replace result, delay, throw, register tool, classify
View mod → -
Not yet reviewed
probe3
Permission override, subagent visibility, agent.spawn model rewrite, turn.step routing, prompt context injection
View mod → -
Not yet reviewed
prodguard
PRODUCTION GUARD: ambient project/environment context + a transport-independent policy core (DashClaw evidence classifier + offlocal policy engine) enforced…
View mod → -
Not yet reviewed
spinner
Pixel-art scenes above the prompt while a turn runs, in fourteen themes, with a pet that follows the running tool, levels up and gets a confetti finale.
View mod → -
Not yet reviewed
catalyst-probes
A consultation and prompt engine configured by TOML tables of probes and prompts.
View mod → -
Not yet reviewed
scope-guard
Tracks recognized file edits against a configurable threshold, with a model judge and user overrides that can permit further edits.
View mod → -
Not yet reviewed
clawd-tales
Clawd acts out every tool call above the prompt with a one-line caption, joined by subagents tinted by model, with failing tests as bugs, todos as pellets and…
View mod →