muse
claudeUse Muse Code from Claude Code to review code or delegate tasks.
3 skills · 8 commands · 1 agent · hooks
0
claude
wisci
WISCI context engineering framework — Write, Isolate, Select, Compress, Iterate. Context store (.wisci/) whose notes quote their code evidence, checked on every load, per-stream handoffs (every compaction summary is one), session hooks, and commits with AI-Context trailers.
/
Plugin wisci from marketplace ph3on1x in ph3on1x/agent-plugins-skills. Commands read from the repo's manifest — 4 days ago.
This plugin runs code on your machine — its hooks fire automatically on events like tool use. The exact commands are listed below; read them before installing.
What it installs
Skills (5)
commitConventional git commit with an AI-Context trailer per changed AI-layer file (.wisci/, CLAUDE.md, AGENTS.md, skills, rules). Optional leading "push".
compressSnapshots session work state — goal, done work, in-progress state, next steps, ruled-out approaches, user constraints — into per-stream handoffs in .wisci/handoff/ for a later session or teammate. Use when the user wants to wrap up, stop for the day, save progress, create a handoff, or continue in a
isolateDelegates research and exploration to subagents with isolated context windows, returns one synthesized report, and saves durable findings to .wisci/context/. Use whenever the user asks to research, investigate, explore, dig into, deep-dive or compare something — a repo's structure, a codebase area o
selectLoads stored project context — a quick orientation with an inventory of stored notes and handoffs, or everything stored on one topic, note or stream — flagging any section whose quoted code is no longer in the codebase. Use when starting or resuming a session, orienting in a project, getting an over
writeSaves knowledge from the conversation — research results, decisions with rationale, architecture notes, API quirks — as a note in .wisci/context/ whose claims about code carry quoted evidence, merging into an existing note on the same topic. Use when the user asks to save, persist, record or write d
Hooks (4)
- SessionStart
sh "${CLAUDE_PLUGIN_ROOT}/hooks/run.sh" session-status
- PreCompact
sh "${CLAUDE_PLUGIN_ROOT}/hooks/run.sh" precompact || exit 1
- PostCompact
sh "${CLAUDE_PLUGIN_ROOT}/hooks/run.sh" mark
- Stop
sh "${CLAUDE_PLUGIN_ROOT}/hooks/run.sh" stop
More from ph3on1x/agent-plugins-skills
All 9 plugins →agy
claudeUse Antigravity from Claude Code to review code or delegate tasks.
3 skills · 7 commands · 1 agent · hooks
0
cmux
claudeSkill for orchestrating independent Claude Code sessions in cmux terminal — split panes, agent monitoring, browser automation, sidebar metadata, notifications, and full CLI coverage.
1 skill · hooks
0
adveloop
claudeGAN-inspired adversarial dev loop — Planner sequentially drives a Generator and Evaluator in fresh cmux panes, with a hard pass/fail gate per deliverable. Adapted from Anthropic's harness-design guidance for long-running agentic apps.
1 skill
0
refine-prompt
claudeInterview-style prompt refiner that picks a framework, fills gaps via AskUserQuestion, assembles a structured XML prompt, confirms, then executes it. In Claude Code, adds a refine prompt button above the prompt box.
1 skill
0
relamo
claudeRecursive Language Model skill — programmatic codebase exploration via persistent Python REPL loop
1 skill
0
Similar plugins
openviking-memory
claudecodexLong-term semantic memory for Claude Code, powered by OpenViking
5 skills · 1 command · 1 MCP server · hooks
volcengine/OpenViking 42,126
memory-engineering
claudeEngineer an agent's forgetting, not just its remembering. Four deterministic stdlib scripts implement the four lenses of agent memory: a cost profiler that splits construction from query spend and reports cost per correct answer (construction energy exceeds total query energy across 300 queries in the Stanford characterization); an architecture picker that scores the four paradigm families — long-context, flat RAG, structure-augmented RAG, agentic — disqualifies on hard constraints, names the cost the winning choice makes you pay, and refuses to pick when the top two tie; a density auditor that classifies every record in a memory directory or JSONL export as FACT / SKILL / LOG / PROSE, finds near-duplicates, and flags stale wording; and a forgetting-policy linter that fails any design with no forgetting rule. Ships cs-memory-engineer agent, /cs-memory-engineering and /cs-forgetting-audit commands, 4 references, and a seven-question forcing worksheet.
1 skill · 2 commands · 1 agent
alirezarezvani/claude-skills 29,725
planning-with-files
claudecodexPersistent project planning files with lifecycle hooks that inject selected plan context. Automatic recovery uses project files only. Explicit catchup modes may read same-project local session records to emit aggregate counts or bounded nonce-framed excerpts. Optional gated mode can request continuation on capable hosts and never runs commands declared in Markdown. No network upload path. Installs across 60+ agents.
6 skills · 13 commands · hooks
OthmanAdi/planning-with-files 28,031
gsd-core
claudeGSD Core is a meta-prompting, context engineering, and spec-driven development system for AI coding agents.
72 skills · 72 commands · 64 agents · hooks
open-gsd/gsd-core 11,494
Diagnose context stuffing vs. context engineering in AI workflows.
1 skill
deanpeters/Product-Manager-Skills 8,001
archcore
claudecodexSpec-driven development and context engineering for AI coding agents, backed by project context in Git.
4 skills · 4 commands · 2 agents · hooks
davepoon/buildwithclaude 3,741
Maintain wisci?
This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.
claude & codex plugins9 plugins