vision

vision is a skill for Claude Code from rjroy/vibe-garden. It costs 78 tokens per session (550 once invoked), scanned A, original, MIT.

A project-direction guide that defines why a project exists, whom it serves, and what it should or should not become.

In plain words
What is it for?
Use it at the start of a project or when its direction is uncertain. It can create or review a vision document based on the codebase and the team’s answers.
Why use it?
It gives teams a shared reference when requirements are unclear or different choices pull the project in different directions.

Skill for Claude Code

Written for Claude Code: ${CLAUDE_PLUGIN_ROOT} variable. Also seen: mentions CLAUDE.md.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the lore-development plugin — 12 skills, 1 agent shipped together

Good fit Use it at the start of a project or when its direction is uncertain. It can create or review a vision document based on the codebase and the team’s answers.

Compare 6 skills from other repositories ↓
Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add rjroy/vibe-garden
Claude Code
/plugin install lore-development

Made for: Claude Code.

Or install lore-development, the plugin that ships this one along with the rest of its 12 skills, 1 agent.

Wrote 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.

agentmods badge for vision

README.md
[![agentmods](https://agentmods.dev/badge/skills/rjroy/vibe-garden/vision.svg)](https://agentmods.dev/skills/rjroy/vibe-garden/vision)
Your own site
<a href="https://agentmods.dev/skills/rjroy/vibe-garden/vision"><img src="https://agentmods.dev/badge/skills/rjroy/vibe-garden/vision.svg" alt="Measured on agentmods" height="20"></a>
Per session 78 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 550 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00078 $0.00550
Opus 5 $0.00039 $0.00275
Sonnet 5 $0.00016 $0.00110
Haiku 4.5 $0.00008 $0.00055

Measured 8d ago against content hash 047b554ddf24, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

vision 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 8d ago.

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.

lore-development/skills/vision/SKILL.md · 40 lines

How it starts

The opening of the file, as written. The whole thing — 40 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Vision

The vision is the north star. It doesn't define requirements or validate behavior — it tells you whether a decision is keeping with the spirit of the project or going against it.

If .lore/reference/vision.md already exists, load it and offer to review or revise.

Two Paths

Existing codebase: Read broadly first — source code, .lore/ artifacts, CLAUDE.md, README. Look for implicit values: what gets built, what gets rejected, what wins when things conflict. Draft from evidence. Where it's ambiguous, say so rather than inventing coherence.

New project: Walk through questions to pull the vision out. Adapt based on responses.

  1. What is this project? Who does it serve? What problem does it solve that isn't solved elsewhere?
  2. What matters most? If you had to name three things this project should always be, what are they?
  3. What should this project never become? What reasonable-sounding ideas would you reject on principle?
  4. Where do your values pull in opposite directions? When one conflicts with another, which wins by default?

Synthesize the user's own words into the document — don't replace their vocabulary with yours.

Refinement

The first draft is a conversation starter. Probe:

  • "Does this principle describe how you actually make decisions, or is it aspirational?"
  • "Are these anti-goals things you'd genuinely reject, or just things you haven't prioritized yet?"

Principles should be behavioral guidelines, not trait aspirations. "We build for simplicity" is a trait. "Every new feature must justify the complexity it adds" is a guideline.

When the document has been reviewed at least once, offer to save. The user can keep refining or defer.

Saving

Save to .lore/reference/vision.md. Load ${CLAUDE_PLUGIN_ROOT}/shared/frontmatter-schema.md for the frontmatter fields. Set status: draft — the user marks it approved. The document body is freeform: what the project is, what it values, what it refuses.

Write the body Markdown-first per the "Body Format" section of ${CLAUDE_PLUGIN_ROOT}/shared/frontmatter-schema.md. Reach for embedded inline HTML only when a visual genuinely clarifies the north star.

Read the full file on GitHub · 40 lines

Changes

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.

  1. 8d ago First seen · 40 lines · 78 tokens per session scan A 047b554ddf24

Subscribe to this mod's changes

vision is a skill published in the GitHub repository rjroy/vibe-garden (6 stars, last pushed 2mo ago), licensed MIT. It adds 78 tokens to every session and 550 once invoked, about $0.0004 per session on Opus 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 2026-08-31.

Related

Other skills, from other repositories

init-rpm

Project setup and verification. First run creates rpm context for a project. Repeat runs verify that an existing rpm setup matches the latest expected layout and apply safe migrations.

dppdppd/rpm · 48 tokens

backlog

Manage the rpm backlog (long-term project tasks in docs/rpm/future/tasks.org — distinct from Claude's native TaskCreate list, which is session-scoped). Add, list, review, postpone, or complete entries. TRIGGER on natural-language backlog operations — phrasings like "backlog X", "add X to backlog", "add to backlog"…

dppdppd/rpm · 156 tokens

version

Report the installed rpm plugin version. Use when the user asks for the rpm version, plugin version, installed version, or wants to verify which rpm release is loaded.

dppdppd/rpm · 35 tokens

recursive-spine-digest

Use when sweeping all recursive-spine-conforming repos for tracking health — aging deferrals (oldest first), stalled milestones, in-flight by lane, assigned-but-untouched issues, and debts named in closing comments but never filed, plus seedling pollen that never transplanted (hive repos). Reports honest denominators…

slopstopper/recursive-spine · 82 tokens

recursive-spine-scaffold

Use when a repo has (or is getting) the tracking stamp and needs the rest of its spine — interviews for and stamps up to six parts, each optional: a rules codex with a moments map, an ADR directory, a CI gate skeleton, a session-memory convention, a constraints file with its sha-pinned drift gate, and the loop…

slopstopper/recursive-spine · 0 tokens

recursive-spine-bootstrap

Use when installing the recursive-spine tracking convention onto a repo — interviews for modules and dialect, then stamps labels, issue/PR templates, a CLAUDE.md/AGENTS.md tracking section, and cross-project board membership. Idempotent; degrades loudly on missing gh scopes; offers (never forces) plumb-line and…

slopstopper/recursive-spine · 76 tokens