Estimate token consumption and rate-limit risk for ARAYA workflows.
npx skills add https://github.com/mahg-es/araya --skill token-efficiency-mahg-es
Please help me install this Agent Skill. Skill: token-efficiency Source: https://github.com/mahg-es/araya/tree/main/skills/token-efficiency Command: npx skills add https://github.com/mahg-es/araya --skill token-efficiency-mahg-es
ARAYA optimization layer that maximizes productive work within provider quotas. Works transparently for ARAYA workflows, direct pi conversations, agent delegations, and sub-agent executions.
Provide a token-budget aware optimization plan for the next ARAYA task by decomposing prompts and reusing context.
High-intent search queries and answers about installing and using this skill.
Token consumption is estimated before execution by calculating input, output, and reasoning tokens. This pre-execution estimation helps predict usage and avoid exceeding provider rate limits or token quotas during complex multi-agent orchestration.
When rate-limit risk is detected based on recent usage patterns, the recommended actions are task decomposition, prompt compression, or deferral. These strategies reduce immediate token load and help maintain productive work within provider quotas.
Context capsules are generated to package and reuse information across ARAYA sessions. This mechanism preserves critical context efficiently, reducing redundant token generation when repetitive information is needed across different workflows or agent delegations.
Provider-specific optimization profiles can be applied to tailor token usage strategies to individual provider constraints. This ensures that interactions are optimized according to the specific rate limits and quota rules of the target provider.
Token usage is tracked continuously across the session, culminating in reported efficiency metrics. This tracking monitors consumption patterns, providing visibility into how effectively token quotas are being utilized for productive work.
1molchuanVerify MCP, Codex, and Gemini endpoints and initialize RPI state.
DevMHOneConfigure spending limits, token quotas, and rate-limit policies across API providers.
ryasrkCompress file contents into context packets for constrained agent communication.
CJ-1981Manage token budgets, session state, and context windows for multi-agent workflows.
