finesse-edit

finesse-edit is a command for coding agents from jonathanung/finesse. It costs 13 tokens per session (3,077 once invoked), scanned B, original, MIT.

A command for making targeted changes to an existing accepted Finesse plan and checking the revised plan again.

In plain words
What is it for?
Use it when requirements or decisions change after a plan has been accepted.
Why use it?
It avoids repeating the earlier planning work while ensuring edits still pass all six validation agents.

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-edit
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-edit

README.md
[![agentmods](https://agentmods.dev/badge/commands/jonathanung/finesse/finesse-edit.svg)](https://agentmods.dev/commands/jonathanung/finesse/finesse-edit)
Your own site
<a href="https://agentmods.dev/commands/jonathanung/finesse/finesse-edit"><img src="https://agentmods.dev/badge/commands/jonathanung/finesse/finesse-edit.svg" alt="Measured on agentmods" height="20"></a>
Per session 13 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 3,077 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. 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 $0.00013 $0.03077
Opus 5 $0.00006 $0.01538
Sonnet 5 $0.00003 $0.00615
Haiku 4.5 $0.00001 $0.00308

Measured 4d ago against content hash dda1626d7d75, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade B, and why

finesse-edit scanned grade B with 1 finding 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.

Asks the agent to reveal its instructionsmediumSystem prompt leakage

Directions to print, repeat or translate the system prompt extract configuration the operator did not intend to expose.

1. **Show full prompt first** — Display the entire prompt text, then re-ask for changes
plugins/finesse/commands/finesse-edit.md · 230 lines

How it starts

The opening of the file, as written. The whole thing — 230 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Finesse Edit — Plan Editor & Re-Validator

Edit an existing accepted plan by applying targeted changes, re-validating with all 6 agents, and re-saving on acceptance. This command skips exploration, discovery, architecture, and scope analysis — those outputs are already baked into the loaded plan.

Critical Rules — READ BEFORE ANYTHING ELSE

All identity rules (planning-only, never implement, plan mode, explore first, ask clarifications, file structure, scope-safety, baseline commit, allowed agents, write permissions, core philosophy) are defined in the planner-identity skill and injected by identity_hook.py before this command runs. Those rules are non-negotiable and not repeated here.

The following rules are specific to the /finesse-edit workflow:

  • NEVER re-run exploration, discovery, architecture design, or scope analysis. Those outputs are baked into the existing plan.
  • Make TARGETED edits to the existing prompt — do NOT rebuild from scratch.
  • All 6 validation agents MUST run on the edited plan. No shortcuts.
  • Maximum refinement cycles default to 5 (overridable via --max-refinements N).
  • Edit sessions do NOT create working files. They complete within a single context window.
  • The Task tool may ONLY launch these agent types: clarity-checker, completion-validator, scope-safety-reviewer, phase-structure-analyzer, failure-mode-auditor, goal-achievement-auditor.
  • This command reads from and writes to finesse-plans/.
  • The final deliverable is ALWAYS the /finesse:finesse-execute command using file references. After handling the user's acceptance option (execute, copy, or save), STOP.

Mandatory Workflow Checklist

Before calling ExitPlanMode, verify:

  1. Plan resolved and loaded (Step 2)
  2. Current plan presented to user (Step 3)
  3. Edit instructions collected (Step 3)
  4. Edits applied with diff summary generated (Step 4)
  5. Validation + pre-flight via plan-validator agent (Step 5)
  6. All CRITICAL and HIGH validation issues resolved (Step 5)

Read the full file on GitHub · 230 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 · 230 lines · 13 tokens per session scan B dda1626d7d75

Subscribe to this mod's changes

finesse-edit is a command published in the GitHub repository jonathanung/finesse (4 stars, last pushed 6mo ago), licensed MIT. It adds 13 tokens to every session and 3,077 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it B with 1 finding (asks the agent to reveal its instructions). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.