@hegemonart/get-design-done 1.59.2 → 1.59.3
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- package/.claude-plugin/marketplace.json +2 -2
- package/.claude-plugin/plugin.json +1 -1
- package/CHANGELOG.md +25 -0
- package/agents/design-advisor.md +1 -1
- package/agents/design-context-checker-gate.md +0 -1
- package/agents/design-context-checker.md +0 -1
- package/agents/design-context-reviewer-gate.md +0 -1
- package/agents/design-context-reviewer.md +0 -1
- package/agents/design-integration-checker-gate.md +0 -1
- package/agents/design-integration-checker.md +0 -1
- package/agents/design-plan-checker.md +0 -1
- package/agents/design-verifier-gate.md +0 -1
- package/agents/design-verifier.md +0 -1
- package/agents/prototype-gate.md +0 -1
- package/agents/quality-gate-runner.md +0 -1
- package/package.json +1 -1
|
@@ -5,14 +5,14 @@
|
|
|
5
5
|
},
|
|
6
6
|
"metadata": {
|
|
7
7
|
"description": "Get Design Done — 5-stage agent-orchestrated design pipeline (Brief → Explore → Plan → Design → Verify) for AI coding agents. 64 agents, 95 skills, 39 connection integrations, two MCP servers, opt-in SQLite state backbone, bidirectional Figma write-back, and a reflector-driven self-improvement loop. Cross-runtime install for Claude Code, Codex, Cursor, OpenCode, Gemini, and more.",
|
|
8
|
-
"version": "1.59.
|
|
8
|
+
"version": "1.59.3"
|
|
9
9
|
},
|
|
10
10
|
"plugins": [
|
|
11
11
|
{
|
|
12
12
|
"name": "get-design-done",
|
|
13
13
|
"source": "./",
|
|
14
14
|
"description": "Agent-orchestrated 5-stage design pipeline (Brief → Explore → Plan → Design → Verify) for AI coding agents. 64 specialized agents, 95 skills, 39 connection integrations (Figma, Refero, Preview, Storybook, Chromatic, Graphify, Linear, Jira, Notion, …), bidirectional Figma write-back, queryable intel store, opt-in SQLite state backbone, and a reflector-driven self-improvement loop. Two MCP servers (gdd-state for typed STATE mutators, gdd-mcp for 13 read-only project-priming tools), tier-aware routing with cost telemetry, and defense-in-depth hooks (protected paths, MCP circuit breaker, injection scanner, budget enforcer). Cross-runtime install for Claude Code, Codex, Cursor, OpenCode, Gemini, Copilot, and more.",
|
|
15
|
-
"version": "1.59.
|
|
15
|
+
"version": "1.59.3",
|
|
16
16
|
"author": {
|
|
17
17
|
"name": "hegemonart"
|
|
18
18
|
},
|
|
@@ -1,7 +1,7 @@
|
|
|
1
1
|
{
|
|
2
2
|
"name": "get-design-done",
|
|
3
3
|
"short_name": "gdd",
|
|
4
|
-
"version": "1.59.
|
|
4
|
+
"version": "1.59.3",
|
|
5
5
|
"description": "Agent-orchestrated 5-stage design pipeline (Brief → Explore → Plan → Design → Verify) for AI coding agents. 64 specialized agents, 95 skills, 39 connection integrations (Figma, Refero, Preview, Storybook, Chromatic, Graphify, Linear, Jira, Notion, …), bidirectional Figma write-back, queryable intel store for O(1) design-surface lookups, opt-in SQLite state backbone, and a reflector-driven self-improvement loop. Two MCP servers (`gdd-state` for typed STATE mutators, `gdd-mcp` for 13 read-only project-priming tools), tier-aware agent routing with cost telemetry, defense-in-depth hooks (protected paths, MCP circuit breaker, injection scanner, budget enforcer), and a cross-runtime install layer for Claude Code, Codex, Cursor, OpenCode, Gemini, Copilot, and more.",
|
|
6
6
|
"author": {
|
|
7
7
|
"name": "hegemonart",
|
package/CHANGELOG.md
CHANGED
|
@@ -4,6 +4,31 @@ All notable changes to get-design-done are documented here. Versions follow [sem
|
|
|
4
4
|
|
|
5
5
|
---
|
|
6
6
|
|
|
7
|
+
## [1.59.3] - 2026-06-04
|
|
8
|
+
|
|
9
|
+
Third point release of the **v1.59 "Audit Closeout & Honesty Pass"** milestone. A routing-coherence pass on agent model/tier declarations.
