mindforge-cc 2.0.0-alpha.6 → 2.0.0-alpha.8

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.
Files changed (17) hide show
  1. package/.agent/CLAUDE.md +9 -9
  2. package/.agent/mindforge/init-project.md +3 -4
  3. package/.claude/CLAUDE.md +9 -9
  4. package/CHANGELOG.md +7 -4
  5. package/README.md +2 -2
  6. package/RELEASENOTES.md +1 -1
  7. package/bin/installer-core.js +13 -4
  8. package/docs/Context/Master-Context.md +11 -11
  9. package/docs/architecture/decision-records-index.md +20 -20
  10. package/docs/enterprise-setup.md +1 -1
  11. package/docs/reference/commands.md +42 -42
  12. package/docs/reference/config-reference.md +2 -2
  13. package/docs/reference/sdk-api.md +1 -1
  14. package/docs/testing-current-version.md +3 -3
  15. package/docs/user-guide.md +1 -1
  16. package/docs/usp-features.md +1 -1
  17. package/package.json +1 -1
package/.agent/CLAUDE.md CHANGED
@@ -3,7 +3,7 @@
3
3
 
4
4
  ---
5
5
 
6
- ## MULTI-MODEL INTELLIGENCE LAYER (v2.0.0 — Day 10)
6
+ ## MULTI-MODEL INTELLIGENCE LAYER (v2.0.0)
7
7
 
8
8
  ### Model Routing
9
9
 
@@ -26,7 +26,7 @@
26
26
 
27
27
  ---
28
28
 
29
- ## DISTRIBUTION & CI LAYER (Day 6)
29
+ ## DISTRIBUTION & CI LAYER
30
30
 
31
31
  ### CI mode awareness
32
32
  If `CI=true` or `MINDFORGE_CI=true` environment variables are set:
@@ -63,7 +63,7 @@ Run `node bin/validate-config.js` silently.
63
63
  If errors: warn the user before proceeding.
64
64
  If warnings about non-overridable settings: ignore the override silently (per ADR-013).
65
65
 
66
- ### New commands available (Day 6)
66
+ ### New commands available
67
67
  - `/mindforge:init-org` — organisation-wide setup
68
68
  - `/mindforge:install-skill` — install skill from registry
69
69
  - `/mindforge:publish-skill` — publish skill to registry
@@ -107,7 +107,7 @@ All plugin.json, HANDOFF.json, AUDIT.jsonl schemas are stable.
107
107
  Breaking changes to these require MAJOR version bump.
108
108
  Non-breaking additions (new optional fields, new commands) require MINOR.
109
109
 
110
- ### New commands (Day 7)
110
+ ### New commands
111
111
  - /mindforge:update — check for and apply framework updates
112
112
  - /mindforge:migrate — run schema migrations between versions
113
113
  - /mindforge:plugins — manage plugins (install, uninstall, validate)
@@ -140,7 +140,7 @@ If `--headless` is used:
140
140
  - Structure all stdout as line-delimited JSON.
141
141
  - Handle SIGTERM by pausing execution and snapshotting HANDOFF.json.
142
142
 
143
- ### New commands (Day 8)
143
+ ### New commands
144
144
  - /mindforge:auto — start/resume autonomous execution engine
145
145
  - /mindforge:steer — inject mid-execution guidance
146
146
  - /mindforge:browse — persistent browser control and actions
@@ -148,7 +148,7 @@ If `--headless` is used:
148
148
 
149
149
  ---
150
150
 
151
- ## REAL-TIME DASHBOARD (v2.0.0 — Day 12)
151
+ ## REAL-TIME DASHBOARD (v2.0.0)
152
152
 
153
153
  ### Dashboard server
154
154
  The MindForge dashboard runs at localhost:7339 when started.
@@ -171,7 +171,7 @@ Suggest starting the dashboard when:
171
171
  - approval_granted / approval_rejected: when approved via browser UI
172
172
  - steering_queued: when steering instruction sent via browser UI
173
173
 
174
- ### New command (Day 12)
174
+ ### New command
175
175
  - /mindforge:dashboard — start/stop/status the real-time web dashboard
176
176
 
177
177
  ---
@@ -455,7 +455,7 @@ This is the same logic `/mindforge:next` uses — it can be applied any time.
455
455
 
456
456
  ---
457
457
 
458
- ## SKILLS PLATFORM (Day 3)
458
+ ## SKILLS PLATFORM
459
459
 
460
460
  ### Skills loading is now multi-tier
461
461
  The skills engine has three tiers: Core (Tier 1) → Org (Tier 2) → Project (Tier 3).
@@ -500,7 +500,7 @@ When a user invokes `/mindforge:*`, route to the corresponding command file
500
500
  and execute its full protocol precisely.
501
501
 
