finesse-help

finesse-help is a command for coding agents from jonathanung/finesse. It costs 8 tokens per session (4,208 once invoked), scanned A, original, MIT.

A help command that explains the Finesse planning tool and lists its available commands and task-specific workflows.

In plain words
What is it for?
Use it when you need to understand Finesse, its commands, or the steps used for features, bugs, refactors, testing, and performance work.
Why use it?
It gives new users an overview of what Finesse does, what it does not do, and how planning proceeds for different task types.

Command

Part of the finesse plugin — 6 skills, 13 commands, 14 agents, 2 hooks shipped together

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 commands/jonathanung/finesse/finesse-help
Clone the repo
git clone --depth 1 https://github.com/jonathanung/finesse

Or install finesse, the plugin that ships this one along with the rest of its 6 skills, 13 commands, 14 agents, 2 hooks.

Wrote 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.

agentmods badge for finesse-help

README.md
[![agentmods](https://agentmods.dev/badge/commands/jonathanung/finesse/finesse-help.svg)](https://agentmods.dev/commands/jonathanung/finesse/finesse-help)
Your own site
<a href="https://agentmods.dev/commands/jonathanung/finesse/finesse-help"><img src="https://agentmods.dev/badge/commands/jonathanung/finesse/finesse-help.svg" alt="Measured on agentmods" height="20"></a>
Per session 8 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 4,208 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 $0.00008 $0.04208
Opus 5 $0.00004 $0.02104
Sonnet 5 $0.00002 $0.00842
Haiku 4.5 $0.00001 $0.00421

Measured 4d ago against content hash b7d9c1e9b95f, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

finesse-help 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.

plugins/finesse/commands/finesse-help.md · 353 lines

How it starts

The opening of the file, as written. The whole thing — 353 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Finesse Plugin Help

Please explain the following to the user:

What is Finesse?

Finesse is a planning and validation tool that transforms vague task descriptions into battle-tested ralph-loop prompts. It does NOT run loops — it plans, validates, and hands off a ready-to-run command.

Finesse automatically detects your task type and runs a tailored workflow:

Task Type Workflow
Feature Discovery (deep) → Codebase Exploration [UAT] → Scope Analysis [UAT] → Clarifying Questions → Architecture Design [UAT] → Plan Construction [UAT] → Validate → Present
Bug Fix Bug Understanding (deep) → Codebase Investigation [UAT] → Scope Analysis [UAT] → Root Cause Analysis [UAT] → Fix Strategy [UAT] → Plan → Validate → Present
Refactor Scope Definition (deep) → Current State Analysis [UAT] → Scope Analysis [UAT] → Target State Design [UAT] → Migration Strategy [UAT] → Plan → Validate → Present
Testing Coverage Analysis [UAT] → Scope Analysis [UAT] → Test Strategy [UAT] → Clarifying Questions → Plan → Validate → Present
Performance Problem Definition (deep) → Profiling & Analysis [UAT] → Scope Analysis [UAT] → Optimization Strategy [UAT] → Plan → Validate → Present
Research Goal Definition (deep) → Source Identification [UAT] → Scope Analysis [UAT] → Research Plan [UAT] → Investigation Strategy [UAT] → Plan → Validate → Present

(deep) = thorough probing phase with iterative back-and-forth. [UAT] = User Acceptance Testing checkpoint (see below).

Available Commands

/finesse [--max-refinements N]

Plan a ralph-loop prompt for any development task.

Arguments:

  • TASK — What you want to do (can be vague — Finesse will clarify)
  • --max-refinements N — Max planning refinement cycles (default: 5). This is Finesse's planning budget, NOT the ralph-loop iteration count.

Usage:

/finesse Build a REST API for managing todos with auth
/finesse Fix the token refresh bug in auth.ts
/finesse Refactor the database layer to use repository pattern
/finesse Add integration tests for the payments module
/finesse Optimize the search endpoint — it's taking 3+ seconds
/finesse Research whether we should use Redis or Memcached for caching
/finesse Investigate the trade-offs between REST and GraphQL for our API

Read the full file on GitHub · 353 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. 4d ago First seen · 353 lines · 8 tokens per session scan A b7d9c1e9b95f

Subscribe to this mod's changes

finesse-help is a command published in the GitHub repository jonathanung/finesse (4 stars, last pushed 6mo ago), licensed MIT. It adds 8 tokens to every session and 4,208 once invoked, about $0.0000 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.