@boyingliu01/xp-gate 0.35.23 → 0.36.0
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/adapter-common.sh +78 -36
- package/adapters/csharp.sh +245 -0
- package/adapters/gate-3.sh +1 -1
- package/adapters/gate-4.sh +1 -1
- package/adapters/gate-9.sh +37 -2
- package/adapters/go.sh +6 -11
- package/adapters/iac.sh +45 -5
- package/adapters/python.sh +6 -11
- package/bin/xp-gate.js +18 -11
- package/gate-10.sh +18 -3
- package/gate-13-compiler-strictness.sh +181 -0
- package/gate-3.sh +1 -1
- package/gate-4.sh +1 -1
- package/gate-9.sh +37 -2
- package/gates/common.ts +9 -2
- package/hooks/adapter-common.sh +78 -36
- package/hooks/gate-10.sh +18 -3
- package/hooks/gate-13-compiler-strictness.sh +181 -0
- package/hooks/gate-3.sh +1 -1
- package/hooks/gate-4.sh +1 -1
- package/hooks/gate-9.sh +37 -2
- package/hooks/gate-registry.sh +161 -0
- package/hooks/lib/test-failure.sh +29 -4
- package/hooks/pre-commit +122 -3
- package/lib/__tests__/agent-runtime-journal.test.js +42 -18
- package/lib/__tests__/check-single-file.test.js +55 -4
- package/lib/__tests__/detect-deps-dsh-profile.test.js +43 -0
- package/lib/__tests__/doctor-delphi.test.js +178 -3
- package/lib/__tests__/doctor-tui-skill-freshness.test.js +3 -3
- package/lib/__tests__/install-skill-full-dir.test.js +45 -2
- package/lib/__tests__/install-skill.test.js +191 -23
- package/lib/__tests__/mirror-sync.test.js +23 -5
- package/lib/__tests__/uninstall-global-residue.test.js +394 -9
- package/lib/__tests__/update-skill-flags.test.js +78 -0
- package/lib/__tests__/update-skill.test.js +334 -57
- package/lib/detect-deps.js +24 -0
- package/lib/doctor.js +80 -12
- package/lib/install-skill.js +85 -21
- package/lib/mattpocock-license-verdict.json +1 -1
- package/lib/uninstall.js +143 -12
- package/lib/update-skill.js +239 -28
- package/mock-policy/AGENTS.md +4 -4
- package/mutation/AGENTS.md +4 -4
- package/package.json +1 -1
- package/plugins/claude-code/.claude-plugin/plugin.json +1 -1
- package/plugins/claude-code/skills/delphi-review/AGENTS.md +4 -4
- package/plugins/claude-code/skills/sprint-flow/AGENTS.md +4 -4
- package/plugins/claude-code/skills/test-specification-alignment/AGENTS.md +4 -4
