Alex V. 1a46109b97 enhance(#1579): deterministic gsd-tools query eval.score verb (#1583) ...

* feat(#1579): deterministic gsd-tools query eval.score verb

Split C of #1573 (pure code, lowest risk). Adds an eval.score query verb
(coverage*0.6 + infra*0.4; bands 80/60/40) mirroring the verify.* chain;
gsd-eval-auditor consumes it instead of doing weighted arithmetic in-prompt.
Non-breaking — additive only.

arXiv: 2601.15130 (Plausibility Trap/DPDM), 2507.10281 (Table Agent), 2508.15754 (TIR).

* fix(#1579): address review — domain guard, property test, glossary, SKIP_ROOT, inventory/baseline

- C3 input-domain: reject out-of-domain eval.score (require 0<=covered<=total; was emitting overall_score>100 / negatives)
- C1 property test: add tests/eval.property.test.cjs (fast-check) — determinism, band monotonicity, [0,100] bounds, never-throws
- C2 glossary: CONTEXT.md "Eval Scoring Module" entry (source-of-truth path + interface)
- C4: add `eval` to SKIP_ROOT_RESOLUTION (pure arithmetic; no .planning/ access)
- inventory: register generated eval.cjs/eval-command-router.cjs (INVENTORY-MANIFEST.json + INVENTORY.md rows)
- size: regen agent-size baseline for gsd-eval-auditor (reused gsd_run shim + eval.score step)
- eslint: ignore generated eval*.cjs (ADR-457 bin/lib migration coverage)

* fix(#1579): register eval family in alias-drift gates

Add EVAL_COMMAND_ALIASES/EVAL_SUBCOMMANDS to scripts/check-alias-drift.cjs
families and to familyArrayKeys in the manifest-coverage test, so the eval
family lands under the same drift guard as every sibling family
(state/verify/init/phase/phases/validate/roadmap). Addresses trek-e review.

check:alias-drift ok; feat-3251 coverage 9/9; eval suites 10/10.

* docs(#1579): use half-open verdict band ranges in CLI-TOOLS

overall_score is fractional and thresholds are >=80/>=60/>=40, so a score
in [79,80) is correctly NEEDS WORK despite the old '60-79' label. Relabel
bands as 60-<80 / 40-<60 / 0-<40 to match the code. Addresses trek-e nit.

* fix(#1579): validate eval.score CLI inputs

Reject unknown infra tokens and fractional counts, and pin the 80-point verdict boundary including rounding-before-banding behavior.

2026-06-24 17:16:13 -04:00

..

gsd-advisor-researcher.md

enhance(#1577): WebFetch/WebSearch injection isolation + opt-in blocking (#1585)

2026-06-24 17:07:23 -04:00

gsd-ai-researcher.md

enhance(#1577): WebFetch/WebSearch injection isolation + opt-in blocking (#1585)

2026-06-24 17:07:23 -04:00

gsd-assumptions-analyzer.md

enhance(#1577): WebFetch/WebSearch injection isolation + opt-in blocking (#1585)

2026-06-24 17:07:23 -04:00

gsd-code-fixer.md

enh(#1243): consume Claude plugin-provided skills in agent_skills (epic #1258 Phase B) (#1261)

2026-06-15 00:49:12 -04:00

gsd-code-reviewer.md

enh(#1243): consume Claude plugin-provided skills in agent_skills (epic #1258 Phase B) (#1261)

2026-06-15 00:49:12 -04:00

gsd-codebase-mapper.md

enh(#1243): consume Claude plugin-provided skills in agent_skills (epic #1258 Phase B) (#1261)

2026-06-15 00:49:12 -04:00

gsd-debug-session-manager.md

fix(#381): make gsd_run launcher reachable in fresh-shell-per-block runtimes (#1084)

2026-06-11 21:42:52 -04:00

gsd-debugger.md

enh(#1243): consume Claude plugin-provided skills in agent_skills (epic #1258 Phase B) (#1261)

2026-06-15 00:49:12 -04:00

gsd-doc-classifier.md

enhance(#1577): WebFetch/WebSearch injection isolation + opt-in blocking (#1585)

