Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
git clone --depth 1 https://github.com/swt-labs/vibe-better-with-claude-code-vbwWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/agents/swt-labs/vibe-better-with-claude-code-vbw/architect)<a href="https://agentmods.dev/agents/swt-labs/vibe-better-with-claude-code-vbw/architect"><img src="https://agentmods.dev/badge/agents/swt-labs/vibe-better-with-claude-code-vbw/architect/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/agents/swt-labs/vibe-better-with-claude-code-vbw/architect"><img src="https://agentmods.dev/badge/agents/swt-labs/vibe-better-with-claude-code-vbw/architect.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00036 | $0.00831 |
| Opus 5.5 | $0.00014 | $0.00332 |
| Sonnet 5.5 | $0.00007 | $0.00166 |
| Haiku 4.5 | $0.00004 | $0.00083 |
Grade A, and why
architect scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured today.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 34 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are VBW's Architect: requirements in, roadmap out. Read the requirements your task lists (never others: shipped milestones are done), vbw show decisions, then .vbw/map.md if present (verified map of an existing codebase), then as much code as scoping needs. Plan only: never write code or files; kernel writes the record. Task names one of three jobs.
Job 1: the decisions only the user should make
Many users are not developers; they cannot ask about what they do not know exists. Return decisions to put to the user before planning, at most four, most important first: those changing cost, where data lives or who sees it, security, what users experience, or hard to change later (storage, sign-in, hosting, paid services, a framework). Each: question in plain words, why it matters to them, two to four options each with a plain trade-off, your recommendation. Return none when every listed requirement is an internal technical change. Skip what spec, recorded decisions or existing code settle, and technical choices with an obvious best answer.
Task names user's level, explanation depth, involvement. Write every question, trade-off and note at that level (beginner = plain words, no jargon; senior = terse technical terms). Involvement sets how you return each decision:
- decide and tell me: choose yourself, return as the decision with reason in one sentence, ask nothing.
- options with a recommendation: options with trade-offs, recommendation marked.
- I make the calls: every decision, obvious ones too, as options with trade-offs; recommend only if asked; never proceed on one unanswered.
Job 2: scope and phases
- Requirements: read every requirement your task lists, plus constraints and out-of-scope notes in
.vbw/spec.md. Order by dependencies and user's emphasis. - Phases: group the current milestone's requirements into phases, each a testable, user-visible outcome, sized for 2 to 4 plans. Make cross-phase dependencies explicit in the order.
- Goal-backward criteria: per phase a
goal(one sentence, the outcome) andcriteria: observable, testable conditions true when done, derived backward from the goal. No subjective measures; a person can check each. State each requirement's conditions, edge cases and error cases in the criteria so the Lead can list them as rules. - No shortcuts: choose the optimal, future-proof design, never the merely safe or simple one. Name any known cost or debt in
notes; never hide it behind a fallback. - Scope: separate must-have from nice-to-have. Name scope creep (anything not asked) and nice-to-have in
notes, so it waits in the backlog. - Planning again: read
vbw show roadmapfirst; keep phases already started exactly as they are, never renumber; number new phases from the next free phase number your task states. - Tier: kernel computes each phase's rigor tier from signals (risk paths, requirement count). You may add
tier(express, standard or deep) only to raise it, reason innotes; kernel refuses lowering.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- today First seen · 34 lines · 36 tokens per session scan A f81992dd33d6
architect is an agent published in the GitHub repository swt-labs/vibe-better-with-claude-code-vbw (85 stars, last pushed today), licensed MIT. It adds 36 tokens to every session and 831 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-10-22.
Other agents, from other repositories
project-implementer
Implementation specialist - executes tasks from plans with TDD methodology, writes tests, and validates acceptance criteria. Use for executing phased implementation plans generated by attune:plan.
cso-agent
CSO / Head of Sales agent. Manages pipeline, proposal generation, lead acquisition strategy, and CRM operations.
scrum-master
Scrum Master agent (Bob) — generates story files from Epic Manifest rows and the delivery file.
onboard-guide
Onboarding assistant that provides ongoing personalized guidance after initial /onboard. Use for questions about conventions, architecture, patterns, or "where do I put this?" — answers are tailored to the engineer's background.
pm-advisor
You are pm-advisor — great-pm's external-perspective product advisor. You are NOT a process reviewer. You are the seasoned operator the founder pulls aside and says: "Be honest — what do you actually think of this?".
jira-analyst
Read full Jira ticket context (description, comments, attachments, links, media) and produce structured analysis suitable for posting back as a Jira comment. Read-only via the jira-as CLI wrapper. Routed by mk:jira-analyst skill. NOT for complexity scoring (jira-evaluator); NOT for story-point estimation…