All Claude Code mods/Browse

Claude Code mods starting with J

93 mods. Each name opens the mod’s page with its hooks, API calls, access and install hint. See what a Claude Code mod can access.

• ja-checkyut0takagi/modsL2 Writes or runs

  返答が英語で書き出されたら知らせる。設定で日本語での書き直しを頼める

• ja-replyAstoremica/ja-replyL2 Writes or runs

  Claude Code の返答と途中経過を日本語に固定する Mod。英語で書かれた段落は表示前に日本語へ訳して置き換える

• jargonDanh295/dannys-claude-modsL2 Writes or runs

  Highlights jargon in Claude's replies; hover or click a term for a plain-English definition

• jarvisrotembab/jarvis-claude-modUnknown access

  A JARVIS-style voice for Claude Code: say "Hey Jarvis" (or hold push-to-talk) to speak, hear the reply, talk over it to interrupt. Local wake word and speech-t…

• jarvistwok020101/claude-jarvisL2 Writes or runs

  J.A.R.V.I.S. HUD: arc-reactor spinner, live telemetry band (context, tok/s, agents by model), subagent uplink animations, input alerts, a prompt-cache guard an…

• jaugeai-bandBenjaminSanchezPaper34/jaugeai-claude-codeL1 Reads

  JaugeAI usage band above the Claude Code prompt: plan, tightest limit and reset time for Claude, Codex and Gemini (requires JaugeAI for Mac, Pro)

• jc-hud-modkarimdjaafar/jc-hud-modL0 Draws & remembers

  JC HUD: mod Claude Code : barre d'instruments Jasmine Conseil (contexte, forfait, modèle, horloges)

• je-coupevincentlauriat/ModsToolsL1 Reads

  End-of-session ritual: typing 'je coupe' asks Claude to update the doc files and shows a band of the ones still untouched

• jeffortvntrungld/jeffortL3 Uses the network

  Per-turn effort routing with TypeSafe's Jev, applied per request at turn.step. Off until /jev on.

• jet-routerjetsongdev/jet-routerL2 Writes or runs

  Experimental Claude Code effort router: fake and opt-in Jev shadow

• jevNasrallah-AL/jev-cliL3 Uses the network

  Cheap, fast, typed AI judgments inside Claude Code via the jevctl CLI (verify, screen, find, classify, extract, rerank, match, route, ask, batch), plus verbati…

• jevgecm0/jev-modL3 Uses the network

  Adds $.jev: typed Choice, Score and Noul judgments from TypeSafe's Jev, with a timeout and validated answers, for other mods to call.

• jevmako-code/gobworksL3 Uses the network

  Jev (TypeSafe's System One model) as Claude's instant co-processor: bulk filter/classify/rank/semantic-grep tools, risk notes under permission dialogs, a check…

• jevntkode/notkode-modsUnknown access

  Jev picks the tool that fits Claude's next step and Claude gets it as a hint, shown live and measured against a control group. Native to Claude Code: no gatewa…

• jevyinjs/claude-jevL2 Writes or runs

  Jev answers clear permission prompts, flags prompt injection in fetched content, checks done claims, nudges large or vague requests, and routes effort and mode…

• jev-auto-compactnotque/vexjoy-agentL3 Uses the network

  Jev-powered verbatim compaction: once context reaches 60%, prunes stale tool calls with zero generation. Skips (never falls back to the LLM summarizer) when no…

• jev-autopermitmako-code/gobworksL3 Uses the network

  Opt-in instant approval for clearly harmless shell commands: a strict pre-filter, then Jev classifies the command; only read-only inspection at ≥ 97% with no n…

• jev-blindspot-bandjsk4581/jev-blindspotL3 Uses the network

  A one-glance summary of jev-blindspot in the band above the prompt: the blind spot count, the deeper question, and the top findings for the prompt you just sen…

• jev-claude-routerFlam1ngFir3ball/jev-claude-routerL3 Uses the network

  Routes each Claude Code turn to the model and effort TypeSafe's Jev picks, weighed against what a switch costs, and compacts with Jev instead of a lossy summar…

• jev-commentsmako-code/gobworksL3 Uses the network

  No narrating comments: every comment an edit adds is judged by Jev in a few hundred ms; 'Added X as requested' and friends go back to Claude.

