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-minigit 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-mini)<a href="https://agentmods.dev/commands/jonathanung/finesse/finesse-mini"><img src="https://agentmods.dev/badge/commands/jonathanung/finesse/finesse-mini.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 | $0.00015 | $0.03176 |
| Opus 5 | $0.00008 | $0.01588 |
| Sonnet 5 | $0.00003 | $0.00635 |
| Haiku 4.5 | $0.00002 | $0.00318 |
Grade A, and why
finesse-mini 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 — 225 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Finesse Mini — Micro-Task Prompt Planner
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-mini micro-task workflow:
- The ralph-loop iteration count is YOUR recommendation (3-8 based on file count).
- Every prompt must follow the meta-prompting skill template with all 10 mandatory attributes.
- Maximum 1 refinement cycle for validation failures. If still failing, present with warnings.
- The Task tool may ONLY launch these agent types: scope-safety-reviewer, completion-validator, goal-achievement-auditor. Do NOT launch code-explorer, code-architect, general-purpose, Bash, or any other agent type. (This overrides the broader list in planner-identity rule 10.)
- Do NOT create working files. Micro-tasks complete within a single context window.
- Do NOT use the exploration cache. Read files directly.
- File naming: derive
<name>from the first 3-4 words of the task description in kebab-case (e.g.,fix-typo-format-ts).
Mandatory Workflow Checklist
You MUST complete ALL 3 phases IN ORDER. Do NOT call ExitPlanMode until all steps are done:
- Phase 1: Quick Exploration completed (1-5 files read)
- Task size gate evaluated (>5 files or >8 iterations = suggest /finesse)
- Phase 2: Prompt constructed with all 10 mandatory attributes
- Git Configuration prompted (mandatory)
- Phase 3: All 3 validators launched in parallel
- All CRITICAL validation issues resolved
- Pre-flight validation run (execution layer, git tracking, scoped files, verification commands)
If ANY step was skipped, STOP and return to the first skipped step.
Finesse Mini is a lightweight single-pass alternative to /finesse, designed for tasks that are small enough that the full multi-phase workflow with UAT checkpoints and 6 parallel validators is overkill. Examples: fix a specific typo, add a missing import, rename a variable across a few files, add a single test case, fix a linter error, update a config value, add a missing null check.
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 · 225 lines · 15 tokens per session scan A be7036ea9906
finesse-mini is a command published in the GitHub repository jonathanung/finesse (4 stars, last pushed 6mo ago), licensed MIT. It adds 15 tokens to every session and 3,176 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.
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.