kernel-model-hint 0.1.0
Under Fable 5.2 or Mythos 5.2, rewrite the system-prompt note on their kernel-optimization training limits so the model suggests Mythos 5.1 for accelerator kernel work.
sipengInstall
/plugin marketplace add SipengXie2024/claude-mods /plugin install kernel-model-hint@sipeng-mods
Run both lines inside Claude Code.
Hooks into
- System prompt
Also in SipengXie2024/claude-mods
-
subagent-opus
0.1.0
When the main loop runs on a Fable or Mythos model, start Agent-tool subagents on Opus instead of inheriting it.
sipeng in Other, updated
0
-
no-bg-poll
0.1.0
Block sleep-and-read polling of background tasks; they send a completion notification.
sipeng in Guardrails, updated
0
-
workflow-opus-guard
0.1.0
Under a Fable or Mythos main loop, deny Workflow scripts whose agent() calls do not pin model: 'opus'.
sipeng in Guardrails, updated
0
-
jev
0.2.0
Jev effort routing for Opus, Mythos, GPT-6 Astra and GPT-6.1 Sol (policy.v15): start effort per prompt from per-model kind tables that start low and hold a raised level while the task goes on, judged by OpenAI's Decisions API over the conversation as Claude Code holds it (user messages and final ...
sipeng in Prompt, updated
0
-
mode
0.2.3
Per-repo general/academic mode: /mode writes .claude/settings.local.json; paper repos get a one-time hint.
sipeng in Status line, updated
0
-
magpie-tasks
0.1.0
Long-running task windows for claude-magpie sessions: an architect per long task, subagent model and effort routing by rules judged through Jev, a task registry and log, worktrees with integration, acceptance and diagnosis of daily tasks, Telegram delivery, startup recovery, rating invitations an...
sipeng in Prompt, updated
0
-
advisor-guard
0.3.0
Under a Fable or Mythos main loop, tell the model never to consult the advisor tool, so the session does not pay for a second model.
sipeng in Guardrails, updated
0
-
context-memory
0.2.0
Lets the working model keep a task note, archives the conversation at compaction, carries the latest note verbatim into the new context, and provides scoped history search and read tools. Makes no model requests of its own.
sipeng in Guardrails, updated
0
-
reply-language
0.1.0
Restate the settings' reply language beside every prompt, so long English context does not pull replies into English.
sipeng in Prompt, updated
0
-
math-render
0.1.0
Draws the TeX math in assistant replies as Unicode in the terminal: inline formulas on one line, display formulas as character art.
sipeng in Other, updated
0
More other mods
-
telemetry
0.1.0
Plugin analytics: hooks $.telemetry's two events, so a plugin logs an event or marks a feature's use as a first-party row, sent in batches with the session's own credential.
Anthropic in Other, updated
155.5k
-
ruflo-mods
0.17.0
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 cost-tracker budget ladder, a mod trust gate for newly installed mods, and the $.ruflo noun other mods compose their status with. Opt-in and remo...
ruvnet in Other, updated
81.6k
-
universal-audit-log
0.2.0
One hook on * that records every event on $ (tool calls, prompts, turns, other plugins' fs/http/process calls) as JSON lines with origin plugin and tier, duration and outcome, including denials. Buffered and flushed to a JSONL file through $.fs at the end of every turn.
claude-code-templates in Other, updated
33.4k
-
habblaud-mensagens
1.0.3
Leva para a sessão do Claude Code as mensagens que você digita no Habblaud (painel do agente ou terminal), como se você as tivesse digitado no terminal.
Márcio Junior in Other, updated
1.3k
-
agent-relay-mobile
0.1.0
Continue your Claude conversation from Agent Relay on mobile.
Agent Relay in Other, updated
1.1k