• jev-compactAkeuuh/claude-modsL3 Uses the network

  Jev decides when to compact, on every turn and on demand, and picks where the live work starts

• jev-compactHAR5HA-7663/jev-compactL3 Uses the network

  Context compaction that prunes instead of summarising: rules drop exploration output and hook noise locally, Jev ranks the rest against a budget, a note says w…

• jev-compact-gatetdimino/claude-code-minoanL3 Uses the network

  Jev decides when the session compacts, inside a 280k: 400k token band; Claude's own summary does the compacting.

• jev-compact-triggerHAR5HA-7663/jev-compactL2 Writes or runs

  Companion to jev-compact: watches context use after every turn and starts a compaction at the configured percentage. Separate plugin on purpose: the engine ski…

• jev-contextHyunjunJeon/jev-contextUnknown access

  Jev keeps the context window lean so compaction comes later: prunes tool output on entry, caps subagent reports, carries exact facts across compaction, compact…

• jev-contextJayDoubleu/cc-mod-jevL3 Uses the network

  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…

• jev-conventionsmako-code/gobworksL3 Uses the network

  Instant repo-convention checks on every edit: CLAUDE.md, AGENTS.md, style guides and config facts compiled into atomic rules, each edit judged against all of t…

• jev-docdriftmako-code/gobworksL3 Uses the network

  Docs that went stale because of this turn's changes: changed names, flags, env vars and config keys are looked up in the docs, and Jev reads each section again…

• jev-effortgebeer/jev-effortL3 Uses the network

  Sets the main conversation's reasoning effort per prompt with TypeSafe's Jev (via OpenRouter), reading recent conversation context. Shadow mode by default: log…

• jev-eval-observertamaratran/jev-prunerL2 Writes or runs

  Pass-through evaluation instrumentation; never changes tool results.

• jev-expressmako-code/gobworksL3 Uses the network

  Reflexes: short read-only requests (git status, diff stat, recent commits, cost, context) answered locally in an Express pane, no model turn.

• jev-gateMongLong0214/jev-gateL3 Uses the network

  Jev Gate in one plugin: the orchestration gate, the extractive compactor, the Jev effort and model router and the jev_evidence tool. Every part is on by defaul…

• jev-gate-compactMongLong0214/jev-gateUnknown access

  Task-aware extractive compaction with bounded Jev dependency selection and the native recent tail; on by default.

• jev-gate-routerMongLong0214/jev-gateUnknown access

  Routes the main thread's effort and each subagent's model and effort with one TypeSafe Jev assessment; on by default, native on any doubt.

• jev-governorroma-vibe/jev-governorUnknown access

  Jev-guided model, effort and subagent routing for Claude Code (Opus 5.5 / Sonnet 5.5), auto-created specialist subagents and Jev-pruned compaction.

• jev-guardAkeuuh/claude-modsL3 Uses the network

  Jev gates Bash, Write and Edit, and screens Read and Bash results for injected instructions; a blocked command is held, for the person to run anyway or keep bl…

• jev-guardmuratcakmak/jev-guardL3 Uses the network

  Probability-scored guardrails for Claude Code: deny rule-breaking edits and unasked-for deploys, route your own docs into each prompt, and check the final answ…

• jev-hudAkeuuh/claude-modsL2 Writes or runs

  A band above the prompt that shows Jev at work: a spinner while it thinks, each intervention in colour, calls, latency and spend

• jev-judgekuhku/kuhaku-pluginsL3 Uses the network

  Annotates Claude Code's AskUserQuestion dialog with TypeSafe Jev's probabilities and a recommended option (labels in Japanese).

• jev-judgemako-code/gobworksL3 Uses the network

  A definition of done Jev checks after every turn: per-criterion probabilities that demand evidence, a band above the prompt, optional auto-continue.

• jev-modVictorGambarini/jev-modL3 Uses the network

  A cheap decision model picks each turn's skill, model and effort, compacts on request, and withholds injected text

• jev-model-routerDmitryBMsk/thinkdialL3 Uses the network

  Picks the model and reasoning effort for each task with TypeSafe's Jev. Routes subagent models at agent.spawn and subagent and main-loop effort at turn.step, w…

• jev-model-routerKiy-K/oxideL3 Uses the network

  Picks the model and the reasoning effort for each task with TypeSafe's Jev, a System One decision model reached either through TypeSafe's own API or the Vercel…

• jev-model-routerTolsee/dotfilesL3 Uses the network

  Corrects the model tier of every subagent spawn (agent.spawn) with a live Jev judgment (haiku / sonnet / opus), instead of relying on /delegate's static routin…

• jev-moodmako-code/gobworksL3 Uses the network

  Claude adapts to how you are doing: Jev reads each prompt's tone in a blink and, when the signal is strong, hands Claude one hidden line of guidance. Silent by…