- package/plugins/dsh/lib/index.d.ts.map +1 -1
- package/plugins/dsh/lib/index.js +7 -4
- package/plugins/dsh/package.json +1 -1
- package/plugins/dsh/skills/delphi-review/AGENTS.md +4 -4
- package/plugins/dsh/skills/sprint-flow/AGENTS.md +4 -4
- package/plugins/dsh/skills/test-specification-alignment/AGENTS.md +4 -4
- package/plugins/dsh/src/index.test.ts +25 -0
- package/plugins/dsh/src/index.ts +7 -4
- package/plugins/opencode/package.json +1 -1
- package/plugins/opencode/skills/delphi-review/AGENTS.md +4 -4
- package/plugins/opencode/skills/sprint-flow/AGENTS.md +4 -4
- package/plugins/opencode/skills/test-specification-alignment/AGENTS.md +4 -4
- package/plugins/qoder/plugin.json +1 -1
- package/plugins/qoder/skills/delphi-review/AGENTS.md +4 -4
- package/plugins/qoder/skills/sprint-flow/AGENTS.md +4 -4
- package/plugins/qoder/skills/test-specification-alignment/AGENTS.md +4 -4
- package/principles/AGENTS.md +4 -4
- package/principles/adapters/csharp.ts +309 -0
- package/principles/analyzer.ts +5 -0
- package/scripts/delphi-external-review.cjs +130 -101
- package/skills/delphi-review/AGENTS.md +4 -4
- package/skills/sprint-flow/AGENTS.md +4 -4
- package/skills/test-specification-alignment/AGENTS.md +4 -4
package/mock-policy/AGENTS.md
CHANGED
|
@@ -1,9 +1,9 @@
|
|
|
1
1
|
# SRC/MOCK-POLICY KNOWLEDGE BASE
|
|
2
2
|
|
|
3
|
-
**Generated:** 2026-11-
|
|
4
|
-
**Commit:**
|
|
5
|
-
**Branch:**
|
|
6
|
-
**Version:** 0.
|
|
3
|
+
**Generated:** 2026-11-04
|
|
4
|
+
**Commit:** eb2097b0
|
|
5
|
+
**Branch:** sprint/2026-11-03-02
|
|
6
|
+
**Version:** 0.36.0.0
|
|
7
7
|
|
|
8
8
|
## OVERVIEW
|
|
9
9
|
Mock layering policy enforcement — Gate M3 of pre-push hook. Ensures integration tests use real implementations for internal dependencies, mock external dependencies, and annotate pending mocks with removal plans. Combines project scope scanning, mock decision engine, and per-file validation into a single pipeline.
|
package/mutation/AGENTS.md
CHANGED
|
@@ -1,9 +1,9 @@
|
|
|
1
1
|
# SRC/MUTATION KNOWLEDGE BASE
|
|
2
2
|
|
|
3
|
-
**Generated:** 2026-11-
|
|
4
|
-
**Commit:**
|
|
5
|
-
**Branch:**
|
|
6
|
-
**Version:** 0.
|
|
3
|
+
**Generated:** 2026-11-04
|
|
4
|
+
**Commit:** eb2097b0
|
|
5
|
+
**Branch:** sprint/2026-11-03-02
|
|
6
|
+
**Version:** 0.36.0.0
|
|
7
7
|
|
|
8
8
|
## OVERVIEW
|
|
9
9
|
**Gate M** (incremental mutation testing) + **Gate M2** helpers (test-layer detection used by `src/mock-policy/`). Pre-push quality gate. TypeScript-only; uses Stryker.
|
package/package.json
CHANGED
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
{
|
|
2
2
|
"name": "xp-gate",
|
|
3
|
-
"version": "0.
|
|
3
|
+
"version": "0.36.0",
|
|
4
4
|
"displayName": "XP-Gate",
|
|
5
5
|
"description": "Extreme Programming quality gates + AI workflow skills for Claude Code. Includes 12 pre-commit gates (Gate 0-11), 8 pre-push gates, Sprint Flow (6 phases), and Delphi multi-expert review (>=90% consensus).",
|
|
6
6
|
"author": {
|
|
@@ -1,9 +1,9 @@
|
|
|
1
1
|
# SKILLS/DELPHI-REVIEW KNOWLEDGE BASE
|
|
2
2
|
|
|
3
|
-
**Generated:** 2026-11-
|
|
4
|
-
**Commit:**
|
|
5
|
-
**Branch:**
|
|
6
|
-
**Version:** 0.
|
|
3
|
+
**Generated:** 2026-11-04
|
|
4
|
+
**Commit:** eb2097b0
|
|
5
|
+
**Branch:** sprint/2026-11-03-02
|
|
6
|
+
**Version:** 0.36.0.0
|
|
7
7
|
|
|
8
8
|
## OVERVIEW
|
|
9
9
|
Delphi Consensus Review — multi-round anonymous expert review (≥90% threshold, exactly 3 experts with distinct executable model IDs). Supports design, requirements, and code-walkthrough modes.
