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/zebbern/termstack/ctf_webgit clone --depth 1 https://github.com/zebbern/termstackWhat 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 | $0.00036 | $0.04142 |
| Opus 5 | $0.00018 | $0.02071 |
| Sonnet 5 | $0.00007 | $0.00828 |
| Haiku 4.5 | $0.00004 | $0.00414 |
Grade C, and why
ctf_web scanned grade C with 4 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.
Cloud metadata endpointmediumServer-side request forgery
One request to 169.254.169.254 can return temporary IAM credentials.
| **SSRF** | URL parameters, redirect endpoints | Target `127.0.0.1`, `169.254.169.254`, internal services | 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.
| Run any command | `mcp_kali-tools_zebbern_exec` | Generic terminal fallback | Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
1. **Technology fingerprint** — `whatweb`, `curl -I`, response headers, error pages Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
| **Pug/Jade** | `#{7*7}` → `49` | `-var x=root.process.mainModule.require('child_process').execSync('id')` | The source is not reproduced here
No licence file
A repository with no LICENSE is all rights reserved by default, so the body is not copied here. The metadata, the measurements and the link are.
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 · 307 lines · 36 tokens per session scan C 3352138eed0b
ctf_web is an agent published in the GitHub repository zebbern/termstack (5 stars, last pushed 4mo ago), with no licence file. It adds 36 tokens to every session and 4,142 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it C with 4 findings (cloud metadata endpoint, unrestricted tool access, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other agents, from other repositories
advisor
Opus 级高级技术顾问，提供第二意见、方案比较和风险审阅。适用于技术选型、实现规划、架构/API/并发/安全问题、疑难 bug 根因、代码或调查结论审阅，以及任何需要判断“是否/哪种/怎么做”的任务；可读取调用方明确列出的证据文件，不负责实现或验证。.
code-reviewer
Expert code review specialist. Proactively reviews code for quality, security, and maintainability. Use immediately after writing or modifying code.
minimal-helper
项目目录定义的最小只读助手，用于独立分析给定上下文并返回简洁结论。.
test-agent
The current test execution owner is the dow test CLI. The /test workflow entry invokes that CLI; it does not dispatch a second independent test plan.
brainstorm-audit-agent
You are an independent design reviewer. Review BRAINSTORM.md to find issues that main agent and user may have overlooked during discussion.
prd-audit-agent
You are an independent requirements reviewer. Review PRD.md to find gaps and issues at the requirements level.