• jev-permission-gatemadisonrickert/jev-permission-gateL3 Uses the network

  Uses TypeSafe's Jev to allow or deny routine tool calls in auto mode, and hands uncertain ones to the built-in classifier

• jev-pilotAkramovic1/jev-pilotL3 Uses the network

  TypeSafe's Jev decides how Claude Code works on each prompt: the main conversation's reasoning effort (low to xhigh, raised to max mid-turn when tool calls kee…

• jev-pingmako-code/gobworksL3 Uses the network

  Notifications only when you are actually needed: after each turn Jev reads whether Claude asks you something, is stuck, or finished a long task; permission pro…

• jev-precommitmako-code/gobworksL3 Uses the network

  A commit gate that reads the staged diff in a blink: Jev flags debug output, commented-out code, TODOs, machine paths, secrets and off-message changes before C…

• jev-prompt-graderSyptern/jev-prompt-graderL3 Uses the network

  Grades each prompt you send with TypeSafe's Jev model and shows what is missing above the prompt box.

• jev-reusemako-code/gobworksL3 Uses the network

  "This helper already exists": new functions are compared against a git-grep symbol index, Jev judges the look-alikes in a few hundred ms, and Claude hears abou…

• jev-routeAkeuuh/claude-modsL3 Uses the network

  Jev picks the model and the effort for each request, from how demanding it is

• jev-routedrewpayment/jev-routeL3 Uses the network

  Routes each turn to the cheapest capable Claude model using Jev, TypeSafe's decision model. Toggle with /route.

• jev-routerHoppin-Sorter/jev-routerL3 Uses the network

  Asks Jev before each prompt what the task is and how hard it is, then picks the Claude model (and optionally effort) and the skill that fit. /jev and the Jev B…

• jev-routerXvectorio/xvector-claude-modsL3 Uses the network

  Per-turn model routing: TypeSafe Jev picks Haiku, Sonnet or Opus for each prompt (port of gargpratyush/jev-router).

• jev-routerdominicrico/jev-routerL3 Uses the network

  Asks TypeSafe Jev before each task which Claude model and effort fit best, then runs the turn on it

• jev-routersatviksinha/jev-model-routerL3 Uses the network

  Routes each turn to a Claude model chosen by TypeSafe's Jev, asked through the Vercel AI Gateway.

• jev-rulesEliaAlberti/jev-rulesL1 Reads

  Jev picks which of your rules apply to each prompt, so Claude only sees the ones that matter.

• jev-scopemako-code/gobworksL3 Uses the network

  Keeps changes on task: every edit is judged by Jev against your last request (and Claude's plan) in a few hundred ms; drive-by changes go back to Claude.

• jev-scoutmako-code/gobworksL3 Uses the network

  Jev ranks every file in the repo against each prompt in ~0.5 s and hands Claude the likely relevant ones (System-1 file triage).

• jev-searchmukiwu/jev-search-mcpL3 Uses the network

  Web search through Jev Search. Answers Claude Code's built-in WebSearch with Jev (sources and time window chosen by Jev, every result ranked by relevance) and…

• jev-seclintmako-code/gobworksL3 Uses the network

  An instant security reviewer on every code edit: ~20 yes/no checks per edit answered by Jev in a few hundred ms, fed back to Claude.

• jev-semaphorestaticdreams/jev-semaphoreL3 Uses the network

  Jev Semaphore for Claude Code: Jev / Kev model routing for subagents, with a live allocation pane, agent graph and context-exchange band

• jev-skill-scoutkaranb192/jev-skill-scoutL3 Uses the network

  Before each prompt reaches the model, TypeSafe's Jev ranks your installed skills against it and attaches one line naming the skill to load. Sends the prompt te…

• jev-skill-suggestionAnatoliyShk/bulgolingoL3 Uses the network

  Keeps the skill listing out of the context window and lets TypeSafe's Jev, a System One decision model, pick at most one skill per prompt from the skills' desc…

• jev-skill-suggestionray-amjad/awesome-claude-code-function-hooksL3 Uses the network

  Scores every skill against your prompt with TypeSafe Jev as you type; observe, block or steer skill loading

• jev-suitecardosoads/jev-suiteL3 Uses the network

  Branch git acima do prompt e juízos do Jev (TypeSafe): guarda de comandos, roteador de esforço, detector de segredos, aviso de agente travado, dica de qualidad…

• jev-test-guardmako-code/gobworksL3 Uses the network

  Catches tests being weakened to make them pass: every test-file edit is judged by Jev in a few hundred ms against what you asked for.