|
|
@@ -1,9 +1,9 @@
|
|
|
1
1
|
# SKILLS/SPRINT-FLOW KNOWLEDGE BASE
|
|
2
2
|
|
|
3
|
-
**Generated:** 2026-11-
|
|
4
|
-
**Commit:**
|
|
5
|
-
**Branch:**
|
|
6
|
-
**Version:** 0.
|
|
3
|
+
**Generated:** 2026-11-04
|
|
4
|
+
**Commit:** eb2097b0
|
|
5
|
+
**Branch:** sprint/2026-11-03-02
|
|
6
|
+
**Version:** 0.36.0.0
|
|
7
7
|
|
|
8
8
|
## OVERVIEW
|
|
9
9
|
**6-phase** development pipeline (v2.0 compact redesign, Issue #290): PREP → DESIGN → BUILD → VERIFY → SHIP → CLOSE. Phase 3/6 BUILD default build mode is **ralph-loop** (REQ-level iteration, 40-67% token savings vs parallel). HARD-GATE between DESIGN (2/6) and BUILD (3/6): design must pass Delphi review (≥90% consensus) before any coding.
|
|
@@ -1,9 +1,9 @@
|
|
|
1
1
|
# SKILLS/TEST-SPECIFICATION-ALIGNMENT KNOWLEDGE BASE
|
|
2
2
|
|
|
3
|
-
**Generated:** 2026-11-
|
|
4
|
-
**Commit:**
|
|
5
|
-
**Branch:**
|
|
6
|
-
**Version:** 0.
|
|
3
|
+
**Generated:** 2026-11-04
|
|
4
|
+
**Commit:** eb2097b0
|
|
5
|
+
**Branch:** sprint/2026-11-03-02
|
|
6
|
+
**Version:** 0.36.0.0
|
|
7
7
|
|
|
8
8
|
## OVERVIEW
|
|
9
9
|
Test-Specification Alignment Engine — two-stage validation ensuring tests accurately reflect requirements and design specs.
|
|
@@ -1 +1 @@
|
|
|
1
|
-
{"version":3,"file":"index.d.ts","sourceRoot":"","sources":["../src/index.ts"],"names":[],"mappings":"AAQA,OAAO,CAAC,MAAM,0BAA0B,CAAA;AACxC,OAAO,KAAK,EAAE,OAAO,EAAE,MAAM,qBAAqB,CAAA;AA0BlD;;;;;;;;;;;;;;;;GAgBG;AACH,eAAO,MAAM,UAAU,GAAI,CAAC,EAAE,OAAO,CAAC,EAAE,OAAO,MAAM;;;GAA6C,CAAA;AAElG,eAAO,MAAM,IAAI,iBAAiB,CAAA;AAGlC,eAAO,MAAM,MAAM,UAA+B,CAAA;AAkQlD;;;;;;;;GAQG;AACH,wBAAgB,mBAAmB,CAAC,KAAK,EAAE,MAAM,GAAG,MAAM,GAAG,SAAS,CAKrE;AAED;;;;;;;;;;;;;;GAcG;AACH,wBAAgB,aAAa,IAAI,MAAM,CAQtC;AAED;;;;;;GAMG;AACH,wBAAgB,kBAAkB,CAAC,QAAQ,EAAE,MAAM,EAAE,SAAS,EAAE,MAAM,GAAG,MAAM,CAE9E;AA8ID;;;;;;;;;;;GAWG;AACH,eAAO,MAAM,MAAM;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;aA4BjB,CAAA;AAEF,wBAAgB,KAAK,CAAC,GAAG,EAAE,OAAO,EAAE,MAAM,GAAE,OAAY,GAAG,IAAI,
|
|
1
|
+
{"version":3,"file":"index.d.ts","sourceRoot":"","sources":["../src/index.ts"],"names":[],"mappings":"AAQA,OAAO,CAAC,MAAM,0BAA0B,CAAA;AACxC,OAAO,KAAK,EAAE,OAAO,EAAE,MAAM,qBAAqB,CAAA;AA0BlD;;;;;;;;;;;;;;;;GAgBG;AACH,eAAO,MAAM,UAAU,GAAI,CAAC,EAAE,OAAO,CAAC,EAAE,OAAO,MAAM;;;GAA6C,CAAA;AAElG,eAAO,MAAM,IAAI,iBAAiB,CAAA;AAGlC,eAAO,MAAM,MAAM,UAA+B,CAAA;AAkQlD;;;;;;;;GAQG;AACH,wBAAgB,mBAAmB,CAAC,KAAK,EAAE,MAAM,GAAG,MAAM,GAAG,SAAS,CAKrE;AAED;;;;;;;;;;;;;;GAcG;AACH,wBAAgB,aAAa,IAAI,MAAM,CAQtC;AAED;;;;;;GAMG;AACH,wBAAgB,kBAAkB,CAAC,QAAQ,EAAE,MAAM,EAAE,SAAS,EAAE,MAAM,GAAG,MAAM,CAE9E;AA8ID;;;;;;;;;;;GAWG;AACH,eAAO,MAAM,MAAM;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;aA4BjB,CAAA;AAEF,wBAAgB,KAAK,CAAC,GAAG,EAAE,OAAO,EAAE,MAAM,GAAE,OAAY,GAAG,IAAI,CAmC9D"}
|
package/plugins/dsh/lib/index.js
CHANGED
|
@@ -483,10 +483,13 @@ export function apply(ctx, config = {}) {
|
|
|
483
483
|
// delphi-review work on a machine whose key lives in the credential store rather
|
|
484
484
|
// than in the host process's inherited environment.
