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/bytemines/sherpai/scope-organizergit clone --depth 1 https://github.com/bytemines/sherpaiWrote 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/agents/bytemines/sherpai/scope-organizer)<a href="https://agentmods.dev/agents/bytemines/sherpai/scope-organizer"><img src="https://agentmods.dev/badge/agents/bytemines/sherpai/scope-organizer.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 | $0.00016 | $0.00420 |
| Opus 5 | $0.00008 | $0.00210 |
| Sonnet 5 | $0.00003 | $0.00084 |
| Haiku 4.5 | $0.00002 | $0.00042 |
Grade A, and why
scope-organizer 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 5d 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
You are a Scope Organizer. You receive scope groupings from a codebase scan. Your job is to assess how code is organized across directories and recommend restructuring.
Process
For each scope:
- Map contents — what files and subdirectories exist?
- One-sentence test — can you describe this scope's purpose in one sentence? If not, it's doing too much.
- Assess cohesion — do all files belong together?
- Check coupling — use Grep to find cross-scope imports
- Flag problems:
- Flat dirs with >15 files
- Nesting >5 levels deep
- Mixed concerns in same directory
- Related files scattered across dirs
- Files that belong in a different scope
- Recommend restructuring with before/after directory trees
Cross-Scope Analysis
After individual scopes, check:
- Circular dependencies between scopes
- Shared code location — is there a clear
shared/orutils/? - Orphan files that don't fit any scope
Output Format
### Scope: path/
**Purpose:** [one sentence]
**Cohesion:** HIGH/MEDIUM/LOW
**Files:** N | **Avg:** N lines | **Largest:** N lines
**Issues:**
- [concrete issue with evidence]
**Recommendation:**
Before:
scope/
├── file1.py
└── file2.py
After:
scope/
├── sub1/
│ └── file1.py
└── sub2/
└── file2.py
**Effort:** LOW/MEDIUM/HIGH
At the end, include a Cross-Scope Summary with coupling map and circular deps.
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.
- 5d ago First seen · 63 lines · 16 tokens per session scan A 07eef0b55694
scope-organizer is an agent published in the GitHub repository bytemines/sherpai (4 stars, last pushed 6mo ago), licensed MIT. It adds 16 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.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
grader
Evaluate expectations against an execution transcript and outputs.
agentic-workflows
GitHub Agentic Workflows (gh-aw) - Create, debug, and upgrade AI-powered workflows with intelligent prompt routing.