#ModGitHub stars

1. 961orca-stratormutlumehmet/claude-pluginsOrca Strator in one install: see every session in every account, watch each account's usage, move sessions to a twin account before a limit, and run a fleet of sessions with handovers. Each part also installs on its own.6
2. 962cache-clockray-amjad/claude-code-modsA one-line band above the prompt: context used, and a countdown until the prompt cache goes cold101
3. 963ballastersinkoc/claude-modsKOZMOS Ballast: a context coach. A toast when the context window passes warnAt, then a band with an anchor and a water-level gauge at actAt: " ctx 89% — compact before the next big task" with Compact now (queued to the end of a running turn) and Not now. Optional auto-compaction between turns, and a before→after toast for every compaction. /ballast toggles the band.21
4. 964flight-recorderpromptadvisers/claude-mods-starter-kitSee inside a turn: a live Gantt timeline of model requests, tool calls and subagents, with tokens and cost per lane.21
5. 965agent-watchice-lfernandes/claude-code-modsSubagents at a glance: a card per agent with its mascot, step and tokens, a band above the prompt, a toast when one stalls, and a summary naming the heaviest agent when they finish11
6. 966context-lensArunjay4213/claude-modsA live /context: a pinned line under the prompt with the window fill and the growth per turn, and /context-lens for a pane with the per-category bars and how many turns are left before auto-compaction.11
7. 967usage-meterhamzafer/claude-code-modsYour plan's 5-hour and 7-day usage as small bars above the prompt, with the reset countdown and the session's cost.426
8. 968context-usageT-AI-Labs/claude-code-modscontext-meter and usage-limits in one band above the prompt: the context fill with its auto-compact threshold, Compact and Clear, and the 5-hour and weekly usage limits beneath it.4
9. 969subagent-meterNarenDawar/narens-claude-toolkitA live status line showing how much of your session's tokens go to subagents, and which agent type uses the most.4
10. 970xrayucsandman/Agnostic-AICLAUDE RUNTIME X-RAY: wildcard inspector with filters (/xray all|tools|subagents|session|usage|ui|errors|unknown|off), a HUD above the prompt, and a black-box timeline file24
11. 971desktop-workspace-homewhyashthakker/awesome-claude-code-modsShow the current workspace, Git state, and session usage together.109
12. 972idle-compactnoash-xrc/claude-toolsCompacts an idle session with a large context just before its prompt cache expires, while the summary still reads from cache3
13. 973sc-accountssimplecore-inc/claude-modsSwitch between saved Claude logins and watch every account's rate limits3
14. 974subagent-limitsAbhiramDwivedi/claude-opsKeeps subagents small: tells the main agent how to size and split work, asks a growing subagent to checkpoint, and refuses its tools past a hard limit so a fresh agent takes over3
15. 975tamagoxtixschreibse/claude-code-modsA little pixel monster in place of the spinner: animated by what Claude is doing, with a visual timer, a stack of token coins, usage charts and Omarchy-style palettes.3
16. 976spawn-ledgerTekkiiiii/the-agencySpawn log (spawn_start/launched/end + cost, native agentId lineage), artifact check and in-session RESPAWN_REQUEST pickup for every subagent, background included7
17. 977gemini-coreKilimcininKorOglu/claude-code-modsKeeps the Gemini keys and tier of every Gemini mod, and each mod's model and thinking level, in one place: adds $.gemini, which builds their Gemini requests, reads the answers and moves to the next key after a quota or key error, and picks a model from Google's list.12
18. 978orca-movemutlumehmet/claude-pluginsPart of Orca Strator (included in the orca-strator bundle). Moves a live session, or every session of an account, to a twin account when one nears its limit, and tells the sessions it works with where it went.6
19. 979context-metercjavdev/modsA tiny meter in the bar under the prompt showing how full the context window is: five cells, the percent and the token counts.2
20. 980prompt-gateiuliandita/modsBefore the main model spends a turn on a vague prompt, a small model, checked by Jev when TYPESAFE_API_KEY is set, says so and asks one short question. Default mode dry only measures. With a key set, the prompt goes to api.typesafe.ai (Jev) from every directory unless jevPaths limits it.2
21. 981review-linttridha643/claude-composio-modsHands Claude a cache-review checklist or test rules when an edit adds a cache or a brittle test assertion2
22. 982RunwayHeuwzen/claude-runwayYour Claude Code 5-hour and weekly limits and the chat’s context window as live meters above the prompt2
23. 983token-weatherhamzafer/claude-code-modsA live forecast of the context window, with a prompt-cache countdown, drawn above the prompt.426
24. 984goal-meterahmadhammoud56/MOAAA progress bar for /goal: real acceptance checks from a long-task brief, karpathy-loop best against its target, or turns against the goal's turn limit5
25. 985read-dedupwdsewdser-bit/claude-code-modsRe-reading a file already in the context returns a one-line notice if unchanged, or only a diff if changed, saving context tokens.5
26. 986context-rolloveraymengraoui/claude-code-context-rolloverRolls long-running (multi-agent) Claude Code work over into fresh sessions before the context gets too large: persists a compact, verified continuation of the project state, starts a genuinely fresh session and resumes the highest-priority work. Publishes its lifecycle as shared state for the Cockpit sidebar.