|
|
485
485
|
//
|
|
486
|
-
//
|
|
487
|
-
//
|
|
488
|
-
//
|
|
489
|
-
|
|
486
|
+
// Read via ctx.get() rather than a bare ctx.credentials (#721): Cordis's context
|
|
487
|
+
// proxy throws "cannot get property ... without inject" on any property that is
|
|
488
|
+
// neither a declared service nor in this plugin's inject list. "credentials" is
|
|
489
|
+
// deliberately NOT in inject — adding it would stop the plugin from loading on a
|
|
490
|
+
// host without the service, discarding the process.env fallback below. ctx.get()
|
|
491
|
+
// is the inject-free read and returns undefined when the host provides none.
|
|
492
|
+
const credentials = ctx.get?.("credentials");
|
|
490
493
|
const resolveApiKey = createCredentialResolver(credentials, process.env);
|
|
491
494
|
ctx.tools.register(gateCheckTool(shell, dialect));
|
|
492
495
|
ctx.tools.register(gatePrinciplesTool(shell, dialect));
|
package/plugins/dsh/package.json
CHANGED
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
{
|
|
2
2
|
"name": "@boyingliu01/dsh-plugin-xp-gate",
|
|
3
|
-
"version": "0.
|
|
3
|
+
"version": "0.36.0",
|
|
4
4
|
"description": "XP-Gate deterministic quality gates + AI workflow skills as a DeepSeek Harness (DSH) native plugin: gate-check / gate-principles / gate-arch tools + 12 SKILL.md skills",
|
|
5
5
|
"type": "module",
|
|
6
6
|
"main": "./lib/index.js",
|
|
@@ -1,9 +1,9 @@
|
|
|
1
1
|
# SKILLS/DELPHI-REVIEW KNOWLEDGE BASE
|
|
2
2
|
|
|
3
|
-
**Generated:** 2026-11-
|
|
4
|
-
**Commit:**
|
|
5
|
-
**Branch:**
|
|
6
|
-
**Version:** 0.
|
|
3
|
+
**Generated:** 2026-11-04
|
|
4
|
+
**Commit:** eb2097b0
|
|
5
|
+
**Branch:** sprint/2026-11-03-02
|
|
6
|
+
**Version:** 0.36.0.0
|
|
7
7
|
|
|
8
8
|
## OVERVIEW
|
|
9
9
|
Delphi Consensus Review — multi-round anonymous expert review (≥90% threshold, exactly 3 experts with distinct executable model IDs). Supports design, requirements, and code-walkthrough modes.
|
|
@@ -1,9 +1,9 @@
|
|
|
1
1
|
# SKILLS/SPRINT-FLOW KNOWLEDGE BASE
|
|
2
2
|
|
|
3
|
-
**Generated:** 2026-11-
|
|
4
|
-
**Commit:**
|
|
5
|
-
**Branch:**
|
|
6
|
-
**Version:** 0.
|
|
3
|
+
**Generated:** 2026-11-04
|
|
4
|
+
**Commit:** eb2097b0
|
|
5
|
+
**Branch:** sprint/2026-11-03-02
|
|
6
|
+
**Version:** 0.36.0.0
|
|
7
7
|
|
|
8
8
|
## OVERVIEW
|
|
9
9
|
**6-phase** development pipeline (v2.0 compact redesign, Issue #290): PREP → DESIGN → BUILD → VERIFY → SHIP → CLOSE. Phase 3/6 BUILD default build mode is **ralph-loop** (REQ-level iteration, 40-67% token savings vs parallel). HARD-GATE between DESIGN (2/6) and BUILD (3/6): design must pass Delphi review (≥90% consensus) before any coding.
