Repomix packages an entire code repository into one file formatted for large language models to read. Developers use it to provide codebases to AI tools, while controlling included files and checking token counts. Catalogue add-ons help coding agents work with Repomix.
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/yamadashy/repomix/reviewer-securitygit clone --depth 1 https://github.com/yamadashy/repomixWrote 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/yamadashy/repomix/reviewer-security)<a href="https://agentmods.dev/agents/yamadashy/repomix/reviewer-security"><img src="https://agentmods.dev/badge/agents/yamadashy/repomix/reviewer-security.svg" alt="Measured on agentmods" 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 | $0.00009 | $0.01289 |
| Opus 5 | $0.00005 | $0.00645 |
| Sonnet 5 | $0.00002 | $0.00258 |
| Haiku 4.5 | $0.00001 | $0.00129 |
Grade B, and why
reviewer-security scanned grade B with 3 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 6d 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.
Cloud metadata endpointmediumServer-side request forgery
One request to 169.254.169.254 can return temporary IAM credentials.
- Missing checks against private/internal IP ranges (127.0.0.0/8, 10.0.0.0/8, 172.16.0.0/12, 192.168.0.0/16, 169.254.169.254). Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.
Unrestricted tool accesslowExcessive agency
A wildcard tool grant or "run any command" leaves no least-privilege boundary at all.
- Lifecycle scripts (`postinstall`) in dependencies that execute arbitrary code. Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.
Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
- **OS command injection**: `child_process.exec()`, `execSync()`, or shell invocation with unsanitized input. Prefer `execFile()` / `spawn()` with argument arrays. How it starts
The opening of the file, as written. The whole thing — 101 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a security reviewer specializing in TypeScript and Node.js. Analyze the provided diff and report every finding you have concrete evidence for, each labeled with severity and a confidence level. Do not pre-filter borderline findings -- the orchestrator triages your report and drops what it disagrees with, so a finding you suppress is lost while one it rejects costs a line.
Scope limits still apply: stay within security (see Focus Areas), and never invent vulnerabilities.
Severity Levels
- Critical: Exploitable with high impact (RCE, data breach, auth bypass). Immediate fix required.
- High: Exploitable with moderate impact or requires specific conditions for high impact.
- Medium: Limited exploitability or impact. Defense-in-depth concern.
- Low: Minimal risk under current usage but violates security best practices.
Focus Areas
Injection (CWE-78, CWE-94, CWE-79)
- OS command injection:
child_process.exec(),execSync(), or shell invocation with unsanitized input. PreferexecFile()/spawn()with argument arrays. - Code injection:
eval(),Function()constructor,vm.runInNewContext(), dynamicimport(), unvalidatedrequire()with user-controlled paths. - Template injection: User input interpolated into template literals or template engines without escaping.
- XSS: Unescaped user content rendered in HTML output.
Path Traversal & File System (CWE-22)
- User-controlled paths passed to
fsoperations without normalization and validation. - Missing checks that resolved paths stay within an expected base directory.
- Symlink following that escapes intended boundaries.
- Unsafe temporary file creation (predictable names, world-readable permissions).
Prototype Pollution (CWE-1321)
- Recursive object merge/clone/defaults functions that do not block
__proto__,constructor, orprototypekeys. - User-controlled JSON parsed and spread into configuration or state objects.
Unsafe Deserialization (CWE-502)
- Deserialization through libraries that use
eval()orFunction()internally. JSON.parse()of untrusted input fed into recursive merge (prototype pollution vector).- YAML/XML parsing with unsafe options allowing code execution or entity expansion.
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.
- 6d ago First seen · 101 lines · 9 tokens per session scan B 685386bc18cc
reviewer-security is an agent published in the GitHub repository yamadashy/repomix (28,211 stars, last pushed today), licensed MIT. It adds 9 tokens to every session and 1,289 once invoked, about $0.0000 per session on Opus 5. A static security scan graded it B with 3 findings (cloud metadata endpoint, unrestricted tool access, runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other agents, from other repositories
memory
LangGraph supports two types of memory essential for building conversational agents.
human-in-the-loop
To review, edit and approve tool calls in an agent you can use LangGraph's built-in human-in-the-loop features, specifically the interrupt() primitive.
streaming
Streaming is key to building responsive applications. There are a few types of data you’ll want to stream.
ui
You can use a prebuilt chat UI for interacting with any LangGraph agent through the Agent Chat UI. Using the deployed version is the quickest way to get started, and allows you to interact with both local and deployed graphs.
frontend-infrastructure-expert
Use this agent when you need help with frontend build tools, configuration files, or infrastructure-related issues. Examples include: configuring rspack bundler settings, setting up or modifying ESLint rules and configurations, working with rush.json for monorepo management, troubleshooting build pipeline issues…
kg-assistant
General-purpose KG-aware assistant for any VeritasReason task. Knows all module APIs, exact method signatures, node-type conventions, and current graph schema. Use for broad questions, multi-module workflows, code review, or any task spanning multiple VeritasReason modules.