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 commands/jonathanung/finesse/finesse-helpgit 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/commands/jonathanung/finesse/finesse-help)<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>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 | $0.00008 | $0.04208 |
| Opus 5 | $0.00004 | $0.02104 |
| Sonnet 5 | $0.00002 | $0.00842 |
| Haiku 4.5 | $0.00001 | $0.00421 |
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.
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
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 · 353 lines · 8 tokens per session scan A b7d9c1e9b95f
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.
Other commands, from other repositories
git
Git operations with intelligent commit messages and workflow optimization.
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.