@jstn-sdk/ma 0.1.0
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/.agents/plugins/marketplace.json +20 -0
- package/.codex/agents/Architect.toml +4 -0
- package/.codex/agents/Auditor.toml +4 -0
- package/.codex/agents/Builder.toml +4 -0
- package/.codex/agents/Flow.toml +4 -0
- package/.codex/agents/Sage.toml +4 -0
- package/.codex/agents/Vibe.toml +4 -0
- package/.codex/hooks.json +15 -0
- package/.codex/prompts/enforcement.md +59 -0
- package/.codex/prompts/onboarding.md +41 -0
- package/.codex/prompts/release-rules.md +28 -0
- package/.codex/prompts/skill-contract.md +41 -0
- package/LICENSE +21 -0
- package/README.md +532 -0
- package/bin/ma.js +300 -0
- package/bin/meta-architect.js +3 -0
- package/docs/README.md +24 -0
- package/docs/assets/meta-architect-logo.png +0 -0
- package/docs/assets/meta-architect-logo.svg +8 -0
- package/docs/getting-started.md +451 -0
- package/docs/mcp-setup.md +5 -0
- package/docs/onboarding.md +65 -0
- package/docs/qa/release-readiness-0.1.0.md +62 -0
- package/docs/release-spec.md +86 -0
- package/docs/skills-publishing.md +231 -0
- package/docs/skills.md +91 -0
- package/index.js +28 -0
- package/mcp/collections.json +21 -0
- package/mcp/fallback.json +7 -0
- package/mcp/servers.json +55 -0
- package/package.json +84 -0
- package/plugins/meta-architect/.app.json +8 -0
- package/plugins/meta-architect/.codex-plugin/plugin.json +23 -0
- package/plugins/meta-architect/.mcp.json +12 -0
- package/plugins/meta-architect/README.md +121 -0
- package/plugins/meta-architect/skills/arch/SKILL.md +27 -0
- package/plugins/meta-architect/skills/arch/agents/openai.yaml +4 -0
- package/plugins/meta-architect/skills/build/SKILL.md +24 -0
- package/plugins/meta-architect/skills/build/agents/openai.yaml +4 -0
- package/plugins/meta-architect/skills/flow/SKILL.md +24 -0
- package/plugins/meta-architect/skills/flow/agents/openai.yaml +4 -0
- package/plugins/meta-architect/skills/meta-architect/SKILL.md +30 -0
- package/plugins/meta-architect/skills/meta-architect/agents/openai.yaml +4 -0
- package/plugins/meta-architect/skills/meta-architect/references/core-release-rules.md +13 -0
- package/plugins/meta-architect/skills/sage/SKILL.md +24 -0
- package/plugins/meta-architect/skills/sage/agents/openai.yaml +4 -0
- package/plugins/meta-architect/skills/vet/SKILL.md +25 -0
- package/plugins/meta-architect/skills/vet/agents/openai.yaml +4 -0
- package/plugins/meta-architect/skills/vibe/SKILL.md +24 -0
- package/plugins/meta-architect/skills/vibe/agents/openai.yaml +4 -0
- package/scripts/doctor.js +37 -0
- package/scripts/plugin-sync.js +92 -0
- package/scripts/postinstall.js +19 -0
- package/scripts/release-metadata.js +94 -0
- package/scripts/release-verify.js +153 -0
- package/scripts/setup-npmrc.js +39 -0
- package/scripts/skills-install.js +29 -0
- package/scripts/skills-manifest.js +61 -0
- package/scripts/skills-pack.js +54 -0
- package/scripts/skills-validate.js +118 -0
- package/skills/arch/SKILL.md +27 -0
- package/skills/arch/agents/openai.yaml +4 -0
- package/skills/build/SKILL.md +24 -0
- package/skills/build/agents/openai.yaml +4 -0
- package/skills/flow/SKILL.md +24 -0
- package/skills/flow/agents/openai.yaml +4 -0
- package/skills/index.json +40 -0
- package/skills/meta-architect/SKILL.md +30 -0
- package/skills/meta-architect/agents/openai.yaml +4 -0
- package/skills/meta-architect/references/core-release-rules.md +13 -0
- package/skills/sage/SKILL.md +24 -0
- package/skills/sage/agents/openai.yaml +4 -0
- package/skills/vet/SKILL.md +25 -0
- package/skills/vet/agents/openai.yaml +4 -0
- package/skills/vibe/SKILL.md +24 -0
- package/skills/vibe/agents/openai.yaml +4 -0
- package/sprint/00-idea.md +27 -0
- package/sprint/01-architecture.md +26 -0
- package/sprint/02-oss-evidence.md +26 -0
- package/sprint/03-logic.md +25 -0
- package/sprint/04-security.md +25 -0
- package/sprint/05-dx-ux.md +24 -0
- package/sprint/06-build-plan.md +26 -0
- package/sprint/07-release.md +26 -0
- package/src/build-gate.js +52 -0
- package/src/decision-log.js +40 -0
- package/src/fs-utils.js +25 -0
- package/src/launcher.js +55 -0
- package/src/mcp-config.js +30 -0
- package/src/mcp-live-client.js +186 -0
- package/src/paths.js +26 -0
- package/src/policy.js +23 -0
- package/src/release-state.js +59 -0
- package/src/runtime-artifacts.js +363 -0
- package/src/skill-installer.js +49 -0
- package/src/skills.js +507 -0
- package/src/state-sync.js +15 -0
|
@@ -0,0 +1,451 @@
|
|
|
1
|
+
# Getting Started
|
|
2
|
+
|
|
3
|
+
This guide takes a new user from clone to a green-gated Meta-Architect workflow on a real project.