502
502
  ---
503
- ## INTELLIGENCE LAYER (Day 5)
503
+ ## INTELLIGENCE LAYER
504
504
 
505
505
  ### MINDFORGE.md loading and override behavior
506
506
  After ORG + PROJECT + STATE + HANDOFF loading, read `MINDFORGE.md` if present.
package/.agent/mindforge/init-project.md CHANGED
@@ -10,11 +10,10 @@ Verify that `CLAUDE.md` exists at the root of the project and `.claude/commands/
10
10
  ```bash
11
11
  mkdir -p .claude/commands/mindforge
12
12
  cp -r .agent/mindforge/* .claude/commands/mindforge/ 2>/dev/null || true
13
- cp -r agents/mindforge/* .claude/commands/mindforge/ 2>/dev/null || true
13
+ cp -r .agents/workflows/* .claude/commands/mindforge/ 2>/dev/null || true
14
14
  cp .agent/CLAUDE.md ./CLAUDE.md 2>/dev/null || true
15
- cp agents/CLAUDE.md ./CLAUDE.md 2>/dev/null || true
16
- cp ./CLAUDE.md ./.cursorrules 2>/dev/null || true
17
- cp ./CLAUDE.md ./.windsurfrules 2>/dev/null || true
15
+ cp .agent/CLAUDE.md ./.cursorrules 2>/dev/null || true
16
+ cp .agent/CLAUDE.md ./.windsurfrules 2>/dev/null || true
18
17
  ```
19
18
 
20
19
  ## Step 1 — Requirements interview
package/.claude/CLAUDE.md CHANGED
@@ -3,7 +3,7 @@
3
3
 
4
4
  ---
5
5
 
6
- ## MULTI-MODEL INTELLIGENCE LAYER (v2.0.0 — Day 10)
6
+ ## MULTI-MODEL INTELLIGENCE LAYER (v2.0.0)
7
7
 
8
8
  ### Model Routing
9
9
 
@@ -26,7 +26,7 @@
26
26
 
27
27
  ---
28
28
 
29
- ## DISTRIBUTION & CI LAYER (Day 6)
29
+ ## DISTRIBUTION & CI LAYER
30
30
 
31
31
  ### CI mode awareness
32
32
  If `CI=true` or `MINDFORGE_CI=true` environment variables are set:
@@ -63,7 +63,7 @@ Run `node bin/validate-config.js` silently.
63
63
  If errors: warn the user before proceeding.
64
64
  If warnings about non-overridable settings: ignore the override silently (per ADR-013).
65
65
 
66
- ### New commands available (Day 6)
66
+ ### New commands available
67
67
  - `/mindforge:init-org` — organisation-wide setup
68
68
  - `/mindforge:install-skill` — install skill from registry
69
69
  - `/mindforge:publish-skill` — publish skill to registry
@@ -107,7 +107,7 @@ All plugin.json, HANDOFF.json, AUDIT.jsonl schemas are stable.
107
107
  Breaking changes to these require MAJOR version bump.
108
108
  Non-breaking additions (new optional fields, new commands) require MINOR.
109
109
 
110
- ### New commands (Day 7)
110
+ ### New commands
111
111
  - /mindforge:update — check for and apply framework updates
112
112
  - /mindforge:migrate — run schema migrations between versions
113
113
  - /mindforge:plugins — manage plugins (install, uninstall, validate)
@@ -140,7 +140,7 @@ If `--headless` is used:
140
140
  - Structure all stdout as line-delimited JSON.
141
141
  - Handle SIGTERM by pausing execution and snapshotting HANDOFF.json.
142
142
 
143
- ### New commands (Day 8)
143
+ ### New commands
144
144
  - /mindforge:auto — start/resume autonomous execution engine
145
145
  - /mindforge:steer — inject mid-execution guidance
146
146
  - /mindforge:browse — persistent browser control and actions
@@ -148,7 +148,7 @@ If `--headless` is used:
148
148
 
149
149
  ---
150
150
 
151
- ## REAL-TIME DASHBOARD (v2.0.0 — Day 12)
151
+ ## REAL-TIME DASHBOARD (v2.0.0)
152
152
 
153
153
  ### Dashboard server
154
154
  The MindForge dashboard runs at localhost:7339 when started.
@@ -171,7 +171,7 @@ Suggest starting the dashboard when:
171
171
  - approval_granted / approval_rejected: when approved via browser UI
172
172
  - steering_queued: when steering instruction sent via browser UI
173
173
 
174
- ### New command (Day 12)
174
+ ### New command
175
175
  - /mindforge:dashboard — start/stop/status the real-time web dashboard
176
176
 
177
177
  ---
@@ -455,7 +455,7 @@ This is the same logic `/mindforge:next` uses — it can be applied any time.
455
455
 
456
456
  ---
457
457
 
458
- ## SKILLS PLATFORM (Day 3)
458
+ ## SKILLS PLATFORM
459
459
 
460
460
  ### Skills loading is now multi-tier
461
461
  The skills engine has three tiers: Core (Tier 1) → Org (Tier 2) → Project (Tier 3).
@@ -500,7 +500,7 @@ When a user invokes `/mindforge:*`, route to the corresponding command file
500
500
  and execute its full protocol precisely.
501
501
 
502
502
  ---
503
- ## INTELLIGENCE LAYER (Day 5)
503
+ ## INTELLIGENCE LAYER
504
504
 
505
505
  ### MINDFORGE.md loading and override behavior
506
506
  After ORG + PROJECT + STATE + HANDOFF loading, read `MINDFORGE.md` if present.
package/CHANGELOG.md CHANGED
@@ -1,11 +1,14 @@
1
1
  # Changelog
2
+ ...
3
+ ## [2.0.0-alpha.8] — Antigravity Visibility Fix — 2026-03-23
2
4
 