• jev-tool-gatem2ai-portfolio/claude-modsL3 Uses the network

  Log-only Jev judgment of risky tool calls (destructive? requested by fetched content?). Never changes a decision; hosted calls off by default.

• jev-topicmako-code/gobworksL3 Uses the network

  Jev notices when a prompt starts an unrelated task and offers a fresh conversation for it, saving context and prompt cache.

• jev-triagemako-code/gobworksL3 Uses the network

  Every failed Bash/PowerShell command gets an instant Jev diagnosis (15 failure classes) and a playbook in this project's terms, as a note Claude reads.

• jev-trimmako-code/gobworksL3 Uses the network

  Huge Bash/PowerShell outputs cut to the lines that matter: Jev scores every 12-line chunk against your request, the full log is saved for Claude to open.

• jev-vault-gatesohryuu101/jev-vault-gateL3 Uses the network

  Uses Jev to spot durable knowledge in a turn and auto-capture it into ~/vault/raw/ for /compile.

• jev-watchdeadczarvc-labs/jev-watchL2 Writes or runs

  Logs what fast-jev-compaction does (outcomes, TypeSafe requests, compactions, hook failures) to JSONL files.

• jevcompjevcomp/jevcompL2 Writes or runs

  Jev decides what Claude Code keeps when it compacts, instead of a model-written summary.

• jevmateGastonGelhorn/jevmateL2 Writes or runs

  A fast decision layer for coding agents. Jev ranks files, picks the tests a change can break, sorts failures and reviews diffs by risk, so Claude reads only wh…

• jevmem-paneAvinash-jetwani/jevmemL2 Writes or runs

  A side pane for Claude Code beside your chat: what jevmem recalled for this prompt, what its guard decided, and what the last turn saved, with why, wrong and f…

• jevshiftunclecode/jevshiftL2 Writes or runs

  Experimental Jev-assisted model and effort selection for Claude Code: observe, pin, off, and opt-in auto.

• jira-bitbucketFyzu/claude-atlassian-modeL3 Uses the network

  Bitbucket review queue and your open PRs in a pane; the current branch's PR, CI and Jira issue in a bar above the prompt

• jira-ticket-panemeganemura/jira-ticket-paneL3 Uses the network

  A pane beside the transcript that fetches one Jira issue by key and lets you attach it to your next prompt.

• jira-trackerpolatmurat/temsa-claude-modsL3 Uses the network

  Tracks the Jira ticket you work on, offers to open one at commit time and closes it out, writing to Jira only after you approve each step.

• job-watchjoeldg/claude-modsL2 Writes or runs

  Live pane of long-running jobs (training, downloads, extractions): progress, ETA, stalls and finishes, read from their logs with no model calls; jobs_list / jo…

• jotDanh295/dannys-claude-modsL1 Reads

  A notes pane: jot text during a session, keep it across sessions, arrow to a note and press Enter to paste it into the prompt.

• journalmako-code/gobworksL2 Writes or runs

  Project memory across sessions: every few turns haiku writes what was done, decided and left open to .claude/journal.md, and new conversations start with the l…

• jp-displayhptukurou0101-design/claude-mods-jpL0 Draws & remembers

  スピナーや操作ヒントなど Claude Code の英語表示を日本語にする

• json-browserwhyashthakker/awesome-claude-code-modsL1 Reads

  Summarize top-level JSON keys with types and a formatted preview.

• json-formatwhyashthakker/awesome-claude-code-modsL1 Reads

  Validate and pretty-print JSON without touching a file.

• json-prettybaselane-sh/modsL0 Draws & remembers

  Bash output that is one long line of JSON is drawn pretty-printed, folded after 30 lines. Display only: Claude reads the output as it was.

• jukebox7KTCrisis/flux7-modsL2 Writes or runs

  Plays music from YouTube when asked in plain words, audio only through a hidden VLC, with a small control pane

• jump-listGururOzatmaca/claude-modsL2 Writes or runs

  A side pane listing every prompt in the session: see where you are, click to jump back

• junior-modebaselane-sh/modsL0 Draws & remembers

  Explains each step and why, and defines jargon once, for a learner.

• justchatorvn/justchat-claude-modL2 Writes or runs

  A /justchat mode where Claude supresses actions like writing code things through instead of writing code in favor of just chatting until told otherwise

• jwt-decodePlagemes/claude-modsL1 Reads

  /jwt decodes a JSON Web Token locally: header, claims, expiry: without sending it anywhere.