|
|
@@ -1,9 +1,9 @@
|
|
|
1
1
|
# SKILLS/TEST-SPECIFICATION-ALIGNMENT KNOWLEDGE BASE
|
|
2
2
|
|
|
3
|
-
**Generated:** 2026-11-
|
|
4
|
-
**Commit:**
|
|
5
|
-
**Branch:**
|
|
6
|
-
**Version:** 0.
|
|
3
|
+
**Generated:** 2026-11-04
|
|
4
|
+
**Commit:** eb2097b0
|
|
5
|
+
**Branch:** sprint/2026-11-03-02
|
|
6
|
+
**Version:** 0.36.0.0
|
|
7
7
|
|
|
8
8
|
## OVERVIEW
|
|
9
9
|
Test-Specification Alignment Engine — two-stage validation ensuring tests accurately reflect requirements and design specs.
|
|
@@ -80,6 +80,31 @@ describe("apply", () => {
|
|
|
80
80
|
expect(names).toContain("gate-arch")
|
|
81
81
|
})
|
|
82
82
|
|
|
83
|
+
/**
|
|
84
|
+
* @test REQ-721
|
|
85
|
+
* @intent 验证 apply(ctx) 在宿主未提供 credentials 服务时仍能启动。Cordis 的
|
|
86
|
+
* 上下文是一个代理:对既未在 inject 声明、也未 provide 的服务做裸属性
|
|
87
|
+
* 读取会直接抛 "cannot get property ... without inject"(#721 根因)。
|
|
88
|
+
* credentials 是可选服务,必须经 ctx.get() 读取(未提供时返回 undefined,
|
|
89
|
+
* 走 process.env 回落),而不是 ctx.credentials。
|
|
90
|
+
* @covers AC-721-01
|
|
91
|
+
*/
|
|
92
|
+
it("applies without a credentials service (Cordis throws on undeclared property reads)", () => {
|
|
93
|
+
const { ctx, captured } = makeCtx("ok")
|
|
94
|
+
// 复现 Cordis 的 context proxy 语义:目标上不存在、也未声明的属性读取抛错,
|
|
95
|
+
// 而不是返回 undefined —— 裸的 ctx.credentials 会在这里把整个插件启动炸掉。
|
|
96
|
+
const cordisLike = new Proxy(ctx as object, {
|
|
97
|
+
get(target, prop, receiver) {
|
|
98
|
+
if (prop === "get") return (_name: string) => undefined
|
|
99
|
+
if (Reflect.has(target, prop)) return Reflect.get(target, prop, receiver)
|
|
100
|
+
throw new Error(`cannot get property "${String(prop)}" without inject`)
|
|
101
|
+
},
|
|
102
|
+
})
|
|
103
|
+
expect(() => apply(cordisLike as unknown as Context)).not.toThrow()
|
|
104
|
+
// apply 存活后,工具仍按契约注册。
|
|
105
|
+
expect(captured.map((c) => (c as CapturedTool).name)).toContain("gate-check")
|
|
106
|
+
})
|
|
107
|
+
|
|
83
108
|
/**
|
|
84
109
|
* @test REQ-DSH-006
|
|
85
110
|
* @intent 验证 apply(ctx) 通过 ctx.skills.registerProvider 注册了 bundled skill provider,
|
package/plugins/dsh/src/index.ts
CHANGED
|
@@ -561,10 +561,13 @@ export function apply(ctx: Context, config: unknown = {}): void {
|
|
|
561
561
|
// delphi-review work on a machine whose key lives in the credential store rather
|
|
562
562
|
// than in the host process's inherited environment.
