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.
git 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-retro)<a href="https://agentmods.dev/commands/jonathanung/finesse/finesse-retro"><img src="https://agentmods.dev/badge/commands/jonathanung/finesse/finesse-retro.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 5.1 | $0.00013 | $0.03387 |
| Opus 5 | $0.00006 | $0.01693 |
| Sonnet 5 | $0.00003 | $0.00677 |
| Haiku 4.5 | $0.00001 | $0.00339 |
Grade A, and why
finesse-retro 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 6d 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 — 274 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Finesse Retro — Post-Execution Retrospective
Perform retrospective analysis on a completed ralph-loop run. This command reads plan metadata, gathers execution data from the user, and produces a timestamped retro document. Optionally performs PR review against the original plan scope and generates validated fix-loop prompts for identified gaps.
This command only writes to finesse-plans/. It is read-only against all other project files except when running verification commands from the original plan (which require user confirmation).
Step 1: Resolve Plan Name
Parse $ARGUMENTS as the plan name.
- If empty: Use Glob to scan
finesse-plans/*-plan.md, list available plans, and ask the user to pick one via AskUserQuestion. - If provided: Check for an exact match at
finesse-plans/<name>-plan.md.- If no exact match: Use Glob for
finesse-plans/*-plan.md, filter for entries containing the argument as a substring (partial match / fuzzy resolution), and list matching candidates via AskUserQuestion. - If no matches at all: Say "No plan found matching '' in finesse-plans/. Available plans:" and list all
-plan.mdfiles. Stop.
- If no exact match: Use Glob for
Step 2: Load Plan Data
Read the plan metadata file (finesse-plans/<name>-plan.md). Extract:
- Task type (from
## Task Typesection) - Summary (from
## Summarysection) - Recommended --max-iterations (from
## Recommended --max-iterationsheading — parse the number) - baseline_commit (from
## baseline_commitor from inline mention — may not exist in older plans) - git_config (from
## git_configor inline mention — may not exist in older plans) - subagent_enabled (from
## subagent_enabledor inline mention — may not exist in older plans)
Read the prompt file (finesse-plans/<name>.md). Extract:
- Scoped files: look for patterns like "Only modify files in", "Do NOT modify anything in", or file path lists
- Phase structure: look for "Phase N:" or "### Phase N" headings
- Completion criteria: look for "## Completion" section content
- Verification commands: look for "Verify:" lines within phases
- Guardrails: look for "## Rules" section, especially "Do NOT" lines
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.
- 6d ago First seen · 274 lines · 13 tokens per session scan A 4590c5555442
finesse-retro 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 3,387 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
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.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.