gstack/docs/designs
Abhijeet Mahagaonkar f7bde4391d feat: add stakeholder lens layer V0.5 (opt-in via --lens)
Ships an opt-in stakeholder-lens layer on /review that runs after the
technical Review Army completes. Zero --lens = zero behavior change.

Core framing: a lens is a loss function, an evidence model, a
materiality threshold, and an escalation policy applied to a bounded
evidence set. Not stakeholder impersonation.

Two lenses in this release:
- insider-abuse (READY) — legitimate authority converted to unauthorized
  outcome without attribution, detection, or approval
- enterprise-readiness (DRAFT) — deployability under CISO / procurement /
  operations governance; ships as DRAFT pending its own Go/No-Go eval

Four additional lens specifications ship in DRAFT / DEFERRED status for
future evaluation: incentive-abuse, regulatory-defensibility,
investor-diligence, competitive-durability.

Design guarantees:
- Preserves Review Army unchanged (P1); no touching of review-army.ts,
  review/specialists/, or review/checklist.md
- Independent lens dispatch (Stage A, no tech findings) followed by
  deterministic reconciliation (Stage B) — clean incremental-value
  measurement
- CTO synthesis as a third stage (not another lens): identifies shared
  technical primitives across independently derived lens findings
  without collapsing distinct perspectives
- Evidence clustering (SHARED_EVIDENCE / MULTI_LENS / EVIDENCE_CLUSTER)
  replaces cross-lens 'confirmation'; production exact-match misses are
  not marked NOVEL
- Read-only tool boundary; lens subagents receive a bounded evidence
  bundle, never repository browse tools
- All stakeholder findings default to ASK / INVESTIGATE; autofix_policy
  ask_always on every lens (no stakeholder auto-fix)
- Append-only event log at ~/.gstack/projects/<slug>/lens-events.jsonl
  with stable finding IDs; sensitive-data controls (local-only,
  owner-only permissions, secret-scanned, GBrain opt-in only)
- Per-lens regression harness (9 fixture types per lens) and per-lens
  Go/No-Go criteria for lens graduation to READY

Insider-abuse ships as the Phase 1 validation lens. Enterprise-readiness
remains DRAFT until its own evaluation gate runs. No Phase 1 lens is
claimed as empirically validated in this PR — validation happens
post-merge per REVIEW_LENSES_V0.md Go/No-Go criteria.

Includes:
- review/lenses/{shared-behavior, registry, insider-abuse, enterprise-readiness,
  incentive-abuse, regulatory-defensibility, investor-diligence,
  competitive-durability}.md
- scripts/lenses/{bundle, events, parser, reconcile, registry, routing,
  synthesis, types, yaml-subset, index}.ts
- scripts/resolvers/lens-layer.ts + gen-skill-docs wiring in
  scripts/gen-skill-docs.ts and scripts/resolvers/index.ts
- bin/gstack-lens-{bundle, event, parse, reconcile, registry, route,
  stats, synthesis-validate}
- hosts/claude/agents/{gstack-cto-synthesizer, gstack-lens-output-validator,
  gstack-lens-reviewer}.md
- test/fixtures/lens-regression/{insider-abuse, enterprise-readiness}/cases.json
- test/lens-{registry, bundle, events, layer-resolver, regression-fixtures}.test.ts
- docs/designs/REVIEW_LENSES_V0.md + docs/{product-context, lens-policy}.yaml.example
- setup and bin/gstack-uninstall wired for lens artifacts
2026-07-31 03:17:44 -07:00
..
BROWSER_SKILLS_V1.md v1.20.0.0 feat: browser-skills runtime + gbrain-support carryover (#1233) 2026-04-28 20:08:04 -07:00
BUN_NATIVE_INFERENCE.md feat(security): ML prompt injection defense for sidebar (v1.4.0.0) (#1089) 2026-04-20 22:18:37 +08:00
CHROME_VS_CHROMIUM_EXPLORATION.md feat: headed mode + sidebar agent + Chrome extension (v0.12.0) (#517) 2026-03-26 11:15:24 -06:00
CONDUCTOR_CHROME_SIDEBAR_INTEGRATION.md feat: headed mode + sidebar agent + Chrome extension (v0.12.0) (#517) 2026-03-26 11:15:24 -06:00
CONDUCTOR_SESSION_API.md feat: headed mode + sidebar agent + Chrome extension (v0.12.0) (#517) 2026-03-26 11:15:24 -06:00
DESIGN_SHOTGUN.md feat: design binary — real UI mockup generation for gstack skills (v0.13.0.0) (#551) 2026-03-27 20:32:59 -06:00
DESIGN_TOOLS_V1.md feat: design binary — real UI mockup generation for gstack skills (v0.13.0.0) (#551) 2026-03-27 20:32:59 -06:00
FIX_1671_PROFILE_MIGRATION.md v1.44.1.0 fix wave: post-windhoek paper-cut — 9 community PRs in one bundle (#1682) 2026-05-25 10:57:15 -07:00
GCOMPACTION.md docs: gstack compact design doc (tabled pending Anthropic API) (#1027) 2026-04-16 15:04:26 -07:00
GSTACK_BROWSER_V0.md feat: GStack Browser — double-click AI browser with anti-bot stealth (#695) 2026-04-04 10:17:05 -07:00
ML_PROMPT_INJECTION_KILLER.md fix: sidebar prompt injection defense (v0.13.4.0) (#611) 2026-03-28 22:10:35 -06:00
PACING_UPDATES_V0.md feat: gstack v1 — simpler prompts + real LOC receipts (v1.0.0.0) (#1039) 2026-04-18 15:05:42 +08:00
PLAN_TUNING_V0.md feat: gstack v1 — simpler prompts + real LOC receipts (v1.0.0.0) (#1039) 2026-04-18 15:05:42 +08:00
PLAN_TUNING_V1.md feat: gstack v1 — simpler prompts + real LOC receipts (v1.0.0.0) (#1039) 2026-04-18 15:05:42 +08:00
REVIEW_LENSES_V0.md feat: add stakeholder lens layer V0.5 (opt-in via --lens) 2026-07-31 03:17:44 -07:00
SELF_LEARNING_V0.md feat: Session Intelligence Layer — /checkpoint + /health + context recovery (v0.15.0.0) (#733) 2026-04-01 00:50:42 -06:00
SESSION_INTELLIGENCE.md feat: session intelligence roadmap + design doc (#727) 2026-03-31 17:01:22 -06:00
SIDEBAR_MESSAGE_FLOW.md feat: gstack browser sidebar = interactive Claude Code REPL with live tab awareness (v1.14.0.0) (#1216) 2026-04-25 22:52:15 -07:00
SLATE_HOST.md docs: Slate agent integration research + design doc (#782) 2026-04-03 06:42:23 -07:00
SLOP_SCAN_FOR_REVIEW_SHIP.md refactor: AI slop reduction with cross-model quality review (v0.16.3.0) (#941) 2026-04-10 17:13:15 -10:00
SYNC_GBRAIN_BATCH_INGEST.md v1.33.0.0 feat: /sync-gbrain memory-stage batch-import refactor (D1-D8) + F6/F9 + signal cleanup (#1432) 2026-05-11 18:47:33 -07:00
v2_PLAN.md v1.46.0.0 feat: gstack v2 foundation — catalog tokens drop 56%, eval-first floor covers all 51 skills (#1712) 2026-05-26 16:50:03 -07:00