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/zebbern/termstackWrote 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/zebbern/termstack/ctf_misc)<a href="https://agentmods.dev/agents/zebbern/termstack/ctf_misc"><img src="https://agentmods.dev/badge/agents/zebbern/termstack/ctf_misc/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/zebbern/termstack/ctf_misc"><img src="https://agentmods.dev/badge/agents/zebbern/termstack/ctf_misc.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 | $0.00031 | $0.04372 |
| Opus 5.5 | $0.00012 | $0.01749 |
| Sonnet 5.5 | $0.00006 | $0.00874 |
| Haiku 4.5 | $0.00003 | $0.00437 |
Grade B, and why
ctf_misc 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 1mo 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.
Unrestricted tool accessmediumExcessive agency
A wildcard tool grant or "run any command" leaves no least-privilege boundary at all.
# breakpoint() drops to pdb (Python 3.7+) — can execute arbitrary code Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl "http://web.archive.org/cdx/search/cdx?url=target.com/*&output=text&fl=original&collapse=urlkey" Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
''.__class__.__mro__[1].__subclasses__() # find subprocess.Popen, os._wrap_close 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.
- 1mo ago First seen · 391 lines · 31 tokens per session scan B 9c86b17dd8d5
ctf_misc is an agent published in the GitHub repository zebbern/termstack (4 stars, last pushed 6mo ago), with no licence file. It adds 31 tokens to every session and 4,372 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it B with 3 findings (unrestricted tool access, makes network calls, runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other agents, from other repositories
web-researcher
Web research specialist — uses native WebFetch and WebSearch tools to execute multi-round searches, fetch pages, analyze content, and produce structured Markdown reports with citations.
verification
Use this agent to verify that implementation work is correct before reporting completion. Invoke after non-trivial tasks (3+ file edits, backend/API changes, infrastructure changes). Pass the ORIGINAL user task description, list of files changed, and approach taken. The agent runs builds, tests, linters, and checks to…
explorer
Fast agent specialized for exploring codebases. Use this when you need to quickly find files by patterns (eg. "src/components//.tsx"), search code for keywords (eg. "API endpoints"), or answer questions about the codebase (eg. "how do API endpoints work?"). When calling this agent, specify the desired thoroughness…
coder
Code implementation specialist. Handles file editing, code migration, module refactoring, and other pure implementation tasks. Use this agent when the user needs to write code, modify files, or move modules — not for architecture design or solution evaluation.
plan
Software architect agent for designing implementation plans. Use this when you need to plan the implementation strategy for a task. Returns step-by-step plans, identifies critical files, and considers architectural trade-offs.
minimal-helper
A small read-only helper agent defined by a project. It analyzes only the context supplied by the caller and returns a concise conclusion in Simplified Chinese.