Colby McHenry ebae044a43 test(agent-eval): A/B harness scripts (adoption, sufficiency, implementation) ...

Eval tooling built while validating codegraph read-displacement:
- ab-adoption.sh   — does the agent PICK codegraph_node to read, vs the Read tool (build A/B).
- ab-sufficiency.sh — when explore/node IS used, is Read ~0? (with vs without codegraph; lists files Read).
- ab-impl.sh       — same, for an implementation task (fresh copy per run; optional build check).

All pre-warm a daemon + skip the WASM re-exec for reliable nested attach; parse
explore/node[file]/node[sym] vs Read/Grep per run.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

2026-06-08 13:41:33 -04:00

..

ab-adoption.sh

test(agent-eval): A/B harness scripts (adoption, sufficiency, implementation)

2026-06-08 13:41:33 -04:00

ab-hook.sh

feat(mcp): codegraph_node reads files like the Read tool (offset/limit, byte-parity)

2026-06-08 12:00:19 -04:00

ab-impl.sh

test(agent-eval): A/B harness scripts (adoption, sufficiency, implementation)

2026-06-08 13:41:33 -04:00

ab-new-vs-baseline.sh

docs(agent-eval): nested MCP attach is startup-latency, not a hard block (#735)

2026-06-08 10:25:40 -04:00

ab-sufficiency.sh

test(agent-eval): A/B harness scripts (adoption, sufficiency, implementation)

2026-06-08 13:41:33 -04:00

arms-F.sh

Release 0.9.4: framework-aware routing + dynamic-dispatch coverage + retrieval improvements (#365)

2026-05-24 04:41:04 -05:00

arms-matrix.sh

Release 0.9.4: framework-aware routing + dynamic-dispatch coverage + retrieval improvements (#365)

2026-05-24 04:41:04 -05:00

audit.sh

feat(eval): add agent-eval harness and /audit + /publish Claude skills

2026-05-20 09:39:17 -05:00

bench-readme.sh

Release 0.9.4: framework-aware routing + dynamic-dispatch coverage + retrieval improvements (#365)

2026-05-24 04:41:04 -05:00

bench-why-repo.sh

feat(mcp): codegraph_explore as the sole primary tool + store coverage + overload disambiguation (#647)

2026-06-02 10:15:27 -05:00

block-read-hook.sh

Release 0.9.4: framework-aware routing + dynamic-dispatch coverage + retrieval improvements (#365)

2026-05-24 04:41:04 -05:00

hook-settings.json

Release 0.9.4: framework-aware routing + dynamic-dispatch coverage + retrieval improvements (#365)

2026-05-24 04:41:04 -05:00

itrun.sh

feat(resolution): gin middleware-chain synthesizer + Opus 4.8 benchmark refresh (#547)

2026-05-28 23:41:11 -05:00

parse-arms.mjs

Release 0.9.4: framework-aware routing + dynamic-dispatch coverage + retrieval improvements (#365)

2026-05-24 04:41:04 -05:00

parse-bench-readme.mjs

feat(mcp): trace relevance + closure-collection + god-file rendering + cold-start handshake (#580)

2026-05-31 18:41:41 -05:00

parse-run.mjs

feat(eval): add agent-eval harness and /audit + /publish Claude skills

2026-05-20 09:39:17 -05:00

parse-session.mjs

feat(eval): add agent-eval harness and /audit + /publish Claude skills

2026-05-20 09:39:17 -05:00

probe-context.mjs

Release 0.9.4: framework-aware routing + dynamic-dispatch coverage + retrieval improvements (#365)

2026-05-24 04:41:04 -05:00

probe-explore.mjs

Release 0.9.4: framework-aware routing + dynamic-dispatch coverage + retrieval improvements (#365)

2026-05-24 04:41:04 -05:00

probe-node.mjs

Release 0.9.4: framework-aware routing + dynamic-dispatch coverage + retrieval improvements (#365)

2026-05-24 04:41:04 -05:00

probe-sweep.mjs

feat(mcp): multi-module Go trace-quality + small-repo retrieval tuning (#494)

2026-05-28 12:38:03 -05:00

probe-trace.mjs

Release 0.9.4: framework-aware routing + dynamic-dispatch coverage + retrieval improvements (#365)

2026-05-24 04:41:04 -05:00

redirect-read-hook.sh

feat(mcp): codegraph_node reads files like the Read tool (offset/limit, byte-parity)

2026-06-08 12:00:19 -04:00

run-agent.sh

feat(eval): add agent-eval harness and /audit + /publish Claude skills

2026-05-20 09:39:17 -05:00

run-all.sh

feat(eval): add agent-eval harness and /audit + /publish Claude skills

2026-05-20 09:39:17 -05:00

run-arms.sh

Release 0.9.4: framework-aware routing + dynamic-dispatch coverage + retrieval improvements (#365)

2026-05-24 04:41:04 -05:00

seq-matrix.mjs

Release 0.9.4: framework-aware routing + dynamic-dispatch coverage + retrieval improvements (#365)

2026-05-24 04:41:04 -05:00