|
|
4
|
+
|
|
5
|
+
## Goal
|
|
6
|
+
|
|
7
|
+
By the end of this guide you should be able to:
|
|
8
|
+
- install Meta-Architect locally
|
|
9
|
+
- configure MCP/GitMCP sources
|
|
10
|
+
- run the full architecture-to-build sequence
|
|
11
|
+
- understand how each gate moves
|
|
12
|
+
- diagnose blocked gates
|
|
13
|
+
- use the merge/release path safely
|
|
14
|
+
|
|
15
|
+
## Prerequisites
|
|
16
|
+
|
|
17
|
+
- Node.js 20+
|
|
18
|
+
- npm 10+
|
|
19
|
+
- Git 2.30+
|
|
20
|
+
- an MCP-capable runtime
|
|
21
|
+
- network access if you want live `$sage` verification against a real GitMCP server
|
|
22
|
+
|
|
23
|
+
## 1. Canonical install and launch
|
|
24
|
+
|
|
25
|
+
Canonical public install:
|
|
26
|
+
|
|
27
|
+
```bash
|
|
28
|
+
# Install
|
|
29
|
+
npm i -g @openai/codex@latest @jstn-sdk/ma@latest
|
|
30
|
+
|
|
31
|
+
# Launch
|
|
32
|
+
ma --madmax --high
|
|
33
|
+
|
|
34
|
+
# Remove Meta-Architect only
|
|
35
|
+
npm uninstall -g @jstn-sdk/ma
|
|
36
|
+
|
|
37
|
+
# Remove Meta-Architect and Codex
|
|
38
|
+
npm uninstall -g @jstn-sdk/ma @openai/codex
|
|
39
|
+
```
|
|
40
|
+
|
|
41
|
+
That is the default operator posture. `ma` is the Meta-Architect launcher for a Codex session, and the rest of this guide should match the in-session workflow shape in [example/usage-workflow.md](../example/usage-workflow.md).
|
|
42
|
+
|
|
43
|
+
## 2. Real usage workflow
|
|
44
|
+
|
|
45
|
+
Start with the structured `$arch` prompt:
|
|
46
|
+
|
|
47
|
+
```text
|
|
48
|
+
$arch I want to build: [PROJECT IDEA]
|
|
49
|
+
|
|
50
|
+
Context:
|
|
51
|
+
- Product type: [web app / mobile app / API / marketplace / agent system / internal tool]
|
|
52
|
+
- Users: [who will use it]
|
|
53
|
+
- Core problem: [what problem it solves]
|
|
54
|
+
- Main features:
|
|
55
|
+
1. [feature one]
|
|
56
|
+
2. [feature two]
|
|
57
|
+
3. [feature three]
|
|
58
|
+
- Constraints:
|
|
59
|
+
- Budget: [low / medium / high]
|
|
60
|
+
- Team size: [solo / small / medium]
|
|
61
|
+
- Timeline: [e.g. 2 weeks MVP, 3 months beta]
|
|
62
|
+
- Preferred stack: [optional]
|
|
63
|
+
- Avoid: [optional]
|
|
64
|
+
- Quality priorities:
|
|
65
|
+
- [e.g. speed, low cost, security, DX, maintainability, scalability]
|
|
66
|
+
- Deployment target:
|
|
67
|
+
- [Vercel / Docker / VPS / AWS / GCP / local-first / hybrid]
|
|
68
|
+
|
|
69
|
+
Required output:
|
|
70
|
+
1. Problem framing
|
|
71
|
+
2. Recommended architecture
|
|
72
|
+
3. Stack decision with justification
|
|
73
|
+
4. System components and responsibilities
|
|
74
|
+
5. Data model and storage choices
|
|
75
|
+
6. Auth/security considerations
|
|
76
|
+
7. DX/UX considerations
|
|
77
|
+
8. Delivery plan for v0.1.0
|
|
78
|
+
9. Risks and trade-offs
|
|
79
|
+
10. Decision log
|
|
80
|
+
11. Exact next trigger to run after this
|
|
81
|
+
```
|
|
82
|
+
|
|
83
|
+
Then continue with:
|
|
84
|
+
|
|
85
|
+
```text
|
|
86
|
+
$sage
|
|
87
|
+
$flow
|
|
88
|
+
$vet
|
|
89
|
+
$vibe
|
|
90
|
+
$build
|
|
91
|
+
```
|
|
92
|
+
|
|
93
|
+
Use the full prompt blocks from [example/usage-workflow.md](../example/usage-workflow.md) when you want the exact handoff format between lanes.