|
|
10
|
+
|
|
11
|
+
### Added
|
|
12
|
+
|
|
13
|
+
- **Model-vs-default-tier coherence check** in `scripts/validate-frontmatter.ts`. The CI frontmatter gate now errors when an agent declares a literal `model` that contradicts its `default-tier` (for example `model: sonnet` under `default-tier: opus`), and emits a non-failing advisory when a haiku-tier agent uses `model: inherit` (which would defeat the cheap-gate cost intent).
|
|
14
|
+
|
|
15
|
+
### Fixed
|
|
16
|
+
|
|
17
|
+
- **Two tier contradictions corrected.** `design-advisor` (was `model: sonnet` under an opus-tier rationale, now `model: inherit`) and `design-plan-checker` (dropped the contradicting `model: sonnet`; it resolves via `default-tier: haiku`).
|
|
18
|
+
- **Cheap-gate cost governance restored.** Stripped the redundant `model: inherit` from 10 haiku-tier gate/checker agents (`design-context-checker`, `design-context-reviewer`, `design-integration-checker`, `design-verifier`, their four `-gate` variants, `prototype-gate`, `quality-gate-runner`) so they resolve to the cheap haiku model instead of inheriting the session model.
|
|
19
|
+
|
|
20
|
+
### Note
|
|
21
|
+
|
|
22
|
+
- The rest of the original 59.3 plan was already shipped by earlier phases: peer-CLI `delegate_to`, the intel-updater PostToolUse hook, the context-reviewer wiring in explore, the planner/verifier output-contracts, and the `audit-aggregator` / `hedge-ensemble` dead-code removal. `touches-pattern-miner` was retained because it has a live caller (`incubator-proposals`); it is not dead code.
|
|
23
|
+
|
|
24
|
+
### Breaking changes
|
|
25
|
+
|
|
26
|
+
None.
|
|
27
|
+
|
|
28
|
+
5,049/5,049 tests pass.
|
|
29
|
+
|
|
30
|
+
---
|
|
31
|
+
|
|
7
32
|
## [1.59.2] - 2026-06-04
|
|
8
33
|
|
|
9
34
|
Second point release of the **v1.59 "Audit Closeout & Honesty Pass"** milestone. Wires the AI-native Wave-2 connections and reconciles the connection count to the honest number.
|
package/agents/design-advisor.md
CHANGED
|
@@ -3,7 +3,7 @@ name: design-advisor
|
|
|
3
3
|
description: Researches a single gray area and produces a 5-column comparison table with rationale. Spawned by design-context-builder when a gray area exceeds judgment threshold. Returns inline text - no file output.
|
|
4
4
|
tools: Read, Grep, Glob, WebSearch
|
|
5
5
|
color: blue
|
|
6
|
-
model:
|
|
6
|
+
model: inherit
|
|
7
7
|
default-tier: opus
|
|
8
8
|
tier-rationale: "Questions prompts to surface ambiguity; wrong advice cascades across downstream spawns"
|
|
9
9
|
parallel-safe: always
|
|
@@ -3,7 +3,6 @@ name: design-context-checker-gate
|
|
|
3
3
|
description: "Cheap Haiku gate that reads a diff and decides whether design-context-checker should spawn. Spawns only when DESIGN-CONTEXT.md itself was modified."
