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 skills add konamgil/mandu --skill mandu-securitygit clone --depth 1 https://github.com/konamgil/manduWrote 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/skills/konamgil/mandu/mandu-security)<a href="https://agentmods.dev/skills/konamgil/mandu/mandu-security"><img src="https://agentmods.dev/badge/skills/konamgil/mandu/mandu-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 | $0.00046 | $0.00853 |
| Opus 5 | $0.00023 | $0.00426 |
| Sonnet 5 | $0.00009 | $0.00171 |
| Haiku 4.5 | $0.00005 | $0.00085 |
Grade A, and why
mandu-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 7d 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 — 128 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Mandu Security
Mandu 애플리케이션의 보안 모범 사례 가이드. slot guard를 통한 인증/인가, 입력 검증, CSRF/XSS 방어, 환경 변수 관리를 다룹니다.
Agent Workflow Contract
This skill is a Domain addendum. It must not replace mandu-agent-workflow.
Use it only after mandu.agent.plan selects security, auth, slot, API, or runtime domains.
Canonical workflow step: plan -> verify -> repair.
Preferred MCP tools:
| Step | Tools |
|---|---|
| plan | mandu.agent.plan, mandu.docs.search |
| apply | mandu.agent.apply |
| verify | mandu.agent.verify, mandu.guard.check, mandu.contract.validate |
| repair | mandu.agent.repair, mandu.guard.explain |
Allowed file edits:
- Auth/session slot logic named in the plan
- Server-only validation and security header configuration
- Environment templates, never secret values
Verification command:
mandu agent verify --changed --json --write
Common failures:
- Exposing secrets through client bundles or sync artifacts
- Changing auth behavior without route/API/slot verification
- Treating guard findings as policy problems before checking source boundaries
Repair path:
mandu agent repair --from .mandu/agent-verify.json --json
When to Apply
Reference these guidelines when:
- Implementing authentication in slots
- Adding authorization guards
- Validating user input
- Protecting against CSRF/XSS attacks
- Managing secrets and environment variables
- Handling sensitive data
Rule Categories by Priority
| Priority | Category | Impact | Prefix |
|---|---|---|---|
| 1 | Authentication | CRITICAL | sec-auth- |
| 2 | Input Validation | CRITICAL | sec-input- |
| 3 | CSRF/XSS Protection | HIGH | sec-protect- |
| 4 | Environment & Secrets | HIGH | sec-env- |
| 5 | Data Handling | MEDIUM | sec-data- |
Quick Reference
1. Authentication (CRITICAL)
sec-auth-guard- Use guard() for authentication checkssec-auth-session- Secure session managementsec-auth-jwt- JWT token handling best practices
What ships with it
8 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 7d ago First seen · 128 lines · 46 tokens per session scan A 28fe8c738a7e
mandu-security is a skill published in the GitHub repository konamgil/mandu (46 stars, last pushed 10d ago), licensed MPL-2.0. It adds 46 tokens to every session and 853 once invoked, about $0.0002 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 skills, from other repositories
api-design-patterns
Comprehensive API design patterns covering REST, GraphQL, gRPC, versioning, authentication, and modern API best practices.
architecture-patterns
Software architecture patterns and best practices.
Full Stack Engineer
Full Stack Engineer delivers production-grade technical work with clear architecture, tests, maintainability, and operational awareness.
pipeline
This skill should be used when the user asks to "create a pipeline spec", "document data transformations", "document data flow", "specify pipeline invariants", "wyx pipeline", or wants to design, retrofit, or discover data pipelines with quality invariants and boundary ownership. Produces PIPELINE.md specs.
add-service
Add a service capsule (or Kafka topic node) to the Cosmos map. Use when the user says "add service X to the cosmos", "wire X into the map", or "add a topic node for Y". Researches the service from source, maps all its connections, then adds SERVICES/TOPICS entries to src/scenarios/ with correct position, color, and…
api-designer
An API contract design guide for planning how software interfaces work before implementation. An API is an agreed way for programs or clients to exchange requests and responses.