Colby McHenry 03069c9118 docs(benchmarks): current-build A/B on all 7 README repos + fix token-measurement bug há 1 mês atrás
..
arms-F.sh a6183d7c83 docs(benchmarks): call-sequence + tool-ablation analysis; agent-eval arms harness há 1 mês atrás
arms-matrix.sh a6183d7c83 docs(benchmarks): call-sequence + tool-ablation analysis; agent-eval arms harness há 1 mês atrás
audit.sh 7fe64b32be feat(eval): add agent-eval harness and /audit + /publish Claude skills há 1 mês atrás
bench-readme.sh 03069c9118 docs(benchmarks): current-build A/B on all 7 README repos + fix token-measurement bug há 1 mês atrás
block-read-hook.sh 25cba9ad7b chore(agent-eval): coverage probes, block-read hook, and design docs há 1 mês atrás
hook-settings.json 25cba9ad7b chore(agent-eval): coverage probes, block-read hook, and design docs há 1 mês atrás
itrun.sh 7fe64b32be feat(eval): add agent-eval harness and /audit + /publish Claude skills há 1 mês atrás
parse-arms.mjs a6183d7c83 docs(benchmarks): call-sequence + tool-ablation analysis; agent-eval arms harness há 1 mês atrás
parse-bench-readme.mjs 03069c9118 docs(benchmarks): current-build A/B on all 7 README repos + fix token-measurement bug há 1 mês atrás
parse-run.mjs 7fe64b32be feat(eval): add agent-eval harness and /audit + /publish Claude skills há 1 mês atrás
parse-session.mjs 7fe64b32be feat(eval): add agent-eval harness and /audit + /publish Claude skills há 1 mês atrás
probe-context.mjs 25cba9ad7b chore(agent-eval): coverage probes, block-read hook, and design docs há 1 mês atrás
probe-explore.mjs 25cba9ad7b chore(agent-eval): coverage probes, block-read hook, and design docs há 1 mês atrás
probe-node.mjs 25cba9ad7b chore(agent-eval): coverage probes, block-read hook, and design docs há 1 mês atrás
probe-trace.mjs 25cba9ad7b chore(agent-eval): coverage probes, block-read hook, and design docs há 1 mês atrás
run-agent.sh 7fe64b32be feat(eval): add agent-eval harness and /audit + /publish Claude skills há 1 mês atrás
run-all.sh 7fe64b32be feat(eval): add agent-eval harness and /audit + /publish Claude skills há 1 mês atrás
run-arms.sh a6183d7c83 docs(benchmarks): call-sequence + tool-ablation analysis; agent-eval arms harness há 1 mês atrás
seq-matrix.mjs a6183d7c83 docs(benchmarks): call-sequence + tool-ablation analysis; agent-eval arms harness há 1 mês atrás