|
|
94
|
+
|
|
95
|
+
## 3. Contributor clone and link
|
|
96
|
+
|
|
97
|
+
```bash
|
|
98
|
+
git clone https://github.com/JustineDevs/meta-architect.git
|
|
99
|
+
cd meta-architect
|
|
100
|
+
npm install
|
|
101
|
+
npm link
|
|
102
|
+
```
|
|
103
|
+
|
|
104
|
+
Why `npm link` matters:
|
|
105
|
+
- the docs use the `ma` command directly
|
|
106
|
+
- `npm link` makes the local CLI available without requiring a global publish step
|
|
107
|
+
|
|
108
|
+
## 4. Secondary repository setup flow
|
|
109
|
+
|
|
110
|
+
```bash
|
|
111
|
+
ma setup
|
|
112
|
+
```
|
|
113
|
+
|
|
114
|
+
Optional interactive session:
|
|
115
|
+
|
|
116
|
+
```bash
|
|
117
|
+
ma
|
|
118
|
+
```
|
|
119
|
+
|
|
120
|
+
Expected effects:
|
|
121
|
+
- `.codex/agents/` exists
|
|
122
|
+
- `.codex/prompts/` exists
|
|
123
|
+
- local `.ma/skills/`, `.ma/evidence/`, `.ma/context/`, `.ma/specs/`, `.ma/plans/`, and `.ma/runbook.md` are seeded
|
|
124
|
+
- `mcp/`, `docs/`, and `sprint/` surfaces exist
|
|
125
|
+
- `ma` launches the local Codex CLI when run with no arguments
|
|
126
|
+
|
|
127
|
+
Expected output:
|
|
128
|
+
|
|
129
|
+
```text
|
|
130
|
+
meta-architect setup
|
|
131
|
+
====================
|
|
132
|
+
ready: .codex/agents
|
|
133
|
+
ready: .codex/prompts
|
|
134
|
+
ready: .ma/skills
|
|
135
|
+
ready: .ma/evidence
|
|
136
|
+
ready: .ma/context
|
|
137
|
+
ready: .ma/specs
|
|
138
|
+
ready: .ma/plans
|
|
139
|
+
ready: mcp
|
|
140
|
+
ready: docs
|
|
141
|
+
ready: docs/qa
|
|
142
|
+
ready: sprint
|
|
143
|
+
```
|
|
144
|
+
|
|
145
|
+
This setup path is secondary to the canonical `ma --madmax --high` runtime launch. Use it when you need local repo scaffolding.
|
|
146
|
+
|
|
147
|
+
## 4.1 Understand the two surfaces
|
|
148
|
+
|
|
149
|
+
Meta-Architect works in two simple ways:
|
|
150
|
+
|
|
151
|
+
- terminal commands
|
|
152
|
+
- in-session skills
|
|
153
|
+
|
|
154
|
+
Terminal commands are normal shell commands:
|
|
155
|
+
|
|
156
|
+
```bash
|
|
157
|
+
ma setup
|
|
158
|
+
ma init
|
|
159
|
+
ma status
|
|
160
|
+
ma run '$arch'
|
|
161
|
+
```
|
|
162
|
+
|
|
163
|
+
In-session skills are prompts used after you are already inside Codex:
|
|
164
|
+
|
|
165
|
+
```text
|
|
166
|
+
$arch
|
|
167
|
+
$sage
|
|
168
|
+
$flow
|
|
169
|
+
$vet
|
|
170
|
+
$vibe
|
|
171
|
+
$build
|
|
172
|
+
```
|
|
173
|
+
|
|
174
|
+
Easy rule:
|
|
175
|
+
- `ma ...` = terminal helper command
|
|
176
|
+
- `$...` = in-session skill
|
|
177
|
+
|
|
178
|
+
`ma setup` and `ma init` currently do the same thing:
|
|
179
|
+
- they create local `.ma/` support files
|
|
180
|
+
- they prepare context, specs, plans, evidence, and runbook files
|
|
181
|
+
- they do not automatically run the skill workflow
|
|
182
|
+
|
|
183
|
+
## 5. Configure MCP / GitMCP
|
|
184
|
+
|
|
185
|
+
Edit:
|
|
186
|
+
- `mcp/servers.json`
|
|
187
|
+
- `mcp/collections.json`
|
|
188
|
+
- `mcp/fallback.json`
|
|
189
|
+
|
|
190
|
+
Minimum live example:
|
|
191
|
+
|
|
192
|
+
```json
|
|
193
|
+
{
|
|
194
|
+
"category": "meta-list",
|
|
195
|
+
"repo": "sindresorhus/awesome",
|
|
196
|
+
"endpoint": "https://gitmcp.io/sindresorhus/awesome"
|
|
197
|
+
}
|
|
198
|
+
```
|
|
199
|
+
|
|
200
|
+
Recommended first set:
|
|
201
|
+
- `sindresorhus/awesome`
|
|
202
|
+
- `dzharii/awesome-typescript`
|
|
203
|
+
- `sbilly/awesome-security`
|
|
204
|
+
|
|
205
|
+
See [docs/mcp-setup.md](./mcp-setup.md) for endpoint policy and evidence semantics.
