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 skills add sloemo01/hermes-skills-bundle --skill interactive-prompt-analyzergit clone --depth 1 https://github.com/sloemo01/hermes-skills-bundleWrote 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/sloemo01/hermes-skills-bundle/interactive-prompt-analyzer)<a href="https://agentmods.dev/skills/sloemo01/hermes-skills-bundle/interactive-prompt-analyzer"><img src="https://agentmods.dev/badge/skills/sloemo01/hermes-skills-bundle/interactive-prompt-analyzer/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/skills/sloemo01/hermes-skills-bundle/interactive-prompt-analyzer"><img src="https://agentmods.dev/badge/skills/sloemo01/hermes-skills-bundle/interactive-prompt-analyzer.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 | $0.00049 | $0.05314 |
| Opus 5 | $0.00024 | $0.02657 |
| Sonnet 5 | $0.00010 | $0.01063 |
| Haiku 4.5 | $0.00005 | $0.00531 |
Grade A, and why
interactive-prompt-analyzer 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 9d 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 — 497 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Interactive Prompt Analyzer v3 — The Ultimate Prompt Intelligence Engine
Mission: Transform any input — text, code, images, files, URLs, voice transcripts — into optimal execution plans with predictive intelligence, self-improving learning, and autonomous optimization. The only prompt analyzer that gets better every time you use it.
🏗️ Architecture: 7-Layer Intelligence Stack
┌─────────────────────────────────────────────────────────────────────────────┐
│ LAYER 7: AUTONOMOUS OPTIMIZATION LAYER │
│ • Self-rewriting prompts for clarity/specificity │
│ • Adversarial stress-testing against 100+ edge cases │
│ • A/B testing framework for option presentation │
│ • Continuous prompt compression for token efficiency │
└─────────────────────────────────────────────────────────────────────────────┘
▲
┌─────────────────────────────────────────────────────────────────────────────┐
│ LAYER 6: CROSS-SESSION LEARNING ENGINE │
│ • Persistent user model across sessions (preferences, patterns, styles) │
│ • Few-shot adaptation from 3-5 interactions │
│ • Preference drift detection & re-calibration │
│ • Collaborative filtering: "Users like you chose..." │
└─────────────────────────────────────────────────────────────────────────────┘
▲
┌─────────────────────────────────────────────────────────────────────────────┐
│ LAYER 5: COUNTERFACTUAL & PREDICTIVE REASONING │
│ • "What if I chose Option B?" — full simulation │
│ • Regret minimization: "You'll regret not doing X because..." │
│ • Monte Carlo outcome simulation (1000+ runs) │
│ • Regret bounds: "95% confidence you won't regret Option A" │
└─────────────────────────────────────────────────────────────────────────────┘
▲
┌─────────────────────────────────────────────────────────────────────────────┐
│ LAYER 4: REAL-TIME COST/QUALITY/LATENCY ESTIMATION │
│ • Token estimation per option (±5% accuracy) │
│ • Wall-clock time prediction (±15%) │
│ • Dollar cost estimation (API + compute) │
│ • Quality prediction: "Option A: 92% completeness, 8% hallucination risk"│
│ • Pareto frontier visualization │
└─────────────────────────────────────────────────────────────────────────────┘
▲
┌─────────────────────────────────────────────────────────────────────────────┐
│ LAYER 3: CONTEXT-AWARE SKILL CHAINING & ORCHESTRATION │
│ • Multi-skill pipelines with data dependencies │
│ • Dynamic skill composition: "Research → Analyze → Synthesize → Act" │
│ • Parallel execution planning with dependency graphs │
│ • Fallback chains: "If Skill A fails, try Skill B → C" │
│ • Resource-aware scheduling (rate limits, quotas, concurrency) │
└─────────────────────────────────────────────────────────────────────────────┘
▲
┌─────────────────────────────────────────────────────────────────────────────┐
│ LAYER 2: PREDICTIVE AMBIGUITY DETECTION & MULTI-MODAL UNDERSTANDING │
│ • Predict ambiguities BEFORE user realizes them │
│ • Multi-modal: text + code + images + files + URLs + voice transcripts │
│ • Semantic + pragmatic + discourse analysis │
│ • Implicit intent mining: "What they need but didn't ask" │
│ • Domain-specific analyzers (coding, research, writing, analysis, ops) │
└─────────────────────────────────────────────────────────────────────────────┘
▲
┌─────────────────────────────────────────────────────────────────────────────┐
│ LAYER 1: DEEP SEMANTIC & PRAGMATIC ANALYSIS │
│ • Entity/relation extraction (spaCy + custom NER) │
│ • Speech act classification (request, question, command, exploration) │
│ • Goal hierarchy extraction (terminal vs instrumental goals) │
│ • Constraint taxonomy: hard/soft, temporal, resource, quality, ethical │
│ • Stakeholder mapping (who's affected, who decides, who implements Constraint satisfaction)│
└─────────────────────────────────────────────────────────────────────────────┘
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.
- 9d ago First seen · 497 lines · 49 tokens per session scan A 3a82576f916c
interactive-prompt-analyzer is a skill published in the GitHub repository sloemo01/hermes-skills-bundle (9 stars, last pushed 1mo ago), licensed MIT. It adds 49 tokens to every session and 5,314 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
hunt-llm-ai
Hunt LLM/AI feature bugs — prompt injection, indirect injection, exfiltration viatool-use/markdown, ASCII smuggling, agentic AI security (OWASP Agentic Apps 2026, ASI01-ASI10). Patterns: direct injection ('ignore previous instructions'), indirect injection via documents/web pages/email the model reads, ASCII smuggling…
lijigang-skill
A Chinese-language approach to writing precise, highly structured prompts, sometimes using Lisp-like notation. It combines concise wording, philosophical questioning, and a process for defining roles, conditions, output formats, and revisions.
baoyu-skill
A Chinese-language approach to explaining AI tools and writing prompts—instructions that tell an AI what you want. It emphasizes step-by-step teaching, hands-on testing, plain-language technical explanations, and organized knowledge sharing.
prompt-enhancer
Use when the user asks to enhance, improve, refine, rewrite, strengthen, or validate a prompt, or says "make this prompt better". Returns a clearer, more specific, better structured version of the prompt without executing it, picking validation checks from the prompt's own context. Contexts include coding, research…
prompt-optimize-zh
A prompt review assistant that examines an AI instruction and returns problems, an improved version, and an explanation of the changes. A prompt is the text that tells an AI what to do.
guidance
Control LLM output with regex and grammars, guarantee valid JSON/XML/code generation, enforce structured formats, and build multi-step workflows with Guidance - Microsoft Research's constrained generation framework.