27. 987overviewsatoramoto/awesome-claudeA session overview pane: context, cost, time, turns, tools, files, subagents, limits and git; cells in the terminal, charts in the desktop app
28. 988attic-widgetoMaN-Rod/claude-code-widgetsCounts which tools Claude calls in this project, puts the unused ones behind ToolSearch, lists the daily ones up front, and reports how many schema tokens each request no longer carries4
29. 989cache-meterT-AI-Labs/claude-code-modsPrompt-cache hit rate in one row above the prompt, with how long the cache stays warm and a Keep warm switch that refreshes it while you are away.4
30. 990limit-barsFynnXland/fynn-modsBars for the 5-hour and weekly usage limits above the prompt, a ring showing how long the prompt cache stays warm, and an optional ring for drive usage by file type. Cache guard: asks before an expensive cold send; /cache, /handoff, /keepwarm, /disk, /bars. Every part of the display can be hidden.4
31. 991todo-barhoobnn/hoobnn-agent-modsThe task list's progress in a band above the prompt, read from the todo and task tools' own calls: no tool, no prompt, no tokens7
32. 992claude-runtimeucsandman/Agnostic-AIShared Claude runtime adapter: normalises function-hook events into ClaudeRuntimeEvent, exposes $.runtime (emit bus, supports, judge, snapshot) to other plugins, and writes a JSONL event log24
33. 993burnrateburnrate-ai/burnrateFull mod: live limits band above the prompt plus the guard (cache watchdog and limit brake).1
34. 994calm-recapkulovema2012/calm-modeCalm Recap: a Welcome back card when you return to the keyboard, and the prompt cache's hit rate and time left in your status line.1
35. 995context-barrichardcsuwandi/claude-modsStacked context-window bar above the prompt, colored like /context; toggle with /context-bar1
36. 996decision-modelkzarzycki/claude-modsA decision model for other mods ($.decision.ask): typed questions about a state, answered by any System One endpoint (Jev by default) or a small Claude model.1
37. 997evidence-meterjaycp30/jay-claude-modShows, under every answer, what Claude actually checked that turn: files read, commands and tests run, web pages fetched, and what failed.1
38. 998lk-where-am-iconnectwithub/loopkeeperKnow where the session is at a glance: repo, branch, worktree, uncommitted and unpushed work, usage windows and the prompt cache in one line above the prompt.1
39. 999read-ceiling-pagerStartupBros-com/hov-marketplaceA Read whose window would exceed Claude Code's token cap is clamped to the lines that fit, and the result says where to continue. Turns a failed round into a successful partial read with an explicit continuation.1
40. 1000repo-spendaseem-upadhyay/qol-modsA bar above the prompt: dollars spent on the current repo over the time your logs cover (every session's share of work done here, worktrees included), and this session's live spend and burn rate1
41. 1001rtk-gainFazzani/claude-modsRTK token savings in the status line, and /rtk-gain draws the full rtk gain report as a card.1
42. 1002session-hudangomedia/claude-modsA card above the message box with the model, effort, context window, usage limits and their reset times, cost and session length1
43. 1003token-limitakagaya/claude-code-modsShows context window fill and rate-limit usage in colour at the right of the prompt footer1
44. 1004usage-barsatyamk4517/claude-modsInteractive band above the prompt: context fill, 5-hour and 7-day plan limits with resets, session cost, and a progress row for any subagents.1
45. 1005usage-bellKTCrisis/flux7-modsRings when the session nears a limit: context fill, rate-limit windows, the auto-memory index1
46. 1006wt-deep-searchhome-dev-lab/workflow-toolboxEXPERIMENTAL. Answers a WebSearch from the local Claude Code doc mirror, context7, Brave or Exa, and adds a detached deep-research rung behind a handle.1
47. 1007orca-quotamutlumehmet/claude-pluginsPart of Orca Strator (included in the orca-strator bundle). Shows every Claude account's 5-hour and 7-day usage in one band, and warns before an account hits its limit.6
48. 1008catalyst-swe-requestTransmuteLabs/CatalystRequest-text policy for devin/swe-2: registers one rule in the host's $.requestText noun.3