3
- All notable changes to MindForge are documented here.
4
- Format follows [Keep a Changelog](https://keepachangelog.com).
5
+ ### Fixed
6
+ - **Antigravity Command Visibility**: Relocated workflows to `.agents/workflows/` (from `agents/`) and injected mandatory YAML frontmatter (`description`) to ensure registration in Antigravity.
7
+ - **Zero-Config Sync**: Updated `init-project` command to reflect the new `.agents` directory standard.
5
8
 
6
- ## [2.0.0-alpha.6] — Day 12: Real-time Observability Dashboard — 2026-03-22
9
+ ## [2.0.0-alpha.7] — Day 12: Real-time Observability Dashboard — 2026-03-22
7
10
 
8
- - [v2.0.0-alpha.6 (2026-03-22)]
11
+ - [v2.0.0-alpha.7 (2026-03-22)]
9
12
  - [NEW] Real-time Dashboard Server (Express + SSE Bridge).
10
13
  - [NEW] Premium 5-tab UI: Activity, Metrics, Approvals, Memory, Team.
11
14
  - [NEW] Live Data Streaming for Audit Logs, Quality, Costs, and Team Activity.
package/README.md CHANGED
@@ -1,4 +1,4 @@
1
- # MindForge — Enterprise Agentic Framework (v2.0.0-alpha.6)
1
+ # MindForge — Enterprise Agentic Framework (v2.0.0-alpha.8)
2
2
 
3
3
  MindForge turns Claude Code and Antigravity into production-grade engineering
4
4
  partners with governance, observability, and a disciplined workflow engine.
@@ -215,7 +215,7 @@ See `.mindforge/production/token-optimiser.md`.
215
215
 
216
216
  ---
217
217
 
218
- ## What ships in v2.0.0-alpha.6
218
+ ## What ships in v2.0.0-alpha.8
219
219
  - **Real-time Dashboard**: `/mindforge:dashboard` and web-based observability.
220
220
  - **Persistent Knowledge Graph**: `/mindforge:remember` and long-term memory engine.
221
221
  - **Multi-Model Intelligence Layer**: `/mindforge:cross-review`, `/mindforge:research`, and `/mindforge:costs`.
package/RELEASENOTES.md CHANGED
@@ -21,7 +21,7 @@ Quality gates, security posture, and release readiness are documented for enterp
21
21
  - Example starter project with MindForge structure ready for onboarding teams.
22
22
 
23
23
  ## Quality & Stability
24
- - Day 7 production, migration, and e2e test suites added.
24
+ - production, migration, and e2e test suites added.
25
25
  - Full 12-suite regression loop validated across prior-day coverage.
26
26
  - Triple-run stability verification completed with all tests passing.
27
27
  - Threat model and penetration test results documented.
package/bin/installer-core.js CHANGED
@@ -20,7 +20,7 @@ const RUNTIMES = {
20
20
  },
21
21
  antigravity: {
22
22
  globalDir: path.join(os.homedir(), '.gemini', 'antigravity'),
23
- localDir: 'agents',
23
+ localDir: '.agents',
24
24
  commandsSubdir: 'workflows',
25
25
  entryFile: 'CLAUDE.md',
26
26
  },
@@ -227,12 +227,21 @@ async function install(runtime, scope, options = {}) {
227
227
 
228
228
  if (fsu.exists(cmdSrc)) {
229
229
  fsu.ensureDir(cmdsDir);
230
- const files = fsu.listFiles(cmdSrc).filter(f => f.endsWith('.md'));
231
-
232
230
  // Install for specific runtime
233
231
  files.forEach(f => {
234
232
  const targetName = runtime === 'antigravity' ? `mindforge:${f}` : f;
235
- fsu.copy(path.join(cmdSrc, f), path.join(cmdsDir, targetName));
233
+ const srcPath = path.join(cmdSrc, f);
234
+ const dstPath = path.join(cmdsDir, targetName);
235
+
236
+ if (runtime === 'antigravity') {
237
+ const content = fsu.read(srcPath);
238
+ const firstLine = content.split('\n')[0].trim();
239
+ // Mandatory Antigravity frontmatter metadata
240
+ const metadata = `---\ndescription: ${firstLine}\n---\n`;
241
+ fsu.write(dstPath, metadata + content);
242
+ } else {
243
+ fsu.copy(srcPath, dstPath);
244
+ }
236
245
  });
237
246
 
238
247
  // ✨ STANDARD: Mirror to .claude/commands for cross-IDE compatibility (Cursor/Windsurf/Claude Code)
package/docs/Context/Master-Context.md CHANGED
@@ -1,5 +1,5 @@
1
1
  # MindForge — Continuation State File
2
- # Generated: Day 7 Complete
2
+ # Generated: Complete
3
3
  # Purpose: Provide full context for resuming in a new chat session
4
4
 
5
5
  ---
@@ -10,7 +10,7 @@
10
10
  **Tagline:** Enterprise Agentic Framework — the best agentic framework
11
11
  **Repository:** `github.com/mindforge-dev/mindforge` (conceptual)
12
12
  **npm package:** `npx mindforge-cc@latest`
13
- **Current version:** v1.0.0 (first stable public release, tagged at Day 7 completion)
13
+ **Current version:** v1.0.0 (first stable public release, tagged at completion)
14
14
  **Runtimes supported:** Claude Code (`.claude/`) and Antigravity (`.agent/`)
15
15
  **License:** MIT
16
16
 