|
|
563
563
|
//
|
|
564
|
-
//
|
|
565
|
-
//
|
|
566
|
-
//
|
|
567
|
-
|
|
564
|
+
// Read via ctx.get() rather than a bare ctx.credentials (#721): Cordis's context
|
|
565
|
+
// proxy throws "cannot get property ... without inject" on any property that is
|
|
566
|
+
// neither a declared service nor in this plugin's inject list. "credentials" is
|
|
567
|
+
// deliberately NOT in inject — adding it would stop the plugin from loading on a
|
|
568
|
+
// host without the service, discarding the process.env fallback below. ctx.get()
|
|
569
|
+
// is the inject-free read and returns undefined when the host provides none.
|
|
570
|
+
const credentials: CredentialProvider | undefined = ctx.get?.("credentials")
|
|
568
571
|
const resolveApiKey = createCredentialResolver(credentials, process.env)
|
|
569
572
|
ctx.tools.register(gateCheckTool(shell, dialect))
|
|
570
573
|
ctx.tools.register(gatePrinciplesTool(shell, dialect))
|
|
@@ -1,9 +1,9 @@
|
|
|
1
1
|
# SKILLS/DELPHI-REVIEW KNOWLEDGE BASE
|
|
2
2
|
|
|
3
|
-
**Generated:** 2026-11-
|
|
4
|
-
**Commit:**
|
|
5
|
-
**Branch:**
|
|
6
|
-
**Version:** 0.
|
|
3
|
+
**Generated:** 2026-11-04
|
|
4
|
+
**Commit:** eb2097b0
|
|
5
|
+
**Branch:** sprint/2026-11-03-02
|
|
6
|
+
**Version:** 0.36.0.0
|
|
7
7
|
|
|
8
8
|
## OVERVIEW
|
|
9
9
|
Delphi Consensus Review — multi-round anonymous expert review (≥90% threshold, exactly 3 experts with distinct executable model IDs). Supports design, requirements, and code-walkthrough modes.
|
|
@@ -1,9 +1,9 @@
|
|
|
1
1
|
# SKILLS/SPRINT-FLOW KNOWLEDGE BASE
|
|
2
2
|
|
|
3
|
-
**Generated:** 2026-11-
|
|
4
|
-
**Commit:**
|
|
5
|
-
**Branch:**
|
|
6
|
-
**Version:** 0.
|
|
3
|
+
**Generated:** 2026-11-04
|
|
4
|
+
**Commit:** eb2097b0
|
|
5
|
+
**Branch:** sprint/2026-11-03-02
|
|
6
|
+
**Version:** 0.36.0.0
|
|
7
7
|
|
|
8
8
|
## OVERVIEW
|
|
9
9
|
**6-phase** development pipeline (v2.0 compact redesign, Issue #290): PREP → DESIGN → BUILD → VERIFY → SHIP → CLOSE. Phase 3/6 BUILD default build mode is **ralph-loop** (REQ-level iteration, 40-67% token savings vs parallel). HARD-GATE between DESIGN (2/6) and BUILD (3/6): design must pass Delphi review (≥90% consensus) before any coding.
|
|
@@ -1,9 +1,9 @@
|
|
|
1
1
|
# SKILLS/TEST-SPECIFICATION-ALIGNMENT KNOWLEDGE BASE
|
|
2
2
|
|
|
3
|
-
**Generated:** 2026-11-
|
|
4
|
-
**Commit:**
|
|
5
|
-
**Branch:**
|
|
6
|
-
**Version:** 0.
|
|
3
|
+
**Generated:** 2026-11-04
|
|
4
|
+
**Commit:** eb2097b0
|
|
5
|
+
**Branch:** sprint/2026-11-03-02
|
|
6
|
+
**Version:** 0.36.0.0
|
|
7
7
|
|
|
8
8
|
## OVERVIEW
|
|
9
9
|
Test-Specification Alignment Engine — two-stage validation ensuring tests accurately reflect requirements and design specs.
|
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
{
|
|
2
2
|
"name": "xp-gate",
|
|
3
|
-
"version": "0.
