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/jonathanung/finesse/prompt-validationnpx skills add jonathanung/finesse --skill prompt-validationgit clone --depth 1 https://github.com/jonathanung/finesseWrote 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/jonathanung/finesse/prompt-validation)<a href="https://agentmods.dev/skills/jonathanung/finesse/prompt-validation"><img src="https://agentmods.dev/badge/skills/jonathanung/finesse/prompt-validation.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 | $0.00012 | $0.01631 |
| Opus 5 | $0.00006 | $0.00816 |
| Sonnet 5 | $0.00002 | $0.00326 |
| Haiku 4.5 | $0.00001 | $0.00163 |
Grade A, and why
prompt-validation 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 4d 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 — 104 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Prompt Validation Orchestration
During a Finesse planning session, you MUST validate every drafted plan before presenting it to the user. This is a non-negotiable gate. This document describes the full 6-validator workflow used by /finesse, /finesse-resume, /finesse-edit, and /finesse-retro. /finesse-mini uses a reduced 3-validator workflow with its own verdict handling rules defined in finesse-mini.md.
Validation Workflow
Step 1: Launch All Validators in Parallel
Use the Task tool to launch ALL SIX agents simultaneously in a single message. Pass the full drafted plan text to each agent in their prompt:
- clarity-checker — Are requirements specific enough for an autonomous agent with no ability to ask questions?
- completion-validator — Are completion criteria binary, explicit, and unambiguous?
- scope-safety-reviewer — Are scope constraints, guardrails, and safety measures in place?
- phase-structure-analyzer — Are phases ordered with verification commands and a cold start paragraph?
- failure-mode-auditor — Are stuck-state recovery, anti-thrashing rules, and failure handling present?
- goal-achievement-auditor — Does the prompt actually achieve the stated goal? Are all observable truths covered by phases and verified by completion criteria?
Each agent returns a verdict: PASS, FAIL, or NEEDS_REWORK.
Severity Tiers
Each verdict is classified into a severity tier based on the agent and verdict type:
| Tier | Condition | Behavior |
|---|---|---|
| CRITICAL | scope-safety-reviewer returns FAIL |
Blocks presentation unconditionally. Must fix before presenting. |
| HIGH | clarity-checker, phase-structure-analyzer, or completion-validator returns FAIL |
Blocks presentation. Must fix before presenting. |
| MEDIUM | goal-achievement-auditor or failure-mode-auditor returns FAIL |
Should fix within refinement budget. Can present with explicit warnings if budget exhausted. |
| LOW | Any agent returns NEEDS_REWORK |
Fix if budget allows after higher tiers resolved. |
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.
- 4d ago First seen · 104 lines · 12 tokens per session scan A 78727e9c081c
prompt-validation is a skill published in the GitHub repository jonathanung/finesse (4 stars, last pushed 6mo ago), licensed MIT. It adds 12 tokens to every session and 1,631 once invoked, about $0.0001 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
llm-app-patterns
Production-ready patterns for building LLM applications. Covers RAG pipelines, agent architectures, prompt IDEs, and LLMOps monitoring. Use when designing AI applications, implementing RAG, building agents, or setting up LLM observability.
enhance-prompt
Transforms vague UI ideas into polished, Stitch-optimized prompts. Enhances specificity, adds UI/UX keywords, injects design system context, and structures output for better generation results.
prompt-optimization
Improve a prompt on the evaluations workbench through a measured loop. Score the baseline first, then duplicate the target column, form a hypothesis from failing rows, edit the copy's prompt draft, run, compare pass rate and cost, and repeat until the numbers hold. Use when the user asks to optimize or improve a…
prompt-engineer
Writes, refactors, and evaluates prompts for LLMs — generating optimized prompt templates, structured output schemas, evaluation rubrics, and test suites. Use when designing prompts for new LLM applications, refactoring existing prompts for better accuracy or token efficiency, implementing chain-of-thought or few-shot…
ideogram4
Prompting patterns for Ideogram 4 text-to-image — best-in-class in-image text rendering and exact color/layout control via structured JSON captions. Use when generating images that need legible on-image text (title cards, thumbnails, logos, signage, CTAs), precise brand colors, or controlled spatial layout. Triggers…
omh-model-optimization
This is a Hermes-native model-optimization workflow skill.