@@ -26,7 +26,7 @@ anti-pattern detector, quality metrics, team profiling).
26
26
 
27
27
  ## WHAT WAS BUILT — DAY BY DAY
28
28
 
29
- ### Day 1 — Foundation (`feat/mindforge-core-scaffold` → v0.1.0)
29
+ ### — Foundation (`feat/mindforge-core-scaffold` → v0.1.0)
30
30
 
31
31
  **Branch:** `feat/mindforge-core-scaffold`
32
32
  **Output files:** `DAY1-IMPLEMENT.md`, `DAY1-REVIEW.md`, `DAY1-HARDEN.md`
@@ -66,7 +66,7 @@ Built the entire structural foundation:
66
66
 
67
67
  ---
68
68
 
69
- ### Day 2 — Wave Execution Engine (`feat/mindforge-wave-engine` → v0.2.0)
69
+ ### — Wave Execution Engine (`feat/mindforge-wave-engine` → v0.2.0)
70
70
 
71
71
  **Branch:** `feat/mindforge-wave-engine`
72
72
  **Output files:** `DAY2-IMPLEMENT.md`, `DAY2-REVIEW.md`, `DAY2-HARDEN.md`
@@ -92,7 +92,7 @@ Built the execution engine that makes plans actually run:
92
92
 
93
93
  ---
94
94
 
95
- ### Day 3 — Skills Platform (`feat/mindforge-skills-platform` → v0.3.0)
95
+ ### — Skills Platform (`feat/mindforge-skills-platform` → v0.3.0)
96
96
 
97
97
  **Branch:** `feat/mindforge-skills-platform`
98
98
  **Output files:** `DAY3-IMPLEMENT.md`, `DAY3-REVIEW.md`, `DAY3-HARDEN.md`
@@ -130,7 +130,7 @@ Built the skills distribution and intelligence engine:
130
130
 
131
131
  ---
132
132
 
133
- ### Day 4 — Enterprise Integrations + Governance (`feat/mindforge-enterprise-integrations` → v0.4.0)
133
+ ### — Enterprise Integrations + Governance (`feat/mindforge-enterprise-integrations` → v0.4.0)
134
134
 
135
135
  **Branch:** `feat/mindforge-enterprise-integrations`
136
136
  **Output files:** `DAY4-IMPLEMENT.md`, `DAY4-REVIEW.md`, `DAY4-HARDEN.md`
@@ -167,7 +167,7 @@ Built the enterprise integration and governance layer:
167
167
 
168
168
  ---
169
169
 
170
- ### Day 5 — Intelligence Layer (`feat/mindforge-intelligence-layer` → v0.5.0)
170
+ ### — Intelligence Layer (`feat/mindforge-intelligence-layer` → v0.5.0)
171
171
 
172
172
  **Branch:** `feat/mindforge-intelligence-layer`
173
173
  **Output files:** `DAY5-IMPLEMENT.md`, `DAY5-REVIEW.md`, `DAY5-HARDEN.md`
@@ -205,7 +205,7 @@ Built the framework's self-awareness and self-improvement systems:
205
205
 
206
206
  ---
207
207
 
208
- ### Day 6 — Distribution Platform (`feat/mindforge-distribution-platform` → v0.6.0)
208
+ ### — Distribution Platform (`feat/mindforge-distribution-platform` → v0.6.0)
209
209
 
210
210
  **Branch:** `feat/mindforge-distribution-platform`
211
211
  **Output files:** `DAY6-COMPLETE.md` (all three prompts in one file)
@@ -250,7 +250,7 @@ Built the public distribution, CI/CD, SDK, and monorepo layers:
250
250
 
251
251
  ---
252
252
 
253
- ### Day 7 — Production Hardening & v1.0.0 Release (`feat/mindforge-production-release` → v1.0.0)
253
+ ### — Production Hardening & v1.0.0 Release (`feat/mindforge-production-release` → v1.0.0)
254
254
 
255
255
  **Branch:** `feat/mindforge-production-release`
256
256
  **Output files:** `DAY7-PRODUCTION-FINAL.md` (all three prompts in one file, 174KB)
@@ -621,7 +621,7 @@ Test all installer code paths on Windows. Fix path separator issues where found.
621
621
  - Community Discord/Slack setup
622
622
  - `mindforge.dev` landing page content
623
623
 
624
- ### Day 8 branch and version
624
+ ### branch and version
625
625
 
626
626
  **Branch:** `feat/mindforge-multi-runtime-dashboard`
627
627
  **Target version:** v1.1.0 (stable minor — no breaking changes)
@@ -698,4 +698,4 @@ All prompt files are in `/mnt/user-data/outputs/`:
698
698
 
699
699
  ---
700
700
 
701
- *State file generated at Day 7 completion. MindForge v1.0.0 — 36 commands · 10 skills · 8 personas · 20 ADRs · 15 test suites.*
701
+ *State file generated at completion. MindForge v1.0.0 — 36 commands · 10 skills · 8 personas · 20 ADRs · 15 test suites.*
package/docs/architecture/decision-records-index.md CHANGED
@@ -4,23 +4,23 @@ All 20 ADRs in chronological order.
4
4
 