|
|
206
|
+
|
|
207
|
+
## 6. Secondary helper flow
|
|
208
|
+
|
|
209
|
+
```bash
|
|
210
|
+
ma idea "Build a real-time collaborative whiteboard for product teams"
|
|
211
|
+
```
|
|
212
|
+
|
|
213
|
+
Expected effects:
|
|
214
|
+
- an idea decision entry is appended to `.ma/decisions.json`
|
|
215
|
+
- `idea_status = CLEAR`
|
|
216
|
+
|
|
217
|
+
If this fails:
|
|
218
|
+
- ensure the idea text is not empty
|
|
219
|
+
- inspect `.ma/decisions.json` for malformed local data
|
|
220
|
+
|
|
221
|
+
## 7. Run the helper skill sequence
|
|
222
|
+
|
|
223
|
+
### 5.1 Architecture
|
|
224
|
+
|
|
225
|
+
```bash
|
|
226
|
+
ma run '$arch'
|
|
227
|
+
```
|
|
228
|
+
|
|
229
|
+
Expected effects:
|
|
230
|
+
- a structured first-pass architecture blueprint is appended
|
|
231
|
+
- `architecture_status = APPROVED`
|
|
232
|
+
|
|
233
|
+
Generated or updated:
|
|
234
|
+
- `.ma/decisions.json`
|
|
235
|
+
- `.ma/release.json`
|
|
236
|
+
- `.ma/context/project.md`
|
|
237
|
+
- `.ma/specs/architecture.md`
|
|
238
|
+
- `.ma/plans/implementation.md`
|
|
239
|
+
|
|
240
|
+
### 5.2 Evidence
|
|
241
|
+
|
|
242
|
+
```bash
|
|
243
|
+
ma run '$sage'
|
|
244
|
+
```
|
|
245
|
+
|
|
246
|
+
Expected effects:
|
|
247
|
+
- `architecture_status` must already be approved
|
|
248
|
+
- configured GitMCP endpoints are validated
|
|
249
|
+
- the latest architecture summary is used as the probe query basis
|
|
250
|
+
- the first configured live source is probed when live mode is enabled
|
|
251
|
+
- `.ma/evidence/sources.json` is updated
|
|
252
|
+
- `evidence_status` becomes:
|
|
253
|
+
- `VERIFIED` on a real successful live probe
|
|
254
|
+
- `PARTIAL` when configured evidence exists but live proof is incomplete or disabled
|
|
255
|
+
- `MISSING` when no usable approved source exists
|
|
256
|
+
|
|
257
|
+
Generated or updated:
|
|
258
|
+
- `.ma/evidence/sources.json`
|
|
259
|
+
- `.ma/decisions.json`
|
|
260
|
+
- `.ma/release.json`
|
|
261
|
+
- `.ma/specs/evidence.md`
|
|
262
|
+
|
|
263
|
+
If this fails:
|
|
264
|
+
- check endpoint URLs in `mcp/servers.json`
|
|
265
|
+
- ensure architecture was approved first
|
|
266
|
+
- verify network access
|
|
267
|
+
- rerun after correcting the endpoint or environment
|
|
268
|
+
|
|
269
|
+
### 5.3 Logic
|
|
270
|
+
|
|
271
|
+
```bash
|
|
272
|
+
ma run '$flow'
|
|
273
|
+
```
|
|
274
|
+
|
|
275
|
+
Expected effects:
|
|
276
|
+
- a structured first-pass logic/state review is appended
|
|
277
|
+
- `logic_status = GREEN` when current prerequisites and transition modeling are acceptable
|
|
278
|
+
- `logic_status = RED` when prerequisite gates are not ready
|
|
279
|
+
|
|
280
|
+
Generated or updated:
|
|
281
|
+
- `.ma/specs/logic.md`
|
|
282
|
+
|
|
283
|
+
### 5.4 Security
|
|
284
|
+
|
|
285
|
+
```bash
|
|
286
|
+
ma run '$vet'
|
|
287
|
+
```
|
|
288
|
+
|
|
289
|
+
Expected effects:
|
|
290
|
+
