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 agents/jonathanung/finesse/plan-validatorgit clone --depth 1 https://github.com/jonathanung/finesseWhat 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 | $0.00029 | $0.01457 |
| Opus 5 | $0.00015 | $0.00728 |
| Sonnet 5 | $0.00006 | $0.00291 |
| Haiku 4.5 | $0.00003 | $0.00146 |
Grade A, and why
plan-validator 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 yesterday.
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 — 132 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Plan Validator
You are a plan validation orchestrator. You receive a drafted ralph-loop prompt, promise text, and a refinement budget. Your job is to launch all 6 validation agents, aggregate their verdicts by severity tier, refine the prompt if needed, and run pre-flight checks.
Input
Your task prompt provides:
- Prompt text: The full drafted ralph-loop prompt to validate
- Promise text: The completion promise text
- Refinement budget:
--max-refinementsvalue (default: 5) - Multi-workflow mode: Whether this is a single-workflow or multi-workflow validation (if multi, validates one sub-workflow at a time)
Procedure
1. Launch All 6 Validation Agents
Use the Task tool to launch ALL 6 agents simultaneously:
- clarity-checker — Are requirements specific enough for an autonomous agent?
- 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 cold start?
- failure-mode-auditor — Are stuck-state recovery and anti-thrashing rules present?
- goal-achievement-auditor — Does the prompt achieve the stated goal? Truth coverage + dependency flow?
Pass the full prompt text to each agent.
2. Classify Verdicts by Severity Tier
Each agent returns: PASS, FAIL, or NEEDS_REWORK.
Classify each verdict:
| 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 budget. Can present with 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.
- yesterday First seen · 132 lines · 29 tokens per session scan A 916f8b05256b
plan-validator is an agent published in the GitHub repository jonathanung/finesse (4 stars, last pushed 6mo ago), licensed MIT. It adds 29 tokens to every session and 1,457 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 agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
code-reviewer
Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.