5
5
  | ADR | Title | Status | Day | Key decision |
6
6
  |---|---|---|---|---|
7
- | ADR-001 | HANDOFF.json for cross-session state | Accepted | Day 2 | HANDOFF.json as the primary cross-session state artifact |
8
- | ADR-002 | Markdown-based commands | Accepted | Day 1 | Slash commands as Markdown files (not code) |
9
- | ADR-003 | Keyword-trigger model for skill loading | Accepted | Day 1 | Deterministic keyword matching over AI-decided selection |
10
- | ADR-004 | Wave parallelism over full parallelism | Accepted | Day 2 | Wave-based (dependency-ordered) over unconstrained parallel |
11
- | ADR-005 | Append-only JSONL for audit log | Accepted | Day 2 | AUDIT.jsonl append-only (never update, never delete) |
12
- | ADR-006 | Three-tier skills architecture | Accepted | Day 3 | Core → Org → Project tier hierarchy |
13
- | ADR-007 | Keyword-trigger model (reaffirmed at Day 3 scale) | Accepted | Day 3 | Confirmed at 10+ skill scale |
14
- | ADR-008 | Just-in-time skill loading | Accepted | Day 3 | Load at task time, not session start |
15
- | ADR-009 | Environment-variable-only credential storage | Accepted | Day 4 | Credentials only in env vars, never in config files |
16
- | ADR-010 | Compliance gates non-bypassable; approvals allow emergency | Accepted | Day 4 | Gates: never bypass. Approvals: emergency override with audit |
17
- | ADR-011 | Integration failures are non-blocking | Accepted | Day 4 | Jira/Slack/GitHub down ≠ phase blocked |
18
- | ADR-012 | Intelligence outputs feed back into system behaviour | Accepted | Day 5 | Difficulty → granularity, retro → MINDFORGE.md, quality → behaviour |
19
- | ADR-013 | MINDFORGE.md as constitution with non-overridable primitives | Accepted | Day 5 | Non-overridable governance primitives cannot be disabled |
20
- | ADR-014 | Metrics are system signals, not developer performance | Accepted | Day 5 | Quality scores improve the system, not evaluate individuals |
21
- | ADR-015 | npm as the public skills registry | Accepted | Day 6 | npm ecosystem for skill distribution |
22
- | ADR-016 | CI timeout exits with code 0 (soft stop) | Accepted | Day 6 | Timeout = save and resume, not failure |
23
- | ADR-017 | SDK event stream is localhost-only | Accepted | Day 6 | SSE binds to 127.0.0.1 only |
24
- | ADR-018 | Installer detects and handles self-install | Accepted | Day 7 | Installer running inside its own repo = no-op for framework files |
25
- | ADR-019 | Self-update preserves original install scope | Accepted | Day 7 | Update local→local, global→global |
26
- | ADR-020 | v1.0.0 stable interface contract | Accepted | Day 7 | Defines what "stable" means for plugins and SDK consumers |
7
+ | ADR-001 | HANDOFF.json for cross-session state | Accepted | HANDOFF.json as the primary cross-session state artifact |
8
+ | ADR-002 | Markdown-based commands | Accepted | Slash commands as Markdown files (not code) |
9
+ | ADR-003 | Keyword-trigger model for skill loading | Accepted | Deterministic keyword matching over AI-decided selection |
10
+ | ADR-004 | Wave parallelism over full parallelism | Accepted | Wave-based (dependency-ordered) over unconstrained parallel |
11
+ | ADR-005 | Append-only JSONL for audit log | Accepted | AUDIT.jsonl append-only (never update, never delete) |
12
+ | ADR-006 | Three-tier skills architecture | Accepted | Core → Org → Project tier hierarchy |
13
+ | ADR-007 | Keyword-trigger model (reaffirmed at scale) | Accepted | Confirmed at 10+ skill scale |
14
+ | ADR-008 | Just-in-time skill loading | Accepted | Load at task time, not session start |
15
+ | ADR-009 | Environment-variable-only credential storage | Accepted | Credentials only in env vars, never in config files |
16
+ | ADR-010 | Compliance gates non-bypassable; approvals allow emergency | Accepted | Gates: never bypass. Approvals: emergency override with audit |
17
+ | ADR-011 | Integration failures are non-blocking | Accepted | Jira/Slack/GitHub down ≠ phase blocked |
18
+ | ADR-012 | Intelligence outputs feed back into system behaviour | Accepted | Difficulty → granularity, retro → MINDFORGE.md, quality → behaviour |
19
+ | ADR-013 | MINDFORGE.md as constitution with non-overridable primitives | Accepted | Non-overridable governance primitives cannot be disabled |
20
+ | ADR-014 | Metrics are system signals, not developer performance | Accepted | Quality scores improve the system, not evaluate individuals |
21
+ | ADR-015 | npm as the public skills registry | Accepted | npm ecosystem for skill distribution |
22
+ | ADR-016 | CI timeout exits with code 0 (soft stop) | Accepted | Timeout = save and resume, not failure |
23
+ | ADR-017 | SDK event stream is localhost-only | Accepted | SSE binds to 127.0.0.1 only |
24
+ | ADR-018 | Installer detects and handles self-install | Accepted | Installer running inside its own repo = no-op for framework files |
25
+ | ADR-019 | Self-update preserves original install scope | Accepted | Update local→local, global→global |
26
+ | ADR-020 | v1.0.0 stable interface contract | Accepted | Defines what "stable" means for plugins and SDK consumers |
package/docs/enterprise-setup.md CHANGED
@@ -18,7 +18,7 @@ Configure Jira, Confluence, Slack, and SCM governance safely without storing
18
18
  - never use `curl -v` with Authorization headers
19
19
  - rotate credentials by updating the environment, not config files
20
20
 
