session-end-unpin
gunkr-com/claude-mod-repo
Unpins the session from the desktop app's sidebar once you ask to end it and Claude finds nothing left: the end-of-session steps done, no question, decision or follow-up waiting
1,027 mods
gunkr-com/claude-mod-repo
Unpins the session from the desktop app's sidebar once you ask to end it and Claude finds nothing left: the end-of-session steps done, no question, decision or follow-up waiting
rajib2k5/claude-market-watch
Stock ticker in the status line, /quote pane, price alerts, a market-context band, and a quote tool the model can call.
scaso01/claude-risk-guardrails
Ongoing monitoring: keep watching the agent after approval, and watch the controls themselves.
scaso01/claude-risk-guardrails
Outcomes analysis: check what a reply claims against what the evidence supports.
ramtinJ95/claude-mods
Drive Nexus coding-agent threads from Claude Code: a live pane of threads and conversations, /nexus commands, and tools for the model
ramtinJ95/claude-mods
Checkpoint notes and fresh context windows that continue from them, with searchable history of earlier windows
ramtinJ95/claude-mods
Spawn, delegate to and monitor Pi and Claude Code agents in Herdr Core terminals, with results pushed back into the session
luwux/keepwarm
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).
jysvai/lanes
On-demand lanes beside your main Claude Code session, as sessions of their own or as teammates inside it, from the first idea to release: a mid lane for side work that needs judgement (research, plans, reviews, tests), a low lane for search, scripts and crawling. Works on the Claude API, Amazon Bedrock, Vertex AI and Foundry. Status line, /lane, and tools the main model calls.
hyperbola-bear/claude-mods
Every subagent Claude starts waits for your approval: approve, refuse, approve all for the turn, change its model (suggested by the task's complexity) or add a note to its task. Then a pane shows each running agent as a pixel character with its context battery, tokens, estimated cost, time and the steps it reports, plus the agents done and a plan's progress above the prompt, the same in the...
hyperbola-bear/claude-mods
A control panel tucked into the corner above the Claude Code prompt, as cards in seven modules you turn on or off: your other sessions (which need you, which are working), a context battery and where your tokens go (files, chat, MCP, shell, skills and plugins, subagents and more), model and effort pickers in three styles, prompt-cache countdown with a 2-minute keep-warm alert, the guesses...
Fox1304/FT_Claude_Overwatch
A small dashboard beside the chat: Claude's progress and helpers drawn as avatars, the steps only you can take, and a queue of ideas Claude clarifies, files and works through alone
AraneaDev/cassandra
Remembers the tool calls that already failed, and says so before your agent runs one again unchanged.
IndjiWR/auto-clear-context
Vicino alle soglie di contesto (morbida, dura, margine di sicurezza) Claude salva lo stato in un handoff validato; la mod esegue /clear e fa ripartire il lavoro nella sessione pulita.
godic97/deid-guard
De-identifies personal data in tabular files (CSV, TSV, XLSX, JSON) before anything reaches the model. Korean and English.
andytw366/claude-mods
A ShowImage tool that shows the pictures Claude wants you to see: in a floating VS Code window from VS Code's terminal (with a small extension), or inline in WezTerm, kitty, Ghostty or iTerm2, also over SSH and in WSL.
LilianMLG/revo-flow
/revo-flow : l'orchestrateur lit les specs, fait un plan, répartit les tâches entre des sous-agents (modèle et effort choisis pour chacun) et affiche une barre de progression par agent dans le panneau latéral ; un cache par projet (graphe des fichiers et fiches de features apprises en fin de flow) lui évite de relire le code : /revo-flow cache. Un agent peut en attendre un autre (relancé quand...
masterA88/claude-side-mods
Live plan progress bars that fill as Claude works, shown in Mission Control. Fork of zycck/claude-mods plan-progress (MIT).
okashiina/illa-mods
Fable 5.2 thinks and orchestrates a mission: plans sized tasks and picks, per task, the executor (Opus 5.5 lead, Sonnet 5.5 worker or Haiku 5.5 scout) and its reasoning effort. Opus runs at medium by default and high only rarely; Sonnet may run high; Haiku is free. Shows every agent and the mission's % in a live pane, and holds its autopilot while Fable waits on the outside world
okashiina/illa-mods
Opus 5.5 conducts a mission: plans sized tasks, delegates hard labor to Sonnet 5.5 workers and narrow jobs to Haiku 5.5 scouts at the reasoning effort each task needs, shows every agent and the mission's % in a live pane, shows "cooking" with live-moving bars while agents work, and holds its autopilot while Opus waits on the outside world instead of nudging it
gpr/claude-code-mods
Tracks tokens and cost per model, agent and session for every session on a git branch, in a right pane.
VAlux/claude-session-progress
Animated progress band for long-running turns, with a completion summary
Ryubara/tether
Holds a project together across Claude Code sessions: an agents pane, watchers that wake the model only for news, and guards against expensive mistakes
ikstewa/workstreams
Workstream board, charters, tmux sidebar and active-session dispatch
No tracking cookies, no third-party scripts. How we handle data