Score breakdown
Popularity is tracked separately. Support, ads, sponsorships, and tips never affect these signals.
Why it matters
Useful for developers running heavy Codex workloads who suspect the top model is overkill for routine edits and want measured routing plus a live view of token spend instead of guessing.
Where this stands now
Agent Smith — local Codex model router plus usage monitor that backs cost claims with benchmarks ranks #70 of 1507 tracked Agent Infrastructure items by composite score (7.2 against a section median of 4.5). The section currently carries 1419 Bronze, 57 Silver, 31 Gold. RepoRadar has retained observations for this record since 2026-10-09 (1 days in the current window). Signal extremes versus the section: momentum at the 96th percentile; novelty at the 95th percentile.
Who should use it
Who should skip it
Skip Agent Smith — local Codex model router plus usage monitor that backs cost claims with benchmarks for now if you are only tracking items with a 'try now' verdict.
About this signal
Agent Smith — local Codex model router plus usage monitor that backs cost claims with benchmarks is tracked by RepoRadar as a developer tool in the Agent Infrastructure section. First seen 2026-10-09; the source record was last checked on 2026-10-09. The current verdict is 'watch' with a Silver tier and moderate setup difficulty. Agent Smith — local Codex model router plus usage monitor that backs cost claims with benchmarks leads on open-source/build quality (8.4) and workflow potential (8.0); its lowest signal is setup ease (6.4), so factor that in before investing setup time. This page summarizes the public evidence on the linked source page and states where additional review is still needed.
How this item is evaluated
The Agent Smith — local Codex model router plus usage monitor that backs cost claims with benchmarks record combines a 7.2/10 composite score with separate popularity (100.0), risk (conditional), and setup (moderate) signals. See the scoring methodology for the current weights and evidence definitions.
Questions worth asking before you adopt this
Putting this into practice? Read How to vet an AI agent or MCP server before you wire it in for the checklist behind this score.
Risk explanation
Router execution uses an existing Codex login, so routed tasks count toward that plan's usage; a skill cannot switch the main task model mid-generation; Cost figures are reference-price multiples on one six-task pilot, not subscription bills; broader quality equivalence is unproven by the author's own account; Young project (created 2026-09-30, last push 2026-10-01); Float is macOS-only with an ad-hoc signature; not hands-on tested.