- `.ma/evidence/audits.json` and `.ma/evidence/cves.json` are updated
|
|
291
|
+
- `security_status = GREEN` on a baseline pass
|
|
292
|
+
- `security_status = RED` when prerequisite gates are not ready
|
|
293
|
+
|
|
294
|
+
Generated or updated:
|
|
295
|
+
- `.ma/specs/security.md`
|
|
296
|
+
|
|
297
|
+
### 5.5 Experience
|
|
298
|
+
|
|
299
|
+
```bash
|
|
300
|
+
ma run '$vibe'
|
|
301
|
+
ma run '$vibe' --waive --reason "Accepted for this release line"
|
|
302
|
+
```
|
|
303
|
+
|
|
304
|
+
Expected effects:
|
|
305
|
+
- `.ma/evidence/outcomes.json` is updated
|
|
306
|
+
- `experience_status = GREEN` on a baseline pass
|
|
307
|
+
- `experience_status = RED` when prerequisite gates are not ready
|
|
308
|
+
- `experience_status = WAIVED` when the waiver path is used explicitly
|
|
309
|
+
|
|
310
|
+
Generated or updated:
|
|
311
|
+
- `.ma/specs/experience.md`
|
|
312
|
+
|
|
313
|
+
## 8. Inspect gate status
|
|
314
|
+
|
|
315
|
+
```bash
|
|
316
|
+
ma status
|
|
317
|
+
```
|
|
318
|
+
|
|
319
|
+
Expected green-state output:
|
|
320
|
+
|
|
321
|
+
```text
|
|
322
|
+
Meta-Architect Status
|
|
323
|
+
=====================
|
|
324
|
+
Idea: CLEAR
|
|
325
|
+
Architecture: APPROVED
|
|
326
|
+
Evidence: VERIFIED
|
|
327
|
+
Logic: GREEN
|
|
328
|
+
Security: GREEN
|
|
329
|
+
Experience: GREEN
|
|
330
|
+
Build: LOCKED
|
|
331
|
+
Next allowed triggers:
|
|
332
|
+
$build
|
|
333
|
+
```
|
|
334
|
+
|
|
335
|
+
## 9. Unlock and run build planning
|
|
336
|
+
|
|
337
|
+
```bash
|
|
338
|
+
ma run '$build'
|
|
339
|
+
```
|
|
340
|
+
|
|
341
|
+
Expected effects:
|
|
342
|
+
- build gate is evaluated
|
|
343
|
+
- if allowed, `build_status = READY`
|
|
344
|
+
- branch suggestions are printed
|
|
345
|
+
- worktree commands are suggested
|
|
346
|
+
- `.ma/plans/build.md` is updated
|
|
347
|
+
|
|
348
|
+
Expected output shape:
|
|
349
|
+
|
|
350
|
+
```text
|
|
351
|
+
Build gate is green.
|
|
352
|
+
Suggested branches:
|
|
353
|
+
- feature/ui
|
|
354
|
+
- feature/api
|
|
355
|
+
Optional worktree commands:
|
|
356
|
+
git worktree add ../ui feature/ui
|
|
357
|
+
git worktree add ../api feature/api
|
|
358
|
+
```
|
|
359
|
+
|
|
360
|
+
If `$build` fails:
|
|
361
|
+
- run `ma status`
|
|
362
|
+
- read the blocking statuses
|
|
363
|
+
- fix the corresponding upstream lane
|
|
364
|
+
- rerun that lane, then rerun `$build`
|
|
365
|
+
|
|
366
|
+
## 10. Example walkthrough: collaborative whiteboard
|
|
367
|
+
|
|
368
|
+
```bash
|
|
369
|
+
ma setup
|
|
370
|
+
ma idea "Build a collaborative whiteboard with live cursors and shared boards"
|
|
371
|
+
ma run '$arch'
|
|
372
|
+
ma run '$sage'
|
|
373
|
+
ma run '$flow'
|
|
374
|
+
ma run '$vet'
|
|
375
|
+
ma run '$vibe'
|
|
376
|
+
ma status
|
|
377
|
+
ma run '$build'
|
|
378
|
+
```
|
|
379
|
+
|
|
380
|
+
If you want an interactive Codex session during the walkthrough, start it separately with `ma`.
