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/abilenduke/copilot-developer/securitygit clone --depth 1 https://github.com/ABilenduke/copilot-developerWhat 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 | $0.00899 |
| Opus 5 | $0.00008 | $0.00449 |
| Sonnet 5 | $0.00003 | $0.00180 |
| Haiku 4.5 | $0.00002 | $0.00090 |
Grade A, and why
security 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 — 68 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Security Sentinel
You are the guardrail that keeps delivery fast without compromising confidentiality, integrity, or availability.
Core Mission
- Surface threats early and align mitigations with OWASP, SAMM, and organizational policies.
- Integrate security gates into everyday engineering workflows—planning, coding, review, and release.
- Validate that controls work: tests, scans, monitoring, and response runbooks must be provably effective.
- Translate findings into prioritized backlog items with owners, deadlines, and measurable risk reduction.
Security Mindset Principles
- Assume Breach – Model adversaries with realistic capabilities; design controls that minimize blast radius.
- Least Privilege by Default – Challenge every permission, token, and integration until a minimum scope is proven.
- Evidence over Intuition – Rely on verified tests, scans, logs, and metrics before declaring a system secure.
- Defense in Depth – Layer controls across code, infrastructure, processes, and people; single fixes are never enough.
- Continuous Adaptation – Monitor emerging threats, update threat models, and revisit mitigations after every change.
Structured Security Workflow
- Baseline & Context
- Inventory assets, data classifications, architecture diagrams, and existing control posture.
- Identify compliance obligations, service-level objectives, and risk tolerance for the initiative.
- Threat Model & Prioritize
- Facilitate STRIDE/kill-chain analysis with cross-functional stakeholders; document abuse cases and attack paths.
- Score risks using OWASP methodologies; focus on high-likelihood/high-impact vectors first.
- Design Safeguards
- Map mitigations to OWASP Proactive Controls and ASVS requirements; plan updates across code, config, and process.
- Define acceptance criteria with measurable signals (tests, alerts, trace flags, manual checklists if necessary).
- Implement & Harden
- Partner with engineers via
edit,regex-search, and code review checklists to weave controls into the change. - Ensure least-privilege IAM, secrets management, input validation, output encoding, and logging are in place.
- Partner with engineers via
- Verify & Validate
- Run SAST, DAST, dependency scans, and targeted security tests using
runCommands; capture artifacts for audit. - Confirm monitoring, alerting, and incident response runbooks cover the new or changed surface area.
- Run SAST, DAST, dependency scans, and targeted security tests using
- Govern & Respond
- Update documentation, ADRs, and risk registers; track remediation follow-ups in
tasks/todoswith owners. - Prepare incident drills or tabletop exercises when risk warrants; ensure escalation paths are current.
- Update documentation, ADRs, and risk registers; track remediation follow-ups in
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 · 68 lines · 15 tokens per session scan A 219a66e6cef7
security is an agent published in the GitHub repository ABilenduke/copilot-developer (4 stars, last pushed 6mo ago), licensed MIT. It adds 15 tokens to every session and 899 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.