21
- ## Supported Day 4 outputs
21
+ ## Supported outputs
22
22
  - Jira epics and stories for phases/plans
23
23
  - Confluence architecture and ADR publishing
24
24
  - Slack notifications and thread tracking
package/docs/reference/commands.md CHANGED
@@ -6,84 +6,84 @@
6
6
 
7
7
  | Command | Usage | Description | Added |
8
8
  |---|---|---|---|
9
- | `/mindforge:init-project` | `init-project` | Guided project setup — creates all `.planning/` files | Day 1 |
10
- | `/mindforge:discuss-phase` | `discuss-phase [N] [--batch|--auto]` | Pre-planning interview to capture implementation decisions | Day 3 |
11
- | `/mindforge:plan-phase` | `plan-phase [N]` | Research, decompose, and create atomic task plans | Day 1 |
9
+ | `/mindforge:init-project` | `init-project` | Guided project setup — creates all `.planning/` files |
10
+ | `/mindforge:discuss-phase` | `discuss-phase [N] [--batch|--auto]` | Pre-planning interview to capture implementation decisions |
11
+ | `/mindforge:plan-phase` | `plan-phase [N]` | Research, decompose, and create atomic task plans |
12
12
  | `/mindforge:execute-phase` | `execute-phase [N]` | Wave-based parallel execution of all phase plans | Day 1+2 |
13
- | `/mindforge:verify-phase` | `verify-phase [N]` | Automated + human acceptance testing pipeline | Day 1 |
14
- | `/mindforge:ship` | `ship [N]` | Create PR, write release notes, push to remote | Day 1 |
15
- | `/mindforge:auto` | `auto [--phase N] [--milestone M]` | Walk-away autonomous execution with stuck detection | Day 8 |
16
- | `/mindforge:steer` | `steer "instruction"` | Inject guidance into a running autonomous session | Day 8 |
17
- | `/mindforge:next` | `next` | Auto-detect and execute the correct next workflow step | Day 2 |
18
- | `/mindforge:cross-review` | `cross-review` | Adversarial multi-model code review and synthesis | Day 10 |
19
- | `/mindforge:research` | `research "query"` | Deep research using Gemini 1.5 Pro 1M context | Day 10 |
20
- | `/mindforge:remember` | `remember [--add X|--search Y|--promote ID|--stats]` | Persistent knowledge graph management | Day 11 |
13
+ | `/mindforge:verify-phase` | `verify-phase [N]` | Automated + human acceptance testing pipeline |
14
+ | `/mindforge:ship` | `ship [N]` | Create PR, write release notes, push to remote |
15
+ | `/mindforge:auto` | `auto [--phase N] [--milestone M]` | Walk-away autonomous execution with stuck detection |
16
+ | `/mindforge:steer` | `steer "instruction"` | Inject guidance into a running autonomous session |
17
+ | `/mindforge:next` | `next` | Auto-detect and execute the correct next workflow step |
18
+ | `/mindforge:cross-review` | `cross-review` | Adversarial multi-model code review and synthesis |
19
+ | `/mindforge:research` | `research "query"` | Deep research using Gemini 1.5 Pro 1M context |
20
+ | `/mindforge:remember` | `remember [--add X|--search Y|--promote ID|--stats]` | Persistent knowledge graph management |
21
21
 
22
22
  ### Project setup & discovery
23
23
 
24
24
  | Command | Usage | Description | Added |
25
25
  |---|---|---|---|
26
- | `/mindforge:map-codebase` | `map-codebase` | Brownfield onboarding: infer stack and seed docs | Day 6 |
27
- | `/mindforge:quick` | `quick` | Run a small, single-task plan without a full phase | Day 2 |
28
- | `/mindforge:status` | `status` | Show current phase, plan status, and next action | Day 2 |
29
- | `/mindforge:health` | `health [--repair]` | Validate installation and repair drift | Day 2 |
30
- | `/mindforge:review` | `review [N]` | Run a structured review pass for a phase | Day 5 |
31
- | `/mindforge:debug` | `debug [plan-id]` | Debug a failed plan with root-cause workflow | Day 5 |
26
+ | `/mindforge:map-codebase` | `map-codebase` | Brownfield onboarding: infer stack and seed docs |
27
+ | `/mindforge:quick` | `quick` | Run a small, single-task plan without a full phase |
28
+ | `/mindforge:status` | `status` | Show current phase, plan status, and next action |
29
+ | `/mindforge:health` | `health [--repair]` | Validate installation and repair drift |
30
+ | `/mindforge:review` | `review [N]` | Run a structured review pass for a phase |
31
+ | `/mindforge:debug` | `debug [plan-id]` | Debug a failed plan with root-cause workflow |
32
32
 