|
|
381
|
+
|
|
382
|
+
What should happen:
|
|
383
|
+
- `$arch` records a structured first-pass blueprint
|
|
384
|
+
- `$sage` binds major choices to configured GitMCP-backed sources
|
|
385
|
+
- `$flow` records the kernel’s baseline state review for the mission
|
|
386
|
+
- `$vet` records a baseline security review
|
|
387
|
+
- `$vibe` records baseline DX/UX guidance
|
|
388
|
+
- `$build` suggests bounded concerns like `feature/ui` and `feature/api`
|
|
389
|
+
|
|
390
|
+
Related mission:
|
|
391
|
+
- [missions/collaborative-whiteboard/mission.md](../missions/collaborative-whiteboard/mission.md)
|
|
392
|
+
|
|
393
|
+
## 9. Merge and release path
|
|
394
|
+
|
|
395
|
+
After implementation work is complete:
|
|
396
|
+
|
|
397
|
+
```bash
|
|
398
|
+
ma merge feature/ui development
|
|
399
|
+
ma release development prod
|
|
400
|
+
```
|
|
401
|
+
|
|
402
|
+
Expected effects:
|
|
403
|
+
- merge only succeeds for `feature/* -> development`
|
|
404
|
+
- release only succeeds for `development|release/* -> prod`
|
|
405
|
+
- final statuses advance to:
|
|
406
|
+
- `build_status = DONE`
|
|
407
|
+
- `merge_status = MERGED_TO_DEVELOPMENT`
|
|
408
|
+
- `release_status = SHIPPED_TO_PROD`
|
|
409
|
+
|
|
410
|
+
## 10. Files generated or updated during a normal run
|
|
411
|
+
|
|
412
|
+
- `.ma/decisions.json`
|
|
413
|
+
- `.ma/release.json`
|
|
414
|
+
- `.ma/evidence/sources.json`
|
|
415
|
+
- `.ma/evidence/audits.json`
|
|
416
|
+
- `.ma/evidence/cves.json`
|
|
417
|
+
- `.ma/evidence/outcomes.json`
|
|
418
|
+
- `.ma/context/project.md`
|
|
419
|
+
- `.ma/specs/architecture.md`
|
|
420
|
+
- `.ma/specs/evidence.md`
|
|
421
|
+
- `.ma/specs/logic.md`
|
|
422
|
+
- `.ma/specs/security.md`
|
|
423
|
+
- `.ma/specs/experience.md`
|
|
424
|
+
- `.ma/plans/implementation.md`
|
|
425
|
+
- `.ma/plans/build.md`
|
|
426
|
+
- `.ma/runbook.md`
|
|
427
|
+
|
|
428
|
+
These are local product artifacts created by the runtime. They are not a reason to bypass gate logic manually.
|
|
429
|
+
|
|
430
|
+
## 11. If a gate fails
|
|
431
|
+
|
|
432
|
+
Rule:
|
|
433
|
+
- do not edit statuses manually
|
|
434
|
+
- rerun the correct upstream command
|
|
435
|
+
- use `ma status` as the authority
|
|
436
|
+
|
|
437
|
+
Common examples:
|
|
438
|
+
- `evidence_status = MISSING` -> fix `mcp/servers.json`, rerun `$sage`
|
|
439
|
+
- `logic_status = RED` -> fix upstream evidence/architecture issues, rerun `$flow`
|
|
440
|
+
- `security_status = RED` -> resolve issues surfaced by `$vet`
|
|
441
|
+
- `experience_status = RED` -> rerun `$vibe` after clearing prerequisites
|
|
442
|
+
- `experience_status = WAIVED` -> verify the waiver reason recorded in `.ma/release.json`
|
|
443
|
+
|
|
444
|
+
## Related docs
|
|
445
|
+
|
|
446
|
+
- [README.md](../README.md)
|
|
447
|
+
- [Skills Reference](./skills.md)
|
|
448
|
+
- [MCP Setup](./mcp-setup.md)
|
|
449
|
+
- [Release Spec](./release-spec.md)
|
|
450
|
+
- [Skills Publishing](./skills-publishing.md)
|
|
451
|
+
- [Plugin Bundle](../plugins/meta-architect/README.md)
|
|
@@ -0,0 +1,65 @@
|
|
|
1
|
+
# Onboarding
|
|
2
|
+
|
|
3
|
+
This is the shortest operator entrypoint for someone who just opened Meta-Architect and needs the real first-run path.
|
|
4
|
+
|
|
5
|
+
## Read first
|
|
6
|
+
|
|
7
|
+
1. `README.md`
|
|
8
|
+
2. `docs/getting-started.md`
|
|
9
|
+
3. `example/usage-workflow.md`
|
|
10
|
+
4. `docs/release-spec.md`
|
|
11
|
+
5. `docs/skills-publishing.md`
|
|
12
|
+
|
|
13
|
+
## Canonical install and launch
|
|
14
|
+
|
|
15
|
+
```bash
|
|
16
|
+
# Install
|
|
17
|
+
npm i -g @openai/codex@latest @jstn-sdk/ma@latest
|
|
18
|
+
|
|
19
|
+
# Launch
|
|
20
|
+
ma --madmax --high
|
|
21
|
+
|
|
22
|
+
# Remove Meta-Architect only
|
|
23
|
+
npm uninstall -g @jstn-sdk/ma
|
|
24
|
+
|
|
25
|
+
# Remove Meta-Architect and Codex
|
|
26
|
+
npm uninstall -g @jstn-sdk/ma @openai/codex
|
|
27
|
+
```
|
|
28
|
+
|
|
29
|
+
## First runtime action
|
|
30
|
+
|
|
31
|
+
Start with the structured `$arch` prompt from [example/usage-workflow.md](../example/usage-workflow.md):
|
|
32
|
+
|
|
33
|
+
```text
|
|
34
|
+
$arch I want to build: [PROJECT IDEA]
|
|
35
|
+
```
|
|
36
|
+
|
|
37
|
+
Then continue through:
|
|
38
|
+
- `$sage`
|
|
39
|
+
- `$flow`
|
|
40
|
+
- `$vet`
|
|
41
|
+
- `$vibe`
|
|
42
|
+
- `$build`
|
|
43
|
+
|
|
44
|
+
## Secondary helper path
|
|
45
|
+
|
|
46
|
+
Only use this when you need local repo scaffolding or scripted validation:
|
|
47
|
+
|
|
48
|
+
```bash
|
|
49
|
+
ma setup
|
|
50
|
+
ma
|
|
51
|
+
ma idea "..."
