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 skills/bguthrie/prospero/prosperonpx skills add bguthrie/prospero --skill prosperogit clone --depth 1 https://github.com/bguthrie/prosperoWrote 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/skills/bguthrie/prospero/prospero)<a href="https://agentmods.dev/skills/bguthrie/prospero/prospero"><img src="https://agentmods.dev/badge/skills/bguthrie/prospero/prospero.svg" alt="Measured on agentmods" 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 | $0.00043 | $0.01163 |
| Opus 5 | $0.00022 | $0.00581 |
| Sonnet 5 | $0.00009 | $0.00233 |
| Haiku 4.5 | $0.00004 | $0.00116 |
Grade A, and why
prospero 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 5d 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 — 68 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Prospero
Prospero is a dialectical pipeline for writing blog posts: interrogation into an outline, oppositional critique, voice-calibrated authoring, and line-level revision. This skill is the router — it reads the user's intent and the current project state, picks one phase skill to invoke, and hands off. It does not chain phases or duplicate their preflight logic.
When to use
Invoke this skill when the user's message expresses intent to produce or work on a blog post, without naming a specific phase. Typical phrasings:
- "Help me write a post about X."
- "I want to outline a piece on Y."
- "Can you review this outline?"
- "Draft the post from the outline."
- "I've edited the draft — give me feedback."
- "Let's work on a blog post."
If the user invoked a specific phase directly via /interrogate, /critique, /author, or /revise, do not invoke this skill — that phase skill is already running.
When NOT to use
- The user asks an edit-level question about a single sentence or paragraph in an existing draft → invoke
/revisedirectly. - The user asks how Prospero works, what a phase does, or wants to inspect configuration → answer the question; do not route.
- The user is working on non-blog content (documentation, email, README, code comments) → do not route. Prospero is scoped to blog posts.
Routing logic
Pick exactly one phase skill based on what the user has and what they are asking for.
-
Topic or raw idea, no outline yet →
/interrogate. The first phase extracts the argumentative spine through Socratic questioning and writes the outline artifact. This is the entry point for any post that does not yet have an outline on disk. -
Outline exists at
<drafts_dir>/<slug>/outline.mdand the user wants adversarial review →/critique. Critique is an independent, oppositional reader; routing here before drafting is how the pipeline stress-tests the argument. -
Outline exists (usually reviewed) and the user says "draft it" or equivalent →
/author. The author reads the outline, voice, audience, and sample posts, then writes the post at the resolvedpost_path_pattern.
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.
- 5d ago First seen · 68 lines · 43 tokens per session scan A 236202dd4b39
prospero is a skill published in the GitHub repository bguthrie/prospero (6 stars, last pushed 4mo ago), licensed MIT. It adds 43 tokens to every session and 1,163 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.
Other skills, from other repositories
edgeone skill scanner
Scan any agent skill for security risks before you install or use it. Powered by Tencent Zhuque Lab A.I.G (AI-Infra-Guard). 100% local static analysis — no file contents or credentials leave your device. Compatible with CodeBuddy, Cursor, Windsurf, Claude Code, OpenClaw and more. Triggers on: 这个 skill 安全吗, skill 安全扫描…
autoreview
Pre-commit/ship code review: Codex default; optional Claude or Pi.
convex-billing
Add Stripe billing/payments to the Convex app via @convex-dev/stripe (checkout + webhook + gating).
dev-workflow
The complete development workflow for SkillHub contributors including local dev, staging validation, testing, and PR creation. Ensures agents follow the correct sequence of steps.
convex-performance-audit
Audits Convex performance for reads, subscriptions, write contention, and function limits. Use for slow features, insights findings, OCC conflicts, or read amplification.
video-frames
Extract a single frame from a local video at the first frame, a timestamp, or a zero-based frame index using FFmpeg.