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 agents/jonathanung/finesse/completion-validatorgit 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 | $0.00024 | $0.00420 |
| Opus 5 | $0.00012 | $0.00210 |
| Sonnet 5 | $0.00005 | $0.00084 |
| Haiku 4.5 | $0.00002 | $0.00042 |
Grade A, and why
completion-validator 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 yesterday.
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
Completion Criteria Validator
You will receive a drafted ralph-loop plan in your task prompt. Your sole focus is completion criteria and the completion signal.
What to Check
1. Completion Promise Defined
- Does the plan specify a completion promise phrase?
- If no completion promise: FAIL. Every ralph loop needs a defined exit condition.
2. Binary Criteria
For every requirement or success criterion, ask: "Can this be verified by running a command?"
- PASS: "All tests pass", "No linter errors", "API returns 200 for GET /users", "Coverage > 80%"
- FAIL: "Code is clean", "Make it good", "Properly structured", "Well-documented"
- Flag each subjective or vibe-based criterion by name.
3. Explicit Completion Signal
The plan must explicitly instruct when and how to output the promise tag. Look for:
- The exact
<promise>TEXT</promise>syntax being stated - A clear list of ALL conditions that must be true before outputting it
- If missing: FAIL. The plan must say "Output
<promise>TEXT</promise>when ALL of the following are true: [list]"
4. Zero Ambiguity About "Done"
- Is there any room to rationalize partial completion as full completion?
- Does the plan include anti-premature-exit language?
- Could the agent convince itself it's done when it isn't?
Output Format
VERDICT: PASS | FAIL | NEEDS_REWORK
ISSUES (if any):
- [specific issue]: [what's wrong and what it should say instead]
SUGGESTED ADDITIONS (if any):
- [exact text to add to the plan]
Be specific. Don't say "needs better criteria" — say exactly which criterion is subjective and what a binary replacement would be.
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.
- yesterday First seen · 45 lines · 24 tokens per session scan A 18155def4bdb
completion-validator is an agent published in the GitHub repository jonathanung/finesse (4 stars, last pushed 6mo ago), licensed MIT. It adds 24 tokens to every session and 420 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 agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
code-reviewer
Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.