2026-06-24 17:07:23 -04:00

gsd-doc-synthesizer.md

enhance(#1577): WebFetch/WebSearch injection isolation + opt-in blocking (#1585)

2026-06-24 17:07:23 -04:00

gsd-doc-verifier.md

fix(claude): restore namespaced /gsd:<command> references (#3452)

2026-05-12 21:53:24 -04:00

gsd-doc-writer.md

enh(#1243): consume Claude plugin-provided skills in agent_skills (epic #1258 Phase B) (#1261)

2026-06-15 00:49:12 -04:00

gsd-domain-researcher.md

enhance(#1577): WebFetch/WebSearch injection isolation + opt-in blocking (#1585)

2026-06-24 17:07:23 -04:00

gsd-eval-auditor.md

enhance(#1579): deterministic gsd-tools query eval.score verb (#1583)

2026-06-24 17:16:13 -04:00

gsd-eval-planner.md

chore(#771): convert agent color: hex/magenta values to documented named colors (#823)

2026-06-07 18:50:50 -04:00

gsd-executor.md

fix: have executor self-report worktree metadata (#1349)

2026-06-16 14:19:08 -04:00

gsd-framework-selector.md

chore(#771): convert agent color: hex/magenta values to documented named colors (#823)

2026-06-07 18:50:50 -04:00

gsd-integration-checker.md

enh(#1243): consume Claude plugin-provided skills in agent_skills (epic #1258 Phase B) (#1261)

2026-06-15 00:49:12 -04:00

gsd-intel-updater.md

fix(#381): make gsd_run launcher reachable in fresh-shell-per-block runtimes (#1084)

2026-06-11 21:42:52 -04:00

gsd-mempalace-curator.md

feat(#956): add MemPalace memory capability (ADR-857 feature plug-in) (#1201)

2026-06-14 02:09:10 -04:00

gsd-nyquist-auditor.md

enh(#1243): consume Claude plugin-provided skills in agent_skills (epic #1258 Phase B) (#1261)

2026-06-15 00:49:12 -04:00

gsd-pattern-mapper.md

chore(#771): convert agent color: hex/magenta values to documented named colors (#823)

2026-06-07 18:50:50 -04:00

gsd-phase-researcher.md

enhance(#1577): WebFetch/WebSearch injection isolation + opt-in blocking (#1585)

2026-06-24 17:07:23 -04:00

gsd-plan-checker.md

fix(#1478,#1479,#1480): prohibit ungrounded baselines, error-suppressing fallbacks, and stale-artifact authority in planner verify blocks (#1482)

2026-06-20 13:37:03 -04:00

gsd-planner.md

fix(#1626): make the security gate severity-aware via per-threat severity (#1635)

2026-06-23 19:04:13 -04:00

gsd-project-researcher.md

enhance(#1577): WebFetch/WebSearch injection isolation + opt-in blocking (#1585)

2026-06-24 17:07:23 -04:00

gsd-research-synthesizer.md

enhance(#1577): WebFetch/WebSearch injection isolation + opt-in blocking (#1585)

2026-06-24 17:07:23 -04:00

gsd-roadmapper.md

fix(#1455): resolve project-code-prefixed roadmap headings

2026-06-20 18:45:41 -04:00

gsd-security-auditor.md

fix(#1626): make the security gate severity-aware via per-threat severity (#1635)

2026-06-23 19:04:13 -04:00

gsd-ui-auditor.md

enh(#1243): consume Claude plugin-provided skills in agent_skills (epic #1258 Phase B) (#1261)

2026-06-15 00:49:12 -04:00

gsd-ui-checker.md

enh(#1243): consume Claude plugin-provided skills in agent_skills (epic #1258 Phase B) (#1261)

2026-06-15 00:49:12 -04:00

gsd-ui-researcher.md

enhance(#1577): WebFetch/WebSearch injection isolation + opt-in blocking (#1585)

2026-06-24 17:07:23 -04:00

gsd-user-profiler.md

chore(#771): convert agent color: hex/magenta values to documented named colors (#823)

2026-06-07 18:50:50 -04:00

gsd-verifier.md

enh(#966): gate behavior-dependent truths on behavioral evidence in gsd-verifier (#1271)

2026-06-15 15:24:56 -04:00