|
|
4
4
|
tools: Read, Bash, Grep
|
|
5
5
|
color: cyan
|
|
6
|
-
model: inherit
|
|
7
6
|
default-tier: haiku
|
|
8
7
|
tier-rationale: "Cheap diff-scan gate - context checker only runs when DESIGN-CONTEXT.md changed"
|
|
9
8
|
size_budget: S
|
|
@@ -3,7 +3,6 @@ name: design-context-checker
|
|
|
3
3
|
description: Validates .design/DESIGN-CONTEXT.md across 6 dimensions (copy specificity, color contract, typography scale, spacing scale, must-have testability, goal observability). Returns APPROVED or BLOCKED with per-dimension BLOCK/FLAG/PASS verdicts. Spawned by the discover stage after design-context-builder completes.
|
|
4
4
|
tools: Read, Grep, Glob
|
|
5
5
|
color: cyan
|
|
6
|
-
model: inherit
|
|
7
6
|
default-tier: haiku
|
|
8
7
|
tier-rationale: "Schema-driven completeness check; deterministic rubric, no reasoning density needed"
|
|
9
8
|
size_budget: LARGE
|
|
@@ -3,7 +3,6 @@ name: design-context-reviewer-gate
|
|
|
3
3
|
description: "Cheap Haiku gate that reads a change signal and decides whether design-context-reviewer should spawn. Suppresses the reviewer when project change is below 5 percent."
|
|
4
4
|
tools: Read, Bash, Grep
|
|
5
5
|
color: cyan
|
|
6
|
-
model: inherit
|
|
7
6
|
default-tier: haiku
|
|
8
7
|
tier-rationale: "Cheap change-signal gate - graph reviewer only runs when the graph changed enough to matter"
|
|
9
8
|
size_budget: S
|
|
@@ -3,7 +3,6 @@ name: design-context-reviewer
|
|
|
3
3
|
description: "Reviews the merged .design/context-graph.json after mapper assembly across 9 checks (schema validity, referential integrity, completeness, layer coverage, id uniqueness, summary quality, edge-expectation consistency, type-prefix consistency, coverage-vs-stack). Hard-rejects on critical breakage; soft-warns on advisory issues. Spawned by the explore stage after the synthesizer merges all fragments."
|
|
4
4
|
tools: Read, Grep, Glob
|
|
5
5
|
color: cyan
|
|
6
|
-
model: inherit
|
|
7
6
|
default-tier: haiku
|
|
8
7
|
tier-rationale: "Schema-driven graph review on top of a deterministic validator; rubric-bound, no reasoning density needed"
|
|
9
8
|
size_budget: LARGE
|
|
@@ -3,7 +3,6 @@ name: design-integration-checker-gate
|
|
|
3
3
|
description: "Cheap Haiku gate that reads a diff and decides whether design-integration-checker should spawn. Returns {spawn, rationale}. Short-circuits when no D-XX decisions or reference docs were touched."
|
|
4
4
|
tools: Read, Bash, Grep
|
|
5
5
|
color: blue
|
|
6
|
-
model: inherit
|
|
7
6
|
default-tier: haiku
|
|
8
7
|
tier-rationale: "Cheap diff-scan gate - expensive integration checker spawned only on heuristic hit"
|
|
9
8
|
size_budget: S
|
|
@@ -3,7 +3,6 @@ name: design-integration-checker
|
|
|
3
3
|
description: Verifies D-XX design decisions from DESIGN-CONTEXT.md are actually wired through source code via grep-based checks on tokens, colors, spacing, component patterns. Runs AFTER design-verifier in the verify stage. Returns Connected/Orphaned/Missing counts.
|
|
4
4
|
tools: Read, Bash, Grep, Glob
|
|
5
5
|
color: blue
|
|
6
|
-
model: inherit
|
|
7
6
|
default-tier: haiku
|
|
8
7
|
tier-rationale: "Cross-artifact link-integrity scan; structured input, structured output"
|
|
9
8
|
size_budget: LARGE
|
|
@@ -3,7 +3,6 @@ name: design-plan-checker
|
|
|
3
3
|
description: Validates DESIGN-PLAN.md will achieve DESIGN-CONTEXT.md brief goals before execution. Goal-backward check on plan structure, not on code. Spawned by the plan stage after design-planner completes.
