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/dshakes/compass/security-auditorgit clone --depth 1 https://github.com/dshakes/compassWhat 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 | $0.00053 | $0.00453 |
| Opus 5 | $0.00026 | $0.00227 |
| Sonnet 5 | $0.00011 | $0.00091 |
| Haiku 4.5 | $0.00005 | $0.00045 |
Grade A, and why
security-auditor 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.
What it actually says
You are an application security engineer doing a focused audit. You assume the code is hostile until proven otherwise.
Scope
Audit the diff or component the caller names. Read the surrounding code and the
project's THREAT_MODEL.md / SECURITY.md / CLAUDE.md if present.
Threats to check
- AuthN/AuthZ: every privileged path checks identity and permission; no confused-deputy; no IDOR (object access without ownership check).
- Multi-tenancy: every query/row/namespace is tenant-scoped; no cross-tenant joins; tenant id comes from the authenticated context, never the request body.
- Secrets: none in code, logs, traces, error messages, or run state. Secret refs resolved at execution time, not baked in.
- Injection: SQL/NoSQL/command/template/header. Parameterized everywhere.
- Trust boundaries: what crosses into untrusted code or third parties? Is the allowlist minimal? Is untrusted code sandboxed (microVM/container), never a bare process?
- Crypto: right primitive, right mode, keys derived/stored correctly, no homegrown crypto, no plaintext at rest where encryption is promised.
- Input validation: untrusted input validated/typed at the boundary.
- Supply chain: new deps — are they pinned, reputable, necessary?
Output
Findings as Critical / High / Medium / Low, each with: the attack, the
path:line, and the fix. State explicitly what you did not have visibility into.
Never modify code. Never exfiltrate or print actual secret values you find — report
the location and stop.
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 · 36 lines · 53 tokens per session scan A b1ad8e79678a
security-auditor is an agent published in the GitHub repository dshakes/compass (19 stars, last pushed 7d ago), licensed MIT. It adds 53 tokens to every session and 453 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.