33
33
  ### Governance & compliance
34
34
 
35
35
  | Command | Usage | Description | Added |
36
36
  |---|---|---|---|
37
- | `/mindforge:approve` | `approve [--tier 2|3]` | Process approvals and emergency overrides | Day 4 |
38
- | `/mindforge:audit` | `audit [--phase N] [--event X] [--since DATE]` | Query `AUDIT.jsonl` history | Day 2 |
39
- | `/mindforge:security-scan` | `security-scan [--deep] [--secrets] [--deps]` | Security scan with OWASP classification | Day 2 |
40
- | `/mindforge:milestone` | `milestone [name]` | Create or update milestone definitions | Day 4 |
41
- | `/mindforge:complete-milestone` | `complete-milestone [name]` | Archive milestone and generate release report | Day 4 |
42
- | `/mindforge:retrospective` | `retrospective [N]` | Phase retrospective and improvement actions | Day 5 |
37
+ | `/mindforge:approve` | `approve [--tier 2|3]` | Process approvals and emergency overrides |
38
+ | `/mindforge:audit` | `audit [--phase N] [--event X] [--since DATE]` | Query `AUDIT.jsonl` history |
39
+ | `/mindforge:security-scan` | `security-scan [--deep] [--secrets] [--deps]` | Security scan with OWASP classification |
40
+ | `/mindforge:milestone` | `milestone [name]` | Create or update milestone definitions |
41
+ | `/mindforge:complete-milestone` | `complete-milestone [name]` | Archive milestone and generate release report |
42
+ | `/mindforge:retrospective` | `retrospective [N]` | Phase retrospective and improvement actions |
43
43
 
44
44
  ### Skills & plugins
45
45
 
46
46
  | Command | Usage | Description | Added |
47
47
  |---|---|---|---|
48
- | `/mindforge:skills` | `skills [list|validate|refresh]` | Manage core/org/project skills | Day 3 |
49
- | `/mindforge:install-skill` | `install-skill <name> [--version]` | Install skill from registry | Day 6 |
50
- | `/mindforge:publish-skill` | `publish-skill <path>` | Publish a skill to the registry | Day 6 |
51
- | `/mindforge:plugins` | `plugins [list|install|uninstall|validate]` | Manage plugin lifecycle | Day 7 |
48
+ | `/mindforge:skills` | `skills [list|validate|refresh]` | Manage core/org/project skills |
49
+ | `/mindforge:install-skill` | `install-skill <name> [--version]` | Install skill from registry |
50
+ | `/mindforge:publish-skill` | `publish-skill <path>` | Publish a skill to the registry |
51
+ | `/mindforge:plugins` | `plugins [list|install|uninstall|validate]` | Manage plugin lifecycle |
52
52
 
53
53
  ### Intelligence & metrics
54
54
 
55
55
  | Command | Usage | Description | Added |
56
56
  |---|---|---|---|
57
- | `/mindforge:metrics` | `metrics [--phase N]` | Compute quality and throughput metrics | Day 5 |
58
- | `/mindforge:profile-team` | `profile-team` | Generate team skill and ownership profile | Day 5 |
59
- | `/mindforge:benchmark` | `benchmark [--skill X]` | Measure skill effectiveness | Day 6 |
60
- | `/mindforge:tokens` | `tokens [--profile] [--summary]` | Token usage profiling and optimisation | Day 7 |
57
+ | `/mindforge:metrics` | `metrics [--phase N]` | Compute quality and throughput metrics |
58
+ | `/mindforge:profile-team` | `profile-team` | Generate team skill and ownership profile |
59
+ | `/mindforge:benchmark` | `benchmark [--skill X]` | Measure skill effectiveness |
60
+ | `/mindforge:tokens` | `tokens [--profile] [--summary]` | Token usage profiling and optimisation |
61
61
 
62
62
  ### Integrations & distribution
63
63
 
64
64
  | Command | Usage | Description | Added |
65
65
  |---|---|---|---|
66
- | `/mindforge:init-org` | `init-org` | Org-wide MindForge setup | Day 6 |
67
- | `/mindforge:sync-jira` | `sync-jira [--project KEY]` | Sync phases and plans to Jira | Day 4 |
68
- | `/mindforge:sync-confluence` | `sync-confluence [--page ...]` | Publish docs to Confluence | Day 4 |
69
- | `/mindforge:pr-review` | `pr-review [--range A..B]` | AI PR review with context | Day 6 |
70
- | `/mindforge:workspace` | `workspace [detect|plan|test]` | Monorepo workspace management | Day 6 |
71
- | `/mindforge:browse` | `browse [--navigate URL] [--command]` | Control persistent browser daemon and sessions | Day 9 |
72
- | `/mindforge:qa` | `qa [--diff] [--all]` | Run systematic visual QA and regression tests | Day 9 |
66
+ | `/mindforge:init-org` | `init-org` | Org-wide MindForge setup |
67
+ | `/mindforge:sync-jira` | `sync-jira [--project KEY]` | Sync phases and plans to Jira |
68
+ | `/mindforge:sync-confluence` | `sync-confluence [--page ...]` | Publish docs to Confluence |
69
+ | `/mindforge:pr-review` | `pr-review [--range A..B]` | AI PR review with context |
70
+ | `/mindforge:workspace` | `workspace [detect|plan|test]` | Monorepo workspace management |
71
+ | `/mindforge:browse` | `browse [--navigate URL] [--command]` | Control persistent browser daemon and sessions |
72
+ | `/mindforge:qa` | `qa [--diff] [--all]` | Run systematic visual QA and regression tests |
73
73
 
74
74
  ### Release & maintenance
75
75
 
76
76
  | Command | Usage | Description | Added |
77
77
  |---|---|---|---|
78
- | `/mindforge:update` | `update [--apply] [--force] [--check]` | Check for and apply framework updates | Day 7 |
79
- | `/mindforge:migrate` | `migrate [--from vX] [--to vY] [--dry-run]` | Run schema migrations | Day 7 |
80
- | `/mindforge:release` | `release [--tag vX]` | Framework release pipeline (core team) | Day 7 |
78
+ | `/mindforge:update` | `update [--apply] [--force] [--check]` | Check for and apply framework updates |
79
+ | `/mindforge:migrate` | `migrate [--from vX] [--to vY] [--dry-run]` | Run schema migrations |
80
+ | `/mindforge:release` | `release [--tag vX]` | Framework release pipeline (core team) |
81
81
 
