init

A setup process for adding Prospero, a blog-writing workflow, to a project. It detects the site's publishing system and creates the project's configuration, writing-voice, and audience files.

In plain words
What is it for?
Use it to initialize or reconfigure Prospero, choose a publishing preset, and create missing voice and audience templates.
Why use it?
Writing tools need to know where content belongs and who it is for. This setup provides that context and avoids starting later stages with missing configuration.

Skill for Claude CodeCodex

Install

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.

agentmods
npx agentmods add skills/bguthrie/prospero/init
Any agent
npx skills add bguthrie/prospero --skill init
Clone the repo
git clone --depth 1 https://github.com/bguthrie/prospero

Made for: Claude Code, Codex.

Per session 49 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,226 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00049 $0.02226
Opus 5 $0.00024 $0.01113
Sonnet 5 $0.00010 $0.00445
Haiku 4.5 $0.00005 $0.00223

Measured 2d ago against content hash 594ac38641c0, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

init 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.

skills/init/SKILL.md · 146 lines

How it starts

The opening of the file, as written. The whole thing — 146 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Init

Set up Prospero in the current project. Idempotent: safe to re-run for reconfiguration. Never overwrites user-modified content in .prospero/voice.md or .prospero/audience.md. A file whose contents are byte-identical to the plugin's template is treated as an unfilled scaffold and is safe to recopy.

When to use

  • Auto-invoked by /interrogate (and any other phase skill) when .prospero/config.toml is absent.
  • Invoked directly via /init when the user wants to change the preset or recopy a missing template file.

Do not invoke any other phase skill from here. Scaffold, confirm, report. Then return control.

Process

You MUST complete each step in order. Do not write any files before the user has confirmed at step 4.

1. Scan for CMS markers

Look in the current working directory (the project root) for the files below. Read each candidate file — do not decide by filename alone.

  • hugo.toml, hugo.yaml, hugo.json → Hugo. Also check for a top-level config.toml/config.yaml that contains Hugo-specific keys (baseURL, theme, [params], [markup]).
  • _config.yml with Jekyll markers (collections:, permalink:, plugins: referencing jekyll-*, or a _posts/ directory nearby) → Jekyll.
  • package.json whose dependencies or devDependencies include ghost, @tryghost/*, or a Ghost-specific build tool → Ghost.
  • None of the above, or ambiguous markers → plain.

Also note whether the implied content directory exists (content/post/ for Hugo, _posts/ for Jekyll, etc.). A matching config plus a matching content directory is strong evidence. A config alone with no content directory is still enough to propose the preset, but mention the missing directory in the proposal so the user can correct course.

If two CMS markers appear to be present (e.g., a Hugo hugo.toml and a Jekyll _config.yml), do not guess. Ask the user which is canonical.

2. Inspect existing .prospero/ files

Before proposing anything, classify the state of each target path so the proposal at step 3 can be accurate. For each of .prospero/config.toml, .prospero/voice.md, .prospero/audience.md, classify as one of:

Read the full file on GitHub · 146 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. 2d ago First seen · 146 lines · 49 tokens per session scan A 594ac38641c0

Subscribe to this mod's changes

init is a skill published in the GitHub repository bguthrie/prospero (6 stars, last pushed 3mo ago), licensed MIT. It adds 49 tokens to every session and 2,226 once invoked, about $0.0002 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

autoreview

Pre-commit/ship code review: Codex default; optional Claude or Pi.

openclaw/clawhub · 20 tokens

babysit

Same-session monitoring loop for PRs, CI runs, tickets, and deployments using the monitorstart / monitorupdate / autonudgestop MCP tools. The loop re-injects your check instructions into THIS session on an idle interval — same context, same tools — and works from dashboard chat, Slack threads, and Discord DMs. Use…

kirodotdev/KiroCrew · 137 tokens

convex

Convex is the backend agents get right on the first try: an all-TypeScript reactive platform where the database, server functions, scheduling, file storage, auth, and realtime sync are one type-safe system, every function is a transaction, and tsc catches most mistakes before deploy. Ideal BOTH for a quick prototype…

openclaw/clawhub · 202 tokens

convex-insights

Query a running Convex app's logs + health in natural language (official MCP): failures, slow/expensive functions, deploy causality — scoped, evidence-backed, with a dashboard deep link.

openclaw/clawhub · 45 tokens

openclaw-design-system

Compatibility alias for existing OpenClaw installations that now applies Carapace semantic tokens, themes, shared CSS foundations, consumer adapters, and established local primitives.

openclaw/clawhub · 37 tokens

happiness-skill

当用户问「怎么才能更幸福/为什么得到了还不满足/怎么减少焦虑」时调用。 核心理念: 幸福是缺憾感清空的默认状态, 是可训练的技能; 欲望是与自己的契约(得到前不快乐), 同时只留一个重大欲望; 活在当下。 不适用于: 临床抑郁等需要专业治疗的场景(本书方法不能替代医疗)。 Triggers: 幸福/不快乐/欲望/焦虑/知足/活在当下/happiness/desire/anxiety.

kangarooking/cangjie-skill · 136 tokens