rrrrrredy/beforedone

rrrrrredy★ 0GoLast synced: 2026-08-17

Open on GitHub

Require fresh, file-bound verification evidence before coding agents declare completion.

README excerpt

BeforeDone Make coding agents prove they're done. BeforeDone is an open-source evidence gate and incident replay toolkit for coding agents. It turns configured checks into receipts bound to their declared relevant-file scope, evaluates completion through one machine-readable gate, and reconstructs failed runs from observable events and artifacts. Codex hooks can block the first Stop attempt; the DeepSeek Harness Bundle evaluates the native turn-stopping boundary; and the project-local Pi extension evaluates a settled run and can start one corrective continuation. Website and guide Evidence and technical report The empirical technical report freezes the protocol, 144 eligible confirmatory outcomes, analysis, and reproducibility artifact. One superseded attempt that produced no outcome is retained for audit and excluded from all effectiveness denominators. Every condition observed 0/60 unsupported completions in the claim-supportable subset, so the report makes no superiority claim; it documents the mechanism, auditability, and measured verifier cost. The separate beforedone-paper repository contains the full protocol, run records, analysis code, and report sources. This keeps the pr…

View full README on GitHub →
Agentsagent-reliabilityai-agentsclicodexcoding-agentdeepseek-harnessdeveloper-toolsdsh-plugin

Category