finesse-validate-execute

A command that checks whether Finesse's execution setup is correctly structured and working. It validates files, hooks, commands, scripts, state handling, and functional behavior.

In plain words
What is it for?
Use it to verify the setup script, stop hook, hook registration, command definitions, and related execution tests.
Why use it?
It catches missing files, invalid configuration, syntax errors, inconsistent paths, and broken execution behavior before the setup is relied on.

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-validate-execute
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.

Per session 14 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 470 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 $0.00014 $0.00470
Opus 5 $0.00007 $0.00235
Sonnet 5 $0.00003 $0.00094
Haiku 4.5 $0.00001 $0.00047

Measured 2d ago against content hash 6eb45074d572, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

finesse-validate-execute 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 2d 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-validate-execute.md · 57 lines

What it actually says

Finesse Validate Execute

Run the validation suite for the Finesse execution layer. This checks structural integrity and runs functional tests against the setup script, stop hook, hook registration, and command definitions.

Execute the validator:

python3 "${CLAUDE_PLUGIN_ROOT}/scripts/validate_execute.py"

What It Checks

Structural Checks

  • All required files exist (scripts, hooks, commands)
  • Python files compile without syntax errors
  • hooks.json is valid JSON with correct Stop hook structure
  • Command markdown files have correct YAML frontmatter
  • Python scripts use only stdlib modules (no external dependencies)
  • State file path is consistent between setup script and stop hook
  • Run log path is consistent between setup script and stop hook

Functional Tests

  • Setup script creates state file with correct YAML frontmatter
  • Setup script creates run-log.json with git hash and timestamps
  • Setup script rejects double-start (existing loop active)
  • Setup script rejects empty prompt
  • Setup script rejects missing prompt file
  • Setup script accepts inline prompt text
  • Stop hook blocks exit and re-feeds prompt when no promise match
  • Stop hook increments iteration counter
  • Stop hook writes per-iteration telemetry
  • Stop hook detects promise match and allows exit
  • Stop hook removes state file on completion
  • Stop hook marks telemetry as completed on promise match
  • Stop hook stops at max iterations
  • Stop hook marks telemetry as max_iterations
  • Stop hook is a no-op when no state file exists

Interpreting Results

  • PASS: Check passed.
  • FAIL: Check failed. Detail explains what went wrong.
  • WARN: Non-blocking issue worth noting.

Exit code 0 means all checks pass. Exit code 1 means at least one check failed.

When to Run

  • After modifying any file in scripts/, hooks/, or the execute-related commands
  • Before committing changes to the execution layer
  • After cloning the repo on a new machine to verify Python 3 compatibility
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. 2d ago First seen · 57 lines · 14 tokens per session scan A 6eb45074d572

Subscribe to this mod's changes

finesse-validate-execute is a command published in the GitHub repository jonathanung/finesse (4 stars, last pushed 6mo ago), licensed MIT. It adds 14 tokens to every session and 470 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.