Mem Budget — AI skill for Claude Code
Show a 4-tier weighted context plan for a query (working/episodic/semantic/procedural) within a token budget.
How to install Mem Budget
Installs to ~/.claude/skills/oooshisuiooo-gowth-mem-mem-budget/SKILL.md
mkdir -p ~/.claude/skills/oooshisuiooo-gowth-mem-mem-budget && curl -fsSL https://raw.githubusercontent.com/OoOshisuiOoO/gowth-mem/HEAD/commands/mem-budget.md -o ~/.claude/skills/oooshisuiooo-gowth-mem-mem-budget/SKILL.md Restart Claude Code, or start a new session, for it to be picked up.
What Mem Budget does
description: Show a 4-tier weighted context plan for a query (working/episodic/semantic/procedural) within a token budget. Deterministic Jaccard + tier weights + Ebbinghaus recency decay. No LLM.
Preview which files the v3.3 budget planner would load for a query, within a char budget.
Run with the Bash tool:
python3 "${CLAUDE_PLUGIN_ROOT}/hooks/scripts/_budget.py" --query "$*" "$@"
Flags
--ws— workspace (default: active).--query "text"— query text; e
Alternatives in AI
- 09 Query Engine — Prompt 09: Get the QueryEngine (Core LLM Loop) Functional 2.3k ★
- Wiki Query — Query the LLM Wiki and synthesize an answer 2.3k ★
- Claude Delegator — Delegate tasks to Codex GPT 5.2 directly from within Claude Code 909 ★
Full documentation available on GitHub
View Source RepositoryRelated Skills
SEO Manager
Claude Code skill: a complete SEO program from the terminal — research, build, and measure. Real crawl budget
Nmem
Give your AI agents a brain that gets smarter over time. 6-tier memory hierarchy with hybrid search, backgroun
Smart Dispatch Report
Show smart-dispatch routing stats — model distribution, estimated savings, and budget-mode downgrades.
Gremlord
Run Claude Code on any model, with a budget — multi-provider router, LLM-triaged tier routing, spend tracking
V Models
Refresh the Compound V tier→model map — discover the concrete models each backend (claude, codex, antigravity,
Pantheon Status
Show Pantheon version, model tier, and all available agents with status
Related Agents
Loop Perf Prep
Prepare lightweight performance checks (RPS/latency budget assertions) for the current loop iteration. Use pro
Independent Evaluator
Independently score architecture/UI/implementation candidates using traceable evidence and reject hard blocker
Power Reader
POWER explorer and review lens. Read-only mapping of code or review of a diff for a POWER run within a hard ca