Vantage

Name: vantage
Author: ymatrix1

A personal, calm view of the true state of your work across AI coding agents, git, pull requests, CI/CD, monitoring, Jira or Linear, and Slack.

Vantage tracks work items, not sessions. Each item moves along one evidence-based track, the A2V track from the A2V: Asked to Verified method:

Asked → Built → Proven → Reviewed → Shipped → Verified

A card moves only on evidence: a git diff, a test or data check that ran after the last edit, a PR approval, a deploy, a clean monitoring window. What an agent says never moves a card.

Status: planning. No code yet. These docs are the source of truth.

Planned install (see first run): from any existing repo, run npx vantage add, or /plugin install vantage then /vantage add inside Claude Code. Nothing in the repo changes unless you opt in with --team.

Or install with a prompt (end goal): paste this into Claude Code or Codex in your repo:

Install Vantage in this repo. Follow https://github.com/ymatrix1/vantage/blob/main/docs/install-for-agents.md exactly: show me the dry run first, wait for my OK, then install, verify with vantage doctor, and tell me what changed.

Documents

Doc	What it covers
A2V method	The method Vantage implements: track, five rules, proof levels, signals
PRD	Problem, pains, user, goals, non-goals, success metrics
UX	Surfaces (Focus, Board, Item, Ambient) and UX rules
Architecture	Sources, event store, linker, scorers, surfaces, privacy
Spec: lifecycle	Stage gates, backward moves, flags, proof rules
Spec: work item model	Entities, anchors, linking rules
Spec: flag registry	Every flag: trigger, severity, icon, one action
Spec: proof	Proof types, strength levels, freshness, fake proof detection, the gate
Spec: behaviors and detectors	Behavior sources, AI-decided and commitment detectors, resume with context
Spec: data schema	Tables, immutability, migrations, merge linking
Spec: visual language	Dot alphabet, proof shine, dot characters, landscape home, calm gamification
Spec: Explain	Answer-first briefs, SCR, MECE issue trees with click-to-expand, via the connected agent
Spec: pings	Who you owe a reply, who to nudge, who to tell it's done
Spec: status line	Text glyphs for the dot alphabet in the terminal
Spec: first run	`vantage init`, first view, one-time legend, demo mode
Spec: decision log	Every AI or person decision, with five fields, who and status
Spec: web UI	Navigation, screen states, keyboard map, API, performance budgets
Spec: settings	Engines, budgets and the data policy for outside models, all off by default
Spec: CI/CD	Docs checks now, code checks in Phase 1, releases later
Mockups	Static HTML mockups with synthetic data
Spec: scoring	Priority, difficulty, spread, staleness
Spec: ingestion	How each source is listened to: push, polling, cursors, relay
Spec: operations	Identity, config, secrets, seen state, daemon, health, quality
Roadmap	Build phases and exit criteria
Decisions	Decision log
Open questions	What still needs deciding
Landscape	Existing tools and why they don't cover this
Research: Vibe Kanban	How Vibe Kanban drives Claude Code, and what it means for Vantage

The A2V plugin in plugin/a2v/ packages the method for any project: a communication rule, an output style, and the skills explain-top-down, prove-it, record-decision, handoff, land-the-day, answer-review, close-the-loop and plan-task. Install it with /plugin marketplace add ymatrix1/vantage, then /plugin install a2v@vantage.

Agent instructions: AGENTS.md (canonical), rules in .agents/rules/, skills in .agents/skills/. Tasks are tracked with beans in .beans/.

Vantage

Documents

Yorumlar (0)