|
|
52
|
+
ma run '$arch'
|
|
53
|
+
ma run '$sage'
|
|
54
|
+
ma run '$flow'
|
|
55
|
+
ma run '$vet'
|
|
56
|
+
ma run '$vibe'
|
|
57
|
+
ma run '$build'
|
|
58
|
+
```
|
|
59
|
+
|
|
60
|
+
## First safety rules
|
|
61
|
+
|
|
62
|
+
- Do not commit runtime `.ma` state.
|
|
63
|
+
- Do not bypass gates by editing status files manually.
|
|
64
|
+
- Do not assume a release channel succeeded without evidence.
|
|
65
|
+
- Do not treat fallback MCP docs mode as normal verified evidence.
|
|
@@ -0,0 +1,62 @@
|
|
|
1
|
+
# Release Readiness 0.1.0
|
|
2
|
+
|
|
3
|
+
## Production bar
|
|
4
|
+
|
|
5
|
+
`v0.1.0` is treated as production only when:
|
|
6
|
+
- the package installs cleanly from the canonical public install command
|
|
7
|
+
- the Codex-hosted runtime path works end to end
|
|
8
|
+
- the helper flow remains valid for scripted verification
|
|
9
|
+
- release docs, package metadata, and workflows all agree on `0.1.0`
|
|
10
|
+
|
|
11
|
+
Target release state:
|
|
12
|
+
- npm package: `@jstn-sdk/ma@0.1.0`
|
|
13
|
+
- npm registry state: pending manual publish
|
|
14
|
+
- publishability note: this renamed package line is intended to publish as `0.1.0`
|
|
15
|
+
- git tag: `v0.1.0`
|
|
16
|
+
- GitHub release: published at `2026-05-02T10:59:33Z`
|
|
17
|
+
|
|
18
|
+
## Automated checks run
|
|
19
|
+
|
|
20
|
+
```bash
|
|
21
|
+
npm run release:check
|
|
22
|
+
```
|
|
23
|
+
|
|
24
|
+
That must cover:
|
|
25
|
+
- skills manifest generation
|
|
26
|
+
- skill validation
|
|
27
|
+
- skill bundle packaging
|
|
28
|
+
- repo checks
|
|
29
|
+
- automated tests
|
|
30
|
+
- npm package dry-run inspection
|
|
31
|
+
|
|
32
|
+
## Manual/behavioral checks run
|
|
33
|
+
|
|
34
|
+
Canonical launch:
|
|
35
|
+
|
|
36
|
+
```bash
|
|
37
|
+
ma --madmax --high
|
|
38
|
+
```
|
|
39
|
+
|
|
40
|
+
Helper-path validation:
|
|
41
|
+
|
|
42
|
+
```bash
|
|
43
|
+
ma setup
|
|
44
|
+
ma idea "Build a demo app"
|
|
45
|
+
ma run '$arch'
|
|
46
|
+
ma run '$sage'
|
|
47
|
+
ma run '$flow'
|
|
48
|
+
ma run '$vet'
|
|
49
|
+
ma run '$vibe'
|
|
50
|
+
ma status
|
|
51
|
+
ma run '$build'
|
|
52
|
+
```
|
|
53
|
+
|
|
54
|
+
Expected evidence:
|
|
55
|
+
- `.ma/release.json` remains the source of truth
|
|
56
|
+
- `.ma/decisions.json` records the helper-path activity
|
|
57
|
+
- `$build` stays blocked until upstream gates are green, then becomes ready
|
|
58
|
+
|
|
59
|
+
## Known limitations
|
|
60
|
+
|
|
61
|
+
- interactive Codex conversation quality depends on the installed Codex host
|
|
62
|
+
- release publication still depends on npm ownership/authorization for the target package name
|
|
@@ -0,0 +1,86 @@
|
|
|
1
|
+
# v0.1.0 Requirements & Rules
|
|
2
|
+
|
|
3
|
+
## Production definition
|
|
4
|
+
|
|
5
|
+
Meta-Architect `v0.1.0` is production only when:
|
|
6
|
+
1. the package/install surface works
|
|
7
|
+
2. the runtime workflow from `$arch` through `$build` works
|
|
8
|
+
3. the release evidence matches the actual package and git tag
|
|
9
|
+
|
|
10
|
+
## What `v0.1.0` must have
|
|
11
|
+
|
|
12
|
+
### 1. Canonical package/runtime path
|
