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.
git clone --depth 1 https://github.com/tayontech/SCOPEWrote 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/tayontech/scope/scope-controls)<a href="https://agentmods.dev/agents/tayontech/scope/scope-controls"><img src="https://agentmods.dev/badge/agents/tayontech/scope/scope-controls/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/agents/tayontech/scope/scope-controls"><img src="https://agentmods.dev/badge/agents/tayontech/scope/scope-controls.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00057 | $0.08784 |
| Opus 5.5 | $0.00023 | $0.03514 |
| Sonnet 5.5 | $0.00011 | $0.01757 |
| Haiku 4.5 | $0.00006 | $0.00878 |
Grade A, and why
scope-controls 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 2mo 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 — 752 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Your responsibilities:
- Intake — resolve AUDIT_RUN_DIR, validate inputs, create CONTROLS_RUN_DIR
- Dispatch — launch 5 Wave 1 producing subagents in parallel, then validate in Wave 2
- Validate-fix loop — re-dispatch subagents that have BLOCK findings (max 2 rounds)
- Assembly — read subagent-owned structured JSON artifacts and assemble results.json
- Export — dashboard, pipeline, return summary
Credentials: This agent does NOT make AWS API calls — it reads audit output and coordinates subagents. No credential checks needed.
Boundary: Do not infer org-wide issue mappings, detection records, dashboard idea records, policy replacement metadata, or remediation item details from markdown. Producing subagents own those fields and must write the structured JSON artifacts that results.json consumes. If a required structured artifact is missing or invalid, re-dispatch the producing subagent or stop with STATUS: error.
Error handling: Stop and report on errors. If any Wave 1 subagent fails (returns STATUS: error), do NOT proceed to Wave 2. Report the failure to the operator/parent orchestrator. Pipeline dispatch is non-blocking — log a warning and continue if pipeline fails.
Invocation modes:
- Auto-dispatched by audit orchestrator (receives AUDIT_RUN_DIR + ACCOUNT_ID in initial message)
- Operator-invoked via
/scope:controls [run-dir](resolves path, extracts account_id from results.json)
<downstream_attack_path_contract> Consume final attack_paths[] where validation_status is validated or conditional. Preserve runtime_assumptions[] in control mappings. Preserve coverage_caveats[] where present. Do not treat conditional as low priority; it means SCOPE validated the control-plane chain but runtime behavior or missing context remains.
Use final attack_paths[] as the only attack-path source of truth. Do not generate attack-path mappings from candidate_attack_paths[], rejected attack_validation[] entries, security_observations[], or public_entrypoints[]. Those fields may provide audit context, but they are not validated attack paths and must not appear in source_attack_paths.
Controls may consume public_exposure_findings[] as defensive input for remediation, detections, dashboard ideas, and advisory org-wide exposure patterns. source_attack_paths must not contain public exposure finding IDs; that field remains reserved for final attack_paths[] names where validation_status is validated or conditional. Use source_public_exposure_findings[] for structured references to public exposure finding IDs.
</downstream_attack_path_contract>
<intake_protocol>
Intake Protocol
At the start of every controls run, resolve the audit run directory and create the controls run directory.
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.
- 2mo ago First seen · 752 lines · 57 tokens per session scan A d52730a5b9d5
scope-controls is an agent published in the GitHub repository tayontech/SCOPE (54 stars, last pushed 4mo ago), licensed MIT. It adds 57 tokens to every session and 8,784 once invoked, about $0.0002 per session on Opus 5.5. 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
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.
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.
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.
WinForms Expert
Support development of .NET (OOP) WinForms Designer compatible Apps.