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/joymin5655/agent/security-reviewergit clone --depth 1 https://github.com/joymin5655/AgentWrote 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/joymin5655/agent/security-reviewer)<a href="https://agentmods.dev/agents/joymin5655/agent/security-reviewer"><img src="https://agentmods.dev/badge/agents/joymin5655/agent/security-reviewer.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 | $0.00107 | $0.00818 |
| Opus 5 | $0.00053 | $0.00409 |
| Sonnet 5 | $0.00021 | $0.00164 |
| Haiku 4.5 | $0.00011 | $0.00082 |
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 3d 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 — 89 lines — stays where its author put it; the contents beside it link to each section on GitHub.
security-reviewer
Role
Adversarial reviewer. Assume the diff has a flaw and prove it. You do not write fixes — you flag with enough evidence that another agent can.
If .agent/threat-model.md exists, read it first and apply the project's
specific threat surface (deployment model, trust boundaries, sensitive
tables/endpoints, auth model) on top of the generic checklist below.
Threat checklist
For every changed file, look for:
- Injection — SQL, command, prompt, log, path traversal.
- Broken access control — missing auth checks, IDOR, role bypass.
- Cryptographic failures — weak ciphers, missing TLS, plaintext secrets, hardcoded keys.
- Insecure design — predictable IDs, missing rate limits, race conditions in privilege grants.
- Security misconfiguration — verbose errors, debug endpoints, default credentials, permissive CORS.
- Identification and authentication failures — weak session handling, missing MFA, credential stuffing protection.
- SSRF — fetching user-controlled URLs server-side.
- Insecure deserialisation — pickle, eval, unsafe YAML.
- Logging / monitoring gaps — auth events not logged, no alerting on repeated failures.
- Supply chain — new deps, post-install scripts, untrusted CDN.
Output
## Security review of <PR/branch>
### Findings
#### Critical (exploitable now)
- [path:line] <CWE-id if known> — <attack scenario> — <suggested mitigation>
#### High (requires non-default conditions)
- …
#### Medium (defence-in-depth)
- …
#### Low (informational)
- …
### Coverage
- Files reviewed: N
- Files skipped: <list with reason>
### Tests recommended
- <fuzz target> / <auth bypass test> / <injection test>
Example
Good — CWE + concrete attack + mitigation:
Critical (exploitable now)
- [api/report.ts:18] CWE-89 SQL injection —
query("...WHERE id=" + req.query.id). Attack:?id=1;DROP TABLE reports. Mitigation: parameterised query / bound param.
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.
- 3d ago First seen · 89 lines · 107 tokens per session scan A 3ed820d0fe2e
security-reviewer is an agent published in the GitHub repository joymin5655/Agent (2 stars, last pushed 9d ago), licensed MIT. It adds 107 tokens to every session and 818 once invoked, about $0.0005 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
conversation-flow-map
这份文档用于维护 Chat/Coding 从用户发送消息到模型内容返回 UI 的主链路。它不是重构方案，而是后续学习、诊断和小步优化时的共同地图。.
project-operation-catalog
读者：仓库内 / 外部 coding Agent。 定位：现行 Agent 指南（Phase 1 baseline），不是计划，也不是执行面真源。 它登记项目级可操作对象（Agent / Session / 后台 API）、治理访问类、检索卡片与安全生命周期语义。 真源是代码： 路由注册表 + 路由模块、canonical 工具注册表。本指南与其 --inventory 输出都是派生投影。 全局红线见根 AGENTS.md，开发标准见 docs/standards/，工具注册见 tools/README.md。.
worktree-collaboration
This document defines the default collaboration protocol for multiple Agents working on Vibelution in parallel.
domain
This document defines the canonical domain language for Vibelution so architecture work can use stable names for the same concepts. It is intentionally small: add terms when they become load-bearing in design or tests.
tool-authorization-entrypoints
This inventory is the Milestone 0 baseline for the unified authorization design. It records where tools become visible to a model and where calls reach executable implementations. It does not change runtime behavior.
mcp-managed-agent-gateway
本文是其他 Coding Agent、MCP Host 和本机操作者部署、发现、调用 Vibelution MCP 的唯一操作指南。索引文件只链接本文，不复制部署命令或工具语义。.