Guards

Keeps secrets out of Claude's context: gitleaks scans every tool output, prompt and attachment before the model reads it, and you decide what the model sees.

Claude asks for API keys in a masked field above the prompt, saves them to the macOS Keychain, Linux keyring or Windows DPAPI, and uses them in Bash without ever seeing them

Asks before harsh DevOps commands: destructive Docker, Kubernetes and Helm calls, CI config edits, broad chmod and chown, and git commands that lose work. Add infra-guard for plain kubectl delete.

Asks before a live API key, token or private key is written, edited or run.

reads every Bash call, fork spawn and Write before it runs: a Write over a tracked file the session never read, a floor command, a system, overwrite, prune or remote-delete command, a known hazard shape, a coder spawn whose brief has no x brief check stamp, or a fork with no why-fork line is refused with its safe door, never a dialog; each refusal and escape is kept in its own store as an...

Live plan progress bars above the Claude Code prompt: stages, steps, a pixel fill and soft sounds for decision, error and done (qa-mods fork: a wider title, the full title on hover, Ukrainian interface)

Sets the reasoning effort of every native subagent call from Jev's rating of its task, leaving the model as it was, and keeps local records to compare efforts.

Gates git work: no commit, push or merge without the user's say-so in the current turn; a push to a branch that already landed is refused; an MR whose branch lacks the target's latest commit is refused; a pushed series must leave the project working at every commit; commit messages kept tidy (format and the issue it is about, then a Haiku review of the body).

A badge under each Bash tool row naming the environment the command targets (AWS profile, kube context, ...). Rules, tiers, format and label scripts are configured in settings.json pluginConfigs. Display only: never touches tool output or model context.

Nexika mizan: keeps your Claude Code session in balance. A band above the prompt shows the branch and who started it, open PRs or MRs per person, the branch's CI (passed, failed with the job, running), RAM and disk with warnings, the context level (fresh, mid, full), the running agent and its task, the current task step and the session cost; /mizan opens the details. At full context it saves a...

The learning loop: every main turn is kept in a ledger across sessions (phase, effort, steps, failed tool calls, agents, advisor calls), joined with the outcomes observed at tool.call (commits kept or reverted, test exits, PR verdicts and merges, no transcript) and the ones /insights writes, and the project's goals; probe sessions are counted and kept out; a phase whose evidence, read on the...

Läuft ein Testbefehl grün durch und liegen danach uncommittete Änderungen im Repo, bekommt Claude still einen Hinweis, den Arbeitsschritt zu committen. Keine Dauerabfrage, kein Git-Hook.

Idle-session guard for Claude Code's 1-hour prompt cache (macOS): about 50 idle minutes after the last turn of a large session it notifies you, optionally after a cache-read fork judges whether to compact, keep warm or leave it; every request and change it makes is audited. Derived from cache-tax (MIT, Karan Bansal).

Keep your API keys and tokens out of your Claude Code conversations: tokens pasted as keyfob: lines are stored before the model sees them, Claude asks for a key through the /keyfob panel, a guard stops Bash commands that would print one, and each command gets only the keys it needs from the OS keystore

Claude Code speaks through murmur (Kokoro on the Apple Neural Engine): turn summaries, needs-you alerts, background tasks, progress check-ins and rate-limit warnings, each session in its own voice (/say picks one)

Shows the state of Claude (working, permission, input, idle, background, compacting) in the iTerm2 tab subtitle.

Sends each local session's status (what Claude is doing, task progress, context and usage) to the Claude Widget desktop app on this computer, and takes its Stop button

Picks the reasoning effort for each turn of the main conversation with a System One classifier (hosted Jev or a compatible service) and shows the level on the spinner and on the line that closes the turn. In shadow mode it shows and logs its pick and sends the session's effort; in enforce mode it sends the pick. Requires CLAUDE_CODE_ENABLE_FUNCTION_HOOKS=1.

Rules for Claude Code alerts: when one is worth sending (done, blocked, error, usage limits) and where it goes (chime, macOS notification, ntfy, Slack, Discord or a JSON webhook).

Git only when you asked: commits, pushes, pull requests, merges and destructive git commands run only when your latest message (or /ship, /kickoff (also as /progress-pane:kickoff), or your answer to Claude's question) allowed them; everything else is refused with a note telling Claude to ask. No UI.

Choose the model versions Claude and its subagents may use: /models lists the newest of each family from Anthropic's Models API (older versions one key away); block a version, or a family's new ones, and subagents, workflows and /model asking for it are refused or moved to an allowed version. One list shared by every Claude Code window on the machine; a repo can keep its own.

Mission control for Claude sessions, in a Notebook look: a band and /progress pane in every session (model, effort, tokens, context, agents, gate, git), and with a worklog a validated worklog tool Claude updates at every step (done only after a green gate), facts the mod sees for itself (gate runs, commits, branch, agents, context and cost), drift hints where the two disagree, a band above the...

カニード が Claude の作業中にダンジョンを自動探索する Claude Mod。回復は Lv アップとテスト成功、あとはマップで見つけたショップだけ。倒れると Lv 1 からやり直し。会話ログのパス・#N・URL もクリックで開ける。Needs function hooks (CLAUDE_CODE_ENABLE_FUNCTION_HOOKS=1) and an interactive terminal.

A board with two tabs: this session shows the task list that Claude and you share, and this machine shows every local session, the ones that wait for you first. /board opens it, and four model tools keep the list.