vibecoding-devtools 1.0.2 → 1.1.0

package/team/notes/project-context/risks-backlog.md

@@ -0,0 +1,6 @@
+# Risks & Backlog
+
+Owner: Regente. Minor and Suggestion findings that were not fixed land here.
+
+| Ref | Item | Type (risk/backlog) | Severity | Owner | Status |
+|---|---|---|---|---|---|

package/team/notes/team-roster.md

@@ -0,0 +1,67 @@
+# Team Roster
+
+Permanent team record. Owner: Regente. Project facts go in the `Project Context` fichário, never here.
+
+## Agents
+
+| Name | Role | CLI | Model · effort | Plan the command assumes |
+|---|---|---|---|---|
+| Regente | Team Maestro | Claude Code | Opus 5.5 · high | Claude Max |
+| Vitral | Frontend Engineer | Claude Code | Sonnet 5.5 · high | Claude Max |
+| Bússola | UX/UI Designer | Claude Code | Opus 5.5 · high | Claude Max |
+| Alicerce | Backend Architect | Claude Code | Sonnet 5.5 · high | Claude Max |
+| Sentinela | AppSec Auditor | Claude Code | Opus 5.5 · medium, no Edit/Write | Claude Max |
+| Crivo | Code Reviewer | Claude Code | Opus 5.5 · medium, no Edit/Write | Claude Max |
+| Guindaste | DevOps Engineer | Claude Code | Sonnet 5.5 · medium | Claude Max |
+| Forja | Backend Engineer | Codex | gpt-6.1-sol · medium | ChatGPT Plus |
+| Ensaio | QA Engineer | Codex | gpt-6.1-sol · medium | ChatGPT Plus |
+| Aquarela | Visual Asset Designer | Codex | gpt-6.1-sol · low + imagegen | ChatGPT Plus |
+| Retina | Visual QA Inspector | Antigravity | gemini-4-argon-medium | Gemini Pro / Argon |
+| Sonda | Research Analyst | Antigravity | gemini-4-argon-high | Gemini Pro / Argon |
+| Formiga | Task Runner | Antigravity | gemini-3.8-flash-medium | Gemini Pro / Gemini |
+
+Launch modes: Claude `--permission-mode auto`; Codex `--approve-for-me` (workspace-write sandbox, no shell network by
+default); Antigravity `--mode auto`, except Formiga: limited agent (`--mode accept-edits` plus a session `--settings`
+allowlist with `toolPermission: request-review`). Allowed: read, search, `mkdir`, `mv`, read-only git, `git mv`,
+`maestri ask/list/note read`; denied: `rm`, network, permission changes, git writes. Other commands prompt: approve once
+only when in scope, never options 2 or 3. Codex and Antigravity start in the role folder and get the project root with
+`--add-dir ../../..`. Exact commands are stored on each terminal (and in the partitura).
+
+Codex restarts may stop on `Hooks need review` (the ECC `SessionStart` hook loses its trust at every start): the
+human trusts it, so press `t` in the review panel, or Esc to skip it; the kit's own hooks keep running either way.
+
+Tier colors (Maestri roles have no color field): Coordination gold · Specification purple · Implementation blue/teal ·
+Validation red/orange · Support green/pink/gray.
+
+## Topology
+
+Regente <-> everyone. Peers: Vitral-Bússola, Vitral-Alicerce, Vitral-Ensaio, Vitral-Crivo, Vitral-Retina,
+Bússola-Retina, Bússola-Aquarela, Alicerce-Forja, Alicerce-Guindaste, Alicerce-Sentinela, Forja-Ensaio, Forja-Crivo,
+Forja-Sentinela (added: backend security findings reach the fixer), Guindaste-Sentinela, Guindaste-Crivo.
+Sonda and Formiga: Regente only. Findings for an owner without a rope go through Regente with their ref.
+
+## Human approval required
+
+Production deploys, releases, merges, destructive operations, handling secrets, sensitive configuration, CI secrets
+and repository settings, significant scope or architecture changes, any change of an agent's model, effort or
+platform (contingencies included).
+
+## Contingencies (propose to the human, apply after OK, between tasks, record in Decisions)
+
+| Trigger | Action |
+|---|---|
+| ChatGPT Plus exhausted | Ensaio to Claude Sonnet 5.5 medium: `maestri recruit --replace "Ensaio" --command "claude --model claude-sonnet-5-5 --effort medium --permission-mode auto --add-dir ../../.."`; verify the auto mode footer; keep it independent of the implementer |
+| Claude Max usage high | Vitral `/effort medium` for routine tasks (session only); Guindaste already runs medium |
+| ChatGPT Plus idle | Simple, non-sensitive DevOps scripts may go to Forja, reviewed by Crivo; sensitive work stays with Guindaste |
+| Argon low | Retina only at milestones; Sonda only for questions that block a decision |
+| Images | ChatGPT Images (Aquarela, imagegen) first; Nano Banana through the `Gemini` portal (Aquarela) for alternatives and edits; capture is rendered pixels, no transparency |
+| Agent unavailable | Reassign only to a competent role; tell the human if it changes an approved configuration |
+
+Review the distribution two weeks after the team's first real task, and record the date in Decisions.
+
+## New project checklist
+
+1. Insert the partitura in the project's workspace.
+2. Fill `Project Context` → Requirements (instance block first).
+3. Make sure the repository has `AGENTS.md` (kit template) with commands and the risk map.
+4. Regente runs a ping round and reads every pool once (maestri-budget checkpoint).