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-wavesgit 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-waves)<a href="https://agentmods.dev/commands/jonathanung/finesse/finesse-waves"><img src="https://agentmods.dev/badge/commands/jonathanung/finesse/finesse-waves.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 | $0.00009 | $0.00640 |
| Opus 5 | $0.00005 | $0.00320 |
| Sonnet 5 | $0.00002 | $0.00128 |
| Haiku 4.5 | $0.00001 | $0.00064 |
Grade A, and why
finesse-waves 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 3d 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 — 73 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Finesse Waves
Wave execution orchestration for multi-workflow plans. Launches parallel sub-workflows in isolated git worktrees via tmux, monitors completion, and handles merge reconciliation.
This command executes the waves orchestrator directly via Bash.
Determine Plugin Root
The plugin root is the directory containing this command file. Resolve it from ${CLAUDE_PLUGIN_ROOT} or by navigating from this file's location to the parent plugins/finesse/ directory.
Parse Subcommand
Parse $ARGUMENTS for the subcommand and optional session name.
If no arguments or empty $ARGUMENTS:
Show usage help:
Finesse Waves — Wave execution orchestration
Subcommands:
start <session-name> Parse execution-graph.md, show dry-run, launch waves
status Show status of all active wave sessions
attach <session-name> Attach to tmux session for observation
stop <session-name> Gracefully stop a wave session
cleanup <session-name> Remove worktrees and tmux sessions
merge <session-name> Manually trigger merge reconciliation
Usage:
/finesse-waves start my-api-project
/finesse-waves status
/finesse-waves attach my-api-project
If subcommand is recognized:
Execute the waves orchestrator directly via Bash. For the start subcommand, always pass --yes to skip the interactive confirmation prompt (since stdin piping does not work reliably from within Claude Code):
python3 "${CLAUDE_PLUGIN_ROOT}/scripts/finesse_waves.py" start --yes <session-name>
For other subcommands (status, stop, cleanup, merge, attach):
python3 "${CLAUDE_PLUGIN_ROOT}/scripts/finesse_waves.py" <subcommand> <session-name>
Where <subcommand> and <session-name> are taken from $ARGUMENTS.
Prerequisites
Before starting wave execution, ensure:
- A multi-workflow plan exists at
finesse-plans/<session-name>/execution-graph.md tmuxis installed and availablegitworktree support is available (Git 2.5+)claudeCLI is accessible from the terminal
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.
- 3d ago First seen · 73 lines · 9 tokens per session scan A c4aced4f583f
finesse-waves is a command published in the GitHub repository jonathanung/finesse (4 stars, last pushed 6mo ago), licensed MIT. It adds 9 tokens to every session and 640 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.