|
|
4
4
|
tools: Read, Bash, Grep, Glob
|
|
5
5
|
color: green
|
|
6
|
-
model: sonnet
|
|
7
6
|
default-tier: haiku
|
|
8
7
|
tier-rationale: "Checks plan artifact against a fixed schema; boolean + gap-list output fits Haiku"
|
|
9
8
|
parallel-safe: always
|
|
@@ -3,7 +3,6 @@ name: design-verifier-gate
|
|
|
3
3
|
description: "Cheap Haiku gate that reads a diff and decides whether design-verifier should spawn. Returns {spawn, rationale}. Short-circuits verifier spawns on small or copy-only changes that don't touch design-system surfaces."
|
|
4
4
|
tools: Read, Bash, Grep
|
|
5
5
|
color: green
|
|
6
|
-
model: inherit
|
|
7
6
|
default-tier: haiku
|
|
8
7
|
tier-rationale: "Cheap diff-scan gate - expensive verifier spawned only on heuristic hit"
|
|
9
8
|
size_budget: S
|
|
@@ -3,7 +3,6 @@ name: design-verifier
|
|
|
3
3
|
description: Goal-backward verification of design outcomes against .design/STATE.md must-haves, NNG heuristics, and audit rubric. Returns pass result or structured gap list. Spawned by the verify stage.
|
|
4
4
|
tools: Read, Write, Bash, Grep, Glob, mcp__Claude_Preview__preview_list, mcp__Claude_Preview__preview_navigate, mcp__Claude_Preview__preview_screenshot, mcp__Claude_Preview__preview_eval, mcp__Claude_Preview__preview_snapshot, mcp__Claude_Preview__preview_inspect
|
|
5
5
|
color: green
|
|
6
|
-
model: inherit
|
|
7
6
|
default-tier: haiku
|
|
8
7
|
tier-rationale: "Verifier runs structured goal-backward checks - cheap Haiku is sufficient and fast"
|
|
9
8
|
size_budget: XXL
|
package/agents/prototype-gate.md
CHANGED
|
@@ -3,7 +3,6 @@ name: prototype-gate
|
|
|
3
3
|
description: "Cheap Haiku gate that scores sketch / spike signals from the active brief / context / plan and emits a JSON verdict recommending whether to prototype before continuing."
|
|
4
4
|
tools: Read, Bash, Grep
|
|
5
5
|
color: yellow
|
|
6
|
-
model: inherit
|
|
7
6
|
default-tier: haiku
|
|
8
7
|
tier-rationale: "Signal-counting rubric over a few small inputs - no synthesis, no writes, no agent spawning. Belongs on Haiku to keep gate latency cheap (≤ 2 s typical)."
|
|
9
8
|
size_budget: S
|
|
@@ -3,7 +3,6 @@ name: quality-gate-runner
|
|
|
3
3
|
description: "Cheap Haiku classifier that ingests {command, exit_code, stderr} tuples from the quality-gate skill's parallel run and emits a JSON verdict - pass/fail plus per-bucket failure groupings (lint / type / test / visual / a11y). Read-only. Does not run commands itself."
|
|
4
4
|
tools: Read, Bash, Grep
|
|
5
5
|
color: amber
|
|
6
|
-
model: inherit
|
|
7
6
|
default-tier: haiku
|
|
8
7
|
tier-rationale: "Pattern-match exit codes and bucket stderr into five named categories - no synthesis, no rewrites, no spawning. Belongs on Haiku to keep classification cost trivial relative to the actual command runs."
|
|
9
8
|
size_budget: S
|
package/package.json
CHANGED
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
{
|
|
2
2
|
"name": "@hegemonart/get-design-done",
|
|
3
|
-
"version": "1.59.
|
|
3
|
+
"version": "1.59.3",
|
|
4
4
|
"description": "A design-quality pipeline for AI coding agents: brief, explore, plan, design, and verify UI work against your design system.",
|
|
5
5
|
"author": "Hegemon",
|
|
6
6
|
"homepage": "https://github.com/hegemonart/get-design-done",
|