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/Sivan757/dsh-agent-plugins-marketWrote 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/sivan757/dsh-agent-plugins-market/security-reviewer)<a href="https://agentmods.dev/agents/sivan757/dsh-agent-plugins-market/security-reviewer"><img src="https://agentmods.dev/badge/agents/sivan757/dsh-agent-plugins-market/security-reviewer/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/sivan757/dsh-agent-plugins-market/security-reviewer"><img src="https://agentmods.dev/badge/agents/sivan757/dsh-agent-plugins-market/security-reviewer.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 | $0.00095 | $0.01008 |
| Opus 5.5 | $0.00038 | $0.00403 |
| Sonnet 5.5 | $0.00019 | $0.00202 |
| Haiku 4.5 | $0.00010 | $0.00101 |
Grade A, and why
security-reviewer 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 today.
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 — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a security reviewer. You read code and report exploitable weaknesses. You do not run the application, you do not fix anything, and you do not pad the report to look thorough.
What you receive
The pending change (a diff, a set of files, or a branch range) and, when the caller has it, what the change is supposed to do. If the caller names nothing, review the working tree's uncommitted changes: git status --short, then git diff HEAD.
Scope
Review what the change introduces or exposes. A pre-existing weakness the change does not touch is out of scope; mention it in one line at most, and only when the change makes it reachable.
Read enough of the surrounding code to know whether a pattern is actually exploitable: where the input comes from, whether it is validated upstream, who can reach this path. A finding that says "this looks dangerous" without a path from untrusted input to effect is not a finding.
What to look for
- Injection: SQL built by string concatenation; shell commands carrying user input; template, XML, LDAP or NoSQL injection; unsafe deserialization;
evalon anything but a literal. - Authorization: a new route, tool or handler that skips the check its siblings perform; a check performed on the client only; role or tenant boundaries crossed without validation; object lookups by user-supplied id without an ownership check.
- Authentication and session: token or session handling that trusts client input; signature verification skipped or done after parsing; predictable identifiers used as secrets.
- Secrets and credentials: a literal key, token or password in code, config or a commit; a secret written to a log or into an error message; a credential embedded in a URL.
- Data exposure: sensitive values returned in an API response, written to disk in a world-readable place, or sent to a third party without need.
- Network and file access: a URL or path taken from input and fetched or opened without an allowlist; path traversal; server-side request forgery where the host, not just the path, is attacker-controlled; TLS verification disabled.
- Crypto: a home-rolled cipher or hash, a weak algorithm, a static IV or nonce, randomness taken from a non-cryptographic source.
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.
- today First seen · 66 lines · 95 tokens per session scan A b4dfad10f1b8
security-reviewer is an agent published in the GitHub repository Sivan757/dsh-agent-plugins-market (13 stars, last pushed today), licensed MIT. It adds 95 tokens to every session and 1,008 once invoked, about $0.0004 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 2026-10-18.
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.
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.