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-resume)<a href="https://agentmods.dev/commands/jonathanung/finesse/finesse-resume"><img src="https://agentmods.dev/badge/commands/jonathanung/finesse/finesse-resume.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 | $0.00012 | $0.02752 |
| Opus 5 | $0.00006 | $0.01376 |
| Sonnet 5 | $0.00002 | $0.00550 |
| Haiku 4.5 | $0.00001 | $0.00275 |
Grade A, and why
finesse-resume 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 8d 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 — 187 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Finesse Resume
Critical Rules — READ BEFORE ANYTHING ELSE
All identity rules are defined in the planner-identity skill and injected by identity_hook.py. Those are non-negotiable and not repeated here. All workflow rules (task classification, UAT checkpoints, multi-workflow, context budget, discovery depth) are defined in finesse.md and apply equally to resumed sessions. The only resume-specific rules are:
- The final deliverable is ALWAYS the ralph-loop command using file references — NEVER output the raw prompt inline. After handling the user's acceptance option, STOP.
- Resumed sessions use the same orchestrator delegation pattern as
finesse.md(exploration-orchestrator, scope-analyzer, architecture-designer, plan-constructor, plan-validator agents).
Mandatory Workflow Checklist
Before calling ExitPlanMode, verify these final-phase gates were completed (in addition to all task-type-specific phases from the resume point):
- ALL 6 validation agents launched in parallel
- All CRITICAL and HIGH 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.
Argument Parsing
Parse $ARGUMENTS:
No argument mode
If $ARGUMENTS is empty or blank:
- Use
Globto scanfinesse-plans/for*-working.mdfiles. - If none found, say "No working files found in finesse-plans/." and stop.
- If exactly one found, load it automatically.
- If multiple found, read each file's YAML frontmatter to extract
task_typeandcurrent_phase. List each working file with its task type and current phase, then useAskUserQuestionto let the user pick one.
With path argument
If $ARGUMENTS contains a path:
- Load the specified file directly.
- If it doesn't exist or can't be read, tell the user "Working file not found at [path]. Please check the path and try again." and stop.
Enter Plan Mode
Enter plan mode immediately after selecting the working file. All work happens in plan mode until the plan is presented.
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.
- 8d ago First seen · 187 lines · 12 tokens per session scan A ece97a760643
finesse-resume is a command published in the GitHub repository jonathanung/finesse (4 stars, last pushed 6mo ago), licensed MIT. It adds 12 tokens to every session and 2,752 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.
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.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.