# Test Saill In Skill

> Proof-of-concept SAILL-in-skill. Replaces a wordy dirtree-check skill with a tight SAILL block. Audits tested_implementations nonce coverage via the Nonce Trace Audit team.

- **Type:** Skill
- **Install:** `agentstack add skill-horizonbrute-standardized-ai-looping-language-saill-test-saill-in-skill`
- **Verified:** Yes — security-reviewed for prompt injection and unsafe behavior
- **Seller:** [HorizonBrute](https://agentstack.voostack.com/s/horizonbrute)
- **Installs:** 0
- **Category:** [Agent Skills](https://agentstack.voostack.com/c/agent-skills)
- **Latest version:** 0.1.0
- **License:** MIT
- **Upstream author:** [HorizonBrute](https://github.com/HorizonBrute)
- **Source:** https://github.com/HorizonBrute/Standardized_AI_Looping_Language-SAILL/tree/main/skills/test_saill_in_skill
- **Website:** https://horizonbrute.github.io/Standardized_AI_Looping_Language-SAILL/

## Install

```sh
agentstack add skill-horizonbrute-standardized-ai-looping-language-saill-test-saill-in-skill
```

Requires the [AgentStack CLI](https://agentstack.voostack.com/docs/cli). Works with Claude Code, Cursor, and any MCP-compatible agent.

## About

# Skill: /test_saill_in_skill

**Model preference:** `#midcost`

"For every dir with a trace nonce file, send a haiku agent to report agents.md files loaded."

### Nonce Trace Audit

1. Scanner (#lowcost) — globs `**/testing_nonce.md` under -context:root-; emits directory list as -context:dirs-.
2. Readers[ Nonce-Reader (#lowcost, parallel) per -context:dirs- ] (wait) — one haiku agent per dir; reads testing_nonce.md and walks parent dirs for agents.md trace lines; returns CSV row: `dir,trace1|trace2|...,nonce`.
3. Synthesizer (#midcost) — collects CSV rows; builds fenced markdown directory tree (nonce ✓, chain depth per node, MISSING flagged).
4. Writer (#lowcost) — writes tree to `documentation/lastrun_dirtree_check.md` with run header; appends `sha256: `.

**Send the Nonce Trace Audit team against -context-**

## Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

- **Author:** [HorizonBrute](https://github.com/HorizonBrute)
- **Source:** [HorizonBrute/Standardized_AI_Looping_Language-SAILL](https://github.com/HorizonBrute/Standardized_AI_Looping_Language-SAILL)
- **License:** MIT
- **Homepage:** https://horizonbrute.github.io/Standardized_AI_Looping_Language-SAILL/

Install and usage instructions live in the source repository linked above.

## Pricing

- **Free** — Free

## Security capabilities

Automated source analysis of v0.1.0 — what this tool can access:

- **Network access:** no
- **Filesystem access:** no
- **Shell / process execution:** no
- **Environment & secrets:** no
- **Dynamic code execution:** no

*"Yes" means the capability is present in the source — more access means more to trust, not that it is unsafe.*


## Versions

- **0.1.0** — security scan: passed — Imported from the upstream source.

## Links

- Listing page: https://agentstack.voostack.com/l/skill-horizonbrute-standardized-ai-looping-language-saill-test-saill-in-skill
- Seller: https://agentstack.voostack.com/s/horizonbrute
- Browse the marketplace: https://agentstack.voostack.com/browse

---
Listed on AgentStack — the marketplace for AI agent skills and MCP servers. Every listing is security-reviewed. Creators keep 70%.