Install payload
Install payload is broadly covered in current results.
100% (2/2)
Browse the directory
/
Showing 2 resources for "token-budget"
Saved
/ search · [ ] view density · esc clear input
Active
1 trusted · 1 review in this set — compare to see which signals differ.
Rollout signal scan
1 rollout risk signal in current results
Biggest gaps: metadata review. 0 entries have 2+ required gaps.
good
Most at-risk entries in this view
Adoption queue
Browse adoption queue · balanced
0/2 visible results are ready for staged adoption under this preset.
ready 0caution 2hold 0
Model Routing Cost and Latency Optimizer Skill
1 blockers: Metadata review
caution
70/100
Request metadata review from maintainers or internal owners.
skills/model-routing-cost-latency-optimizer · trust trusted · confidence 83%
MCP Tool Result Budget Review Agent
1 blockers: Metadata review
caution
50/100
Request metadata review from maintainers or internal owners.
Collect package checksum or signed artifact information.
agents/mcp-tool-result-budget-review-agent · trust review · confidence 67%
Decision confidence
Decision confidence scan · balanced
1/2 results are high-confidence for the selected preset.
high 1medium 1low 0
Model Routing Cost and Latency Optimizer Skill
Confident candidate for staged adoption.
high
74/100
Missing: Metadata review
skills/model-routing-cost-latency-optimizer · trust trusted
MCP Tool Result Budget Review Agent
Address Metadata review, Package integrity before broader rollout.
medium
54/100
Missing: Metadata reviewMissing: Package integrity
agents/mcp-tool-result-budget-review-agent · trust review
Freshness distribution
50% of this view is aging or stale
Median age 81 days; 1 fresh of 2 scanned. Re-verify the oldest entries.
Oldest entries in this view
Design and validate model routing strategies that reduce cost and latency while preserving output quality.
Source-backed Claude Code subagent that reviews MCP tool result sizes against output token budgets, flagging tools that exceed the warning and default limits and recommending pagination, filtering, MAX_MCP_OUTPUT_TOKENS tuning, and per-tool size annotations.