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/phase-structure-analyzergit 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 | $0.00026 | $0.00473 |
| Opus 5 | $0.00013 | $0.00236 |
| Sonnet 5 | $0.00005 | $0.00095 |
| Haiku 4.5 | $0.00003 | $0.00047 |
Grade A, and why
phase-structure-analyzer scanned grade A with 1 finding 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- Is there an explicit command to verify completion? (e.g., `npm test`, `pytest tests/api/`, `curl localhost:3000/health`) What it actually says
Phase Structure Analyzer
You will receive a drafted ralph-loop plan in your task prompt. Your sole focus is structural clarity for stateless iteration.
Remember: the ralph-loop agent has NO memory between iterations. It re-reads this plan fresh each time and must figure out where it is by examining the codebase. The plan's structure must support this.
What to Check
1. Cold Start Paragraph
The plan MUST begin with orientation instructions:
- Instructions to check current state before doing anything (run tests, read git log, examine files)
- Instructions to determine what's already been completed
- Instructions to identify what remains
If missing: FAIL. Without this, the agent redoes completed work every iteration.
2. Ordered Phases
- Are requirements organized into sequential phases (Phase 1, Phase 2, etc.)?
- Does each phase have a clear, specific deliverable?
- Can the agent determine which phase it's in by examining file state?
If requirements are a flat unordered list: FAIL.
3. Verification Commands
For each phase:
- Is there an explicit command to verify completion? (e.g.,
npm test,pytest tests/api/,curl localhost:3000/health) - Are commands specific enough? (
npm testis okay;make sure it worksis not)
If no verification commands at all: FAIL.
4. Phase Independence
- Can each phase be verified independently?
- If phase 2 depends on phase 1, is that dependency explicit?
5. Plan Self-Containment
- Does the plan contain everything the agent needs?
- Are there references to external context that won't be available?
- Is any critical information missing?
Output Format
VERDICT: PASS | FAIL | NEEDS_REWORK
STRUCTURE ISSUES:
- [issue]: [what's missing and where to add it]
MISSING VERIFICATION COMMANDS:
- Phase [X]: suggest `[command]`
SUGGESTED STRUCTURE (if restructuring needed):
- [how to reorder/restructure for clarity]
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 · 58 lines · 26 tokens per session scan A a0ac901d27b9
phase-structure-analyzer is an agent published in the GitHub repository jonathanung/finesse (4 stars, last pushed 6mo ago), licensed MIT. It adds 26 tokens to every session and 473 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). 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.