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 zebbern/termstack --skill audit-flowgit 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/skills/zebbern/termstack/audit-flow)<a href="https://agentmods.dev/skills/zebbern/termstack/audit-flow"><img src="https://agentmods.dev/badge/skills/zebbern/termstack/audit-flow/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/skills/zebbern/termstack/audit-flow"><img src="https://agentmods.dev/badge/skills/zebbern/termstack/audit-flow.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 | $0.00084 | $0.03798 |
| Opus 5.5 | $0.00034 | $0.01519 |
| Sonnet 5.5 | $0.00017 | $0.00760 |
| Haiku 4.5 | $0.00008 | $0.00380 |
Grade A, and why
audit-flow 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 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.
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.
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 ships with it
11 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.
- COMMANDS.md 8.9 KB
- COMMANDS.mdZone.Identifier 25 B
- EXAMPLES.md 9.5 KB
- EXAMPLES.mdZone.Identifier 25 B
- schema.sql 6.7 KB
- schema.sqlZone.Identifier 25 B
- scripts/audit.py 59 KB runs code
- scripts/audit.pyZone.Identifier 25 B
- setup.sh 2.5 KB runs code
- setup.shZone.Identifier 25 B
- SKILL.mdZone.Identifier 25 B
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 · 369 lines · 84 tokens per session scan A 8c2d8b9bca08
audit-flow is a skill published in the GitHub repository zebbern/termstack (4 stars, last pushed 6mo ago), with no licence file. It adds 84 tokens to every session and 3,798 once invoked, about $0.0003 per session on Opus 5.5. 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 skills, from other repositories
ultra-adlc
End-to-end delivery orchestration for explicitly requested, very large software changes that must be completely implemented and independently proven. Use when the user invokes "ultra-adlc" or asks for an Ultra-ADLC-scale full delivery; do not use for ordinary features, small fixes, reviews, or ad hoc parallel work.
cron
A scheduler for running the same agent task at set times or repeating intervals, such as every day or every five minutes. It uses the standard five-part cron schedule format.
clarifying-questions
A requirements-clarification guide for situations where a request is vague, hides important assumptions, or may ask for the wrong solution.
debugging
A methodical way to find the underlying cause of software bugs by observing what happens, forming hypotheses, and testing them. It separates finding the cause from applying and checking the fix.
error-handling
A guide to handling failures and recording useful logs in software. It explains when to pass an error upward, handle it locally, or retry it.
lion-writing-skills
A set of instructions for creating or changing reusable skills in the Lion-Skills repository. A skill is an operations guide that tells a future coding agent when and how to handle a recurring workflow.