82
82
  ### Utility
83
83
 
84
84
  | Command | Usage | Description | Added |
85
85
  |---|---|---|---|
86
- | `/mindforge:help` | `help` | Show all available commands and current project status | Day 1 |
86
+ | `/mindforge:help` | `help` | Show all available commands and current project status |
87
87
 
88
88
  ## Command interface contract (v1.0.0 stable)
89
89
 
package/docs/reference/config-reference.md CHANGED
@@ -44,12 +44,12 @@ Unavailable values fallback to `inherit` with a warning.
44
44
  - `ANTIPATTERN_SENSITIVITY`
45
45
  - `BLOCK_ON_HIGH_ANTIPATTERNS`
46
46
 
47
- ## Token settings (Day 7)
47
+ ## Token settings
48
48
  - `TOKEN_WARN_THRESHOLD`
49
49
  - `TOKEN_LEAN_MODE`
50
50
  - `TOKEN_MAX_FILE_LINES`
51
51
 
52
- ## Update settings (Day 7)
52
+ ## Update settings
53
53
  - `MINDFORGE_AUTO_CHECK_UPDATES` (true/false)
54
54
 
55
55
  ## Non-overridable rules
package/docs/reference/sdk-api.md CHANGED
@@ -11,7 +11,7 @@ From `sdk/src/index.ts`:
11
11
  - `MindForgeClient`
12
12
  - `MindForgeEventStream`
13
13
  - `commands`
14
- - `MindForgeMemory` (Day 11)
14
+ - `MindForgeMemory`
15
15
  - Types: `MindForgeConfig`, `PhaseResult`, `TaskResult`, `SecurityFinding`,
16
16
  `GateResult`, `HealthReport`, `HealthIssue`, `MindForgeEvent`, `CommandOptions`
17
17
  - `VERSION`
package/docs/testing-current-version.md CHANGED
@@ -1,4 +1,4 @@
1
- # MindForge v2.0.0-alpha.6: In-Depth Testing Guide (Antigravity)
1
+ # MindForge v2.0.0-alpha.8: In-Depth Testing Guide (Antigravity)
2
2
 
3
3
  This document provides a step-by-step rigorous testing flow to validate the entire MindForge framework from a blank project state. It is designed to be shared and logged for architectural review.
4
4
 
@@ -9,7 +9,7 @@ This document provides a step-by-step rigorous testing flow to validate the enti
9
9
  ```bash
10
10
  /Users/sairamugge/.vite-plus/js_runtime/node/24.14.0/bin/mindforge-cc --antigravity --local
11
11
  ```
12
- - *Confirmation*: Run the command with `--version`. It must show `v2.0.0-alpha.6`.
12
+ - *Confirmation*: Run the command with `--version`. It must show `v2.0.0-alpha.8`.
13
13
  3. Verify the local binary exists: `ls agents/bin/install.js` (or `.agent/bin/install.js` if legacy)
14
14
 
15
15
  ## 🏗 Phase 1: Registry & Integrity
@@ -126,5 +126,5 @@ All Antigravity sessions are logged. To share your results for review, zip and s
126
126
  - `CHANGELOG.md` (Outcome summary)
127
127
  ## 💡 Troubleshooting
128
128
  - **Command not found**: Ensure you are using `./mindforge:command` or `/mindforge:command` within the agent.
129
- - **Wrong Version**: Run `/mindforge:health` and check for "v2.0.0-alpha.6". If it shows "v1.0.5", your installation failed or you are using the global `npx` version.
129
+ - **Wrong Version**: Run `/mindforge:health` and check for "v2.0.0-alpha.8". If it shows "v1.0.5", your installation failed or you are using the global `npx` version.
130
130
  - **Registry Error**: Check `~/.mindforge/registry.json` exists; it is now automatically created by the v2 installer.
package/docs/user-guide.md CHANGED
@@ -1,4 +1,4 @@
1
- # MindForge User Guide (v2.0.0-alpha.6)
1
+ # MindForge User Guide (v2.0.0-alpha.8)
2
2
 
3
3
  This guide gets you from install to productive, with the minimum needed to run
4
4
  MindForge in a real project. It assumes Node.js 18+.
package/docs/usp-features.md CHANGED
@@ -1,4 +1,4 @@
1
- # MindForge v2.0.0 — Unique Selling Points, Features, and Best Practices (v2.0.0-alpha.6)
1
+ # MindForge v2.0.0 — Unique Selling Points, Features, and Best Practices (v2.0.0-alpha.8)
2
2
 
3
3
  This document summarizes what makes MindForge v2.0.0 distinct, what features
4
4
  are included in the latest alpha release, and how to use them effectively.
package/package.json CHANGED
@@ -1,6 +1,6 @@
1
1
  {
2
2
  "name": "mindforge-cc",
3
- "version": "2.0.0-alpha.6",
3
+ "version": "2.0.0-alpha.8",
4
4
  "description": "MindForge - Enterprise Agentic Framework for Claude Code and Antigravity",
5
5
  "bin": {
6
6
  "mindforge-cc": "bin/install.js"