|
|
3
|
+
"version": "0.36.0",
|
|
4
4
|
"displayName": "XP-Gate",
|
|
5
5
|
"description": "Extreme Programming quality gates + AI workflow skills for Qoder. Includes 12 pre-commit gates (Gate 0-11), 8 pre-push gates, Sprint Flow (6 phases), and Delphi multi-expert review (>=90% consensus).",
|
|
6
6
|
"author": {
|
|
@@ -1,9 +1,9 @@
|
|
|
1
1
|
# SKILLS/DELPHI-REVIEW KNOWLEDGE BASE
|
|
2
2
|
|
|
3
|
-
**Generated:** 2026-11-
|
|
4
|
-
**Commit:**
|
|
5
|
-
**Branch:**
|
|
6
|
-
**Version:** 0.
|
|
3
|
+
**Generated:** 2026-11-04
|
|
4
|
+
**Commit:** eb2097b0
|
|
5
|
+
**Branch:** sprint/2026-11-03-02
|
|
6
|
+
**Version:** 0.36.0.0
|
|
7
7
|
|
|
8
8
|
## OVERVIEW
|
|
9
9
|
Delphi Consensus Review — multi-round anonymous expert review (≥90% threshold, exactly 3 experts with distinct executable model IDs). Supports design, requirements, and code-walkthrough modes.
|
|
@@ -1,9 +1,9 @@
|
|
|
1
1
|
# SKILLS/SPRINT-FLOW KNOWLEDGE BASE
|
|
2
2
|
|
|
3
|
-
**Generated:** 2026-11-
|
|
4
|
-
**Commit:**
|
|
5
|
-
**Branch:**
|
|
6
|
-
**Version:** 0.
|
|
3
|
+
**Generated:** 2026-11-04
|
|
4
|
+
**Commit:** eb2097b0
|
|
5
|
+
**Branch:** sprint/2026-11-03-02
|
|
6
|
+
**Version:** 0.36.0.0
|
|
7
7
|
|
|
8
8
|
## OVERVIEW
|
|
9
9
|
**6-phase** development pipeline (v2.0 compact redesign, Issue #290): PREP → DESIGN → BUILD → VERIFY → SHIP → CLOSE. Phase 3/6 BUILD default build mode is **ralph-loop** (REQ-level iteration, 40-67% token savings vs parallel). HARD-GATE between DESIGN (2/6) and BUILD (3/6): design must pass Delphi review (≥90% consensus) before any coding.
|
|
@@ -1,9 +1,9 @@
|
|
|
1
1
|
# SKILLS/TEST-SPECIFICATION-ALIGNMENT KNOWLEDGE BASE
|
|
2
2
|
|
|
3
|
-
**Generated:** 2026-11-
|
|
4
|
-
**Commit:**
|
|
5
|
-
**Branch:**
|
|
6
|
-
**Version:** 0.
|
|
3
|
+
**Generated:** 2026-11-04
|
|
4
|
+
**Commit:** eb2097b0
|
|
5
|
+
**Branch:** sprint/2026-11-03-02
|
|
6
|
+
**Version:** 0.36.0.0
|
|
7
7
|
|
|
8
8
|
## OVERVIEW
|
|
9
9
|
Test-Specification Alignment Engine — two-stage validation ensuring tests accurately reflect requirements and design specs.
|
package/principles/AGENTS.md
CHANGED
|
@@ -1,9 +1,9 @@
|
|
|
1
1
|
# PRINCIPLES CHECKER MODULE
|
|
2
2
|
|
|
3
|
-
**Generated:** 2026-11-
|
|
4
|
-
**Commit:**
|
|
5
|
-
**Branch:**
|
|
6
|
-
**Version:** 0.
|
|
3
|
+
**Generated:** 2026-11-04
|
|
4
|
+
**Commit:** eb2097b0
|
|
5
|
+
**Branch:** sprint/2026-11-03-02
|
|
6
|
+
**Version:** 0.36.0.0
|
|
7
7
|
|
|
8
8
|
## OVERVIEW
|
|
9
9
|
Clean Code & SOLID principles checker — **Gate 4** of pre-commit. 14 rules × 9 language adapters, SARIF 2.1.0 output. Houses the **Boy Scout Rule** enforcement engine (Gate 6) and warning-baseline storage.
|