01-metrics
01Agent
Analysis dimension: METRICS — quality, completeness, and trustworthiness of auto-iter instrumentation; what the metrics reveal about cycle performance.
3 14d ago A 0 tokens
original MIT
3Stars on the repository
10Mods indexed here, across every type
14d agoLast push, which is what freshness is scored on
MITLicence, which decides whether bodies are shown
02-reports
02Agent
Dimension: REPORTS — quality, accuracy, and usefulness of post-stream analysis reports. Audited reports: stream-2026-05-24-cycles-135-144.md, stream-2026-05-25-cycles-145-154.md, stream-2026-05-29-cycles-168-177.md, stream-2026-06-01-cycles-178-187.md. Ground truth: analysis-2026-06-02-cycles-158-187/dataset.json and…
3 14d ago A 0 tokens
original MIT
Agent
The loop is not predictably consistent across cycles 153–187. Three distinct sub-eras exist with incompatible step schemas, missing logs, and sharply different rework rates. The single recurring root cause is the auto-merge race (CI 2 min completes before DJ 3–5 min; auto-merge fires; BLOCKER lands post-merge). This…
3 14d ago A 0 tokens
original MIT
Agent
Six DJ BLOCKERs escaped to main in cycles 178–187, all confirmed real (0 false positives). The defect classes are: missing test file (×2), API-default mismatch (×1), duplicated abstraction (×1), wrong format helper (×1), zero-value flag bug (×1). Core repo conventions — paging.Collect, typed errors, ContentTypePolicy…
3 14d ago A 0 tokens
original MIT
Agent
Dimension: Adherence to documented workflow rules and explicit user feedback Generated: 2026-06-02 Analyst: review-agent (Claude Sonnet 4.6).
3 14d ago A 0 tokens
original MIT
Agent
Analysis date: 2026-06-02 Dimension: Tokenomics & Speed Window: Cycles 153–187 (30 cycles logged); token-valid subset: 157–164 (May-25 era) + 178–187 (Jun-1 stream). Cycles 168–177 log "tokens": 0 — fully excluded as missing instrumentation, not treated as free.
3 14d ago A 0 tokens
original MIT