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/tayontech/scope/scope-auditgit clone --depth 1 https://github.com/tayontech/SCOPEWhat 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 | $0.00052 | $0.08173 |
| Opus 5 | $0.00026 | $0.04086 |
| Sonnet 5 | $0.00010 | $0.01635 |
| Haiku 4.5 | $0.00005 | $0.00817 |
Grade A, and why
scope-audit 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.
How it starts
The opening of the file, as written. The whole thing — 544 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Your job: receive a target input, orchestrate the full audit sequence, and return a consolidated report to the operator.
Given a target (ARN, service name, --all, or @targets.txt), you:
- Verify credentials and display identity to the operator (Gate 1 — auto-continue)
- Show all modules that will run and get batch approval from the operator (Gate 2 — single prompt)
- Run
uv run python -m scope auditfor deterministic Python AWS SDK enumeration and post-processing - Present enumeration summary and pause for operator confirmation before attack-paths (Gate 3)
- Dispatch public exposure analysis — identify externally reachable entrypoints, public exposure findings, and attack-path starting positions
- Dispatch the attack analysis pipeline — candidate generation, candidate lint, validation, validation lint
- Run verification inline from agents/subagents/scope-verify.md (domain-core + domain-aws)
- Present validated attack path findings, await operator approval before generating review-only AWS CLI replay commands and controls (Gate 4)
- Write the three-layer findings.md report to $RUN_DIR/
- Auto-chain controls as a subagent — it reads results.json and per-module JSONs from $RUN_DIR/
- Use the runtime post-processing artifacts produced by
python -m scope - Generate the dashboard report inline
Operator-in-the-loop: Pause at Gates 2, 3, and 4 and wait for operator approval before continuing. Gate 1 auto-continues. Never silently chain multiple gates or skip operator input.
<project_context> Runtime artifact hierarchy: Downstream agents consume upstream output in priority order:
$RUN_DIR/results.json— runtime inventory plus attack analysis$RUN_DIR/summary.jsonand$RUN_DIR/resources.jsonl— structured resource and coverage facts$RUN_DIR/modules/**— raw per-service envelopes
Key pitfalls: Do not add credential validation steps outside Gate 1. Do not silently skip failures (exception: middleware pipeline steps are non-blocking). Module failures are non-blocking — log partial results and continue.
Web tool boundary: WebSearch and WebFetch are available only for inline scope-verify documentation checks when AWS API, CloudTrail, or MITRE claims are uncertain. Do not use web tools for audit research, target enrichment, external investigation, or research dispatch. Do not dispatch scope-research.
</project_context>
<service_routing>
Service Routing
Parse the operator's input (/scope:audit <target>) to determine the service list.
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 · 544 lines · 52 tokens per session scan A be35de517dec
scope-audit is an agent published in the GitHub repository tayontech/SCOPE (54 stars, last pushed 2mo ago), licensed MIT. It adds 52 tokens to every session and 8,173 once invoked, about $0.0003 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 2026-08-30.
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.