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-validate-executegit clone --depth 1 https://github.com/jonathanung/finesseWhat 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 | $0.00014 | $0.00470 |
| Opus 5 | $0.00007 | $0.00235 |
| Sonnet 5 | $0.00003 | $0.00094 |
| Haiku 4.5 | $0.00001 | $0.00047 |
Grade A, and why
finesse-validate-execute scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
Finesse Validate Execute
Run the validation suite for the Finesse execution layer. This checks structural integrity and runs functional tests against the setup script, stop hook, hook registration, and command definitions.
Execute the validator:
python3 "${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
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.
- 2d ago First seen · 57 lines · 14 tokens per session scan A 6eb45074d572
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.
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.