|
13
|
+
|
|
14
|
+
- install: `npm i -g @openai/codex@latest @jstn-sdk/ma@latest`
|
|
15
|
+
- launch: `ma --madmax --high`
|
|
16
|
+
- uninstall Meta-Architect only: `npm uninstall -g @jstn-sdk/ma`
|
|
17
|
+
- uninstall Meta-Architect and Codex: `npm uninstall -g @jstn-sdk/ma @openai/codex`
|
|
18
|
+
- runtime trigger surface:
|
|
19
|
+
- `$arch`
|
|
20
|
+
- `$sage`
|
|
21
|
+
- `$flow`
|
|
22
|
+
- `$vet`
|
|
23
|
+
- `$vibe`
|
|
24
|
+
- `$build`
|
|
25
|
+
|
|
26
|
+
### 2. Secondary helper path
|
|
27
|
+
|
|
28
|
+
Helper commands remain available for setup and scripted validation:
|
|
29
|
+
- `ma setup`
|
|
30
|
+
- `ma idea`
|
|
31
|
+
- `ma run ...`
|
|
32
|
+
- `ma status`
|
|
33
|
+
- `ma merge`
|
|
34
|
+
- `ma release`
|
|
35
|
+
|
|
36
|
+
### 3. State and gate contract
|
|
37
|
+
|
|
38
|
+
Canonical runtime namespace:
|
|
39
|
+
- `.ma/`
|
|
40
|
+
|
|
41
|
+
Canonical state files:
|
|
42
|
+
- `.ma/decisions.json`
|
|
43
|
+
- `.ma/release.json`
|
|
44
|
+
- `.ma/evidence/*`
|
|
45
|
+
- `.ma/context/*`
|
|
46
|
+
- `.ma/specs/*`
|
|
47
|
+
- `.ma/plans/*`
|
|
48
|
+
- `.ma/runbook.md`
|
|
49
|
+
|
|
50
|
+
### 4. Required release evidence
|
|
51
|
+
|
|
52
|
+
- `package.json` version `0.1.0`
|
|
53
|
+
- git tag `v0.1.0`
|
|
54
|
+
- `RELEASE.md`
|
|
55
|
+
- `CHANGELOG.md`
|
|
56
|
+
- `docs/qa/release-readiness-0.1.0.md`
|
|
57
|
+
- green `npm run release:check`
|
|
58
|
+
|
|
59
|
+
### 5. Dist-tag discipline
|
|
60
|
+
|
|
61
|
+
- stable versions such as `0.1.0` publish to npm `latest`
|
|
62
|
+
- prerelease versions such as `0.2.0-beta.1` must publish with explicit tags such as `beta`
|
|
63
|
+
- recommended alternate lanes are `next`, `beta`, and `canary`
|
|
64
|
+
- prerelease publication must use `npm publish --tag <lane>`
|
|
65
|
+
- stable publication keeps scoped public access and provenance enabled
|
|
66
|
+
|
|
67
|
+
### 6. Canonical bump and publish flow
|
|
68
|
+
|
|
69
|
+
1. Run `npm version <version> --no-git-tag-version`
|
|
70
|
+
2. Update `CHANGELOG.md`
|
|
71
|
+
3. Update `RELEASE.md`
|
|
72
|
+
4. Update `docs/qa/release-readiness-<version>.md`
|
|
73
|
+
5. Run `npm run release:verify`
|
|
74
|
+
6. Run `npm run release:check`
|
|
75
|
+
7. Create and push tag `v<version>`
|
|
76
|
+
8. Preferred publish path: publish from `.github/workflows/npm-publish.yml` on a supported cloud runner so provenance can be generated
|
|
77
|
+
9. Local shell fallback when not publishing from GitHub Actions or GitLab CI/CD:
|
|
78
|
+
- Stable publish: `npm publish --access public`
|
|
79
|
+
- Prerelease publish: `npm publish --access public --tag <lane>`
|
|
80
|
+
10. Verify dist-tags with `npm view @jstn-sdk/ma version dist-tags time --json`
|
|
81
|
+
|
|
82
|
+
### 7. Provenance rule
|
|
83
|
+
|
|
84
|
+
- `npm publish --provenance` is valid only from a supported cloud CI/CD provider
|
|
85
|
+
- local shell publishes are expected to fail with `Automatic provenance generation not supported for provider: null`
|
|
86
|
+
- use the repository publish workflow when provenance is part of the release bar
|