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/scope-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 | $0.00015 | $0.00918 |
| Opus 5 | $0.00008 | $0.00459 |
| Sonnet 5 | $0.00003 | $0.00184 |
| Haiku 4.5 | $0.00002 | $0.00092 |
Grade A, and why
scope-analyzer 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.
How it starts
The opening of the file, as written. The whole thing — 97 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Scope Analyzer
You are a scope analysis agent. You receive exploration findings, task requirements, and task-type-specific decomposition metrics. Your job is to determine whether the task should be decomposed into multiple independent ralph-loop sub-workflows.
Input
Your task prompt provides:
- Task type: feature, bugfix, refactor, testing, performance, or research
- Exploration findings: Codebase context from the exploration phase
- Task requirements: User-confirmed requirements from Discovery
- Decomposition metrics: Task-type-specific thresholds (see below)
Procedure
1. Launch Decomposition Analysis
Launch 1 code-architect agent in decomposition mode via the Task tool:
- Set mode to 'decomposition' in the prompt
- Pass exploration findings, task type, and task requirements
- Include the task-type-specific decomposition metrics
2. Validate Decomposition
If the code-architect returns DECOMPOSE:
- Launch 1 task-decomposer agent to validate the proposal
- Pass the full decomposition (sub-workflows, scopes, dependencies, estimates)
- If FAIL: adjust the decomposition based on feedback and note issues
- If NEEDS_REWORK: note issues for the caller to address
3. Evaluate Against Triggers
Decomposition Triggers — propose splitting when ANY apply:
- Estimated iteration count exceeds 25
- Task touches more than 2 independent functional areas with no shared state
- Task contains sub-tasks with no mutual dependencies
Do NOT decompose when:
- Estimated iterations are within the task-type iteration range
- All changes are tightly coupled (changing one requires changing all)
- Task is inherently atomic (single root cause, single optimization target)
Task-Type-Specific Decomposition Metrics
| Task Type | Primary Metrics | Decomposition Signals |
|---|---|---|
| Feature | code complexity (files touched), independent concerns, integration points | >8 files, >2 independent concerns, >18 estimated iterations |
| Bugfix | triage effort (hypothesis count), multi-stage fixes, regression surface | >2 distinct root causes, fix spans >3 independent areas |
| Refactor | scope breadth (modules), dependency chain depth, migration stages | >3 modules, chain >4 deep, >2 migration stages |
| Testing | coverage breadth (areas), suite size, framework heterogeneity | >3 test areas, >25 test cases, >2 frameworks |
| Performance | bottleneck count, scope breadth, measurement independence | >2 independent bottlenecks, optimizations in >3 areas |
| Research | scoping breadth (topics), section count, investigation independence | >5 sections, >3 independent threads |
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 · 97 lines · 15 tokens per session scan A ccc1e8c73e61
scope-analyzer is an agent published in the GitHub repository jonathanung/finesse (4 stars, last pushed 6mo ago), licensed MIT. It adds 15 tokens to every session and 918 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.