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.
npx agentmods add commands/connorrmcd6/vibe-spec/spec-setupgit clone --depth 1 https://github.com/Connorrmcd6/vibe-specWhat 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 | $0.00055 | $0.00721 |
| Opus 5 | $0.00028 | $0.00360 |
| Sonnet 5 | $0.00011 | $0.00144 |
| Haiku 4.5 | $0.00006 | $0.00072 |
Grade A, and why
spec-setup scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 56 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are running /spec-setup: a guided, confirm-each-step onboarding that
gets the user's machine ready by installing only the tools their project needs.
Consult the vibe-spec skill
(${CLAUDE_PLUGIN_ROOT}/skills/vibe-spec/reference/18-prerequisites.md) for the tool
list, detection commands, and OS-specific install methods.
Hard rules
- Never auto-install. Propose the exact command and wait for the user to confirm before running anything. If they decline, just print the command for them to run themselves.
- Never run
sudowithout surfacing it explicitly and getting confirmation. - Prefer user-space installers (Corepack for pnpm, fnm/nvm for Node, uv, Colima for Docker) over system-wide package changes.
- Handle one tool at a time, in dependency order.
- Skip tools that are already present — just note the version.
What to do
-
Consult
reference/18-prerequisites.md. -
Determine the required tool set (spec first):
- If
docs/project-spec.mdexists, read it and infer the needed tools from the features and the tool mappings written during/spec-refine:- any web app ⇒ Git, Node, pnpm
- Postgres / Prisma / a local database ⇒ Docker
- dbt / data pipelines / transforms ⇒ uv
- Git is always required
- Otherwise, use the
$ARGUMENTSproject type if given, else ask the user which it is (static / crud / api / data). Map it to references via the "what do I need?" table inSKILL.md, then to tools. - Tell the user the resolved tool set and why, before proceeding.
- If
-
Detect what's already installed (same checks as
/spec-doctor), scoped to the required set. Detect the OS first. For Docker, also check the daemon (docker info). -
For each MISSING tool, in dependency order (Git → Node → pnpm → Docker → uv):
- State what it's for and the recommended OS-specific install command from the reference (prefer Corepack for pnpm, fnm/nvm for Node).
- Ask the user to confirm before running it. On confirmation, run it; if they decline, print the command and move on.
- Re-run that tool's detection to verify it now works before continuing. If it
still fails, suggest
/spec-troubleshootand the reference's alternate install method.
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.
- 2d ago First seen · 56 lines · 55 tokens per session scan A 965b7158b92a
spec-setup is a command published in the GitHub repository Connorrmcd6/vibe-spec (9 stars, last pushed 1mo ago), licensed MIT. It adds 55 tokens to every session and 721 once invoked, about $0.0003 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.
Other commands, from other repositories
cleanup-repo
When /cleanup-repo is invoked, immediately execute the following steps to analyze, organize, and clean up the repository structure when files are scattered and disorganized.
devops
When /devops is invoked, immediately execute the following steps to create, configure, or manage DevOps infrastructure, CI/CD pipelines, and deployment configurations.
magic-wand
When /magic-wand [issue description] is invoked, immediately execute the following steps to perform a comprehensive, expert-level analysis and fix when standard debugging approaches have failed.
audit-code
When /audit-code [target] is invoked, immediately execute the following steps to analyze code quality, security, and adherence to project standards.
brainstorm
When /brainstorm [topic] is invoked, immediately execute the following steps to collaboratively brainstorm, enhance, and plan new features for the app through an iterative product management workflow.
clean-code
When /clean-code [target] is invoked, immediately execute the following steps to remove redundant code, unused variables, dead code, debug statements, and other technical debt.