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 marcoguillermaz/Tierward --skill skill-securitygit clone --depth 1 https://github.com/marcoguillermaz/TierwardWrote 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/marcoguillermaz/tierward/skill-security)<a href="https://agentmods.dev/skills/marcoguillermaz/tierward/skill-security"><img src="https://agentmods.dev/badge/skills/marcoguillermaz/tierward/skill-security/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/marcoguillermaz/tierward/skill-security"><img src="https://agentmods.dev/badge/skills/marcoguillermaz/tierward/skill-security.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 | $0.00069 | $0.01883 |
| Opus 5 | $0.00034 | $0.00941 |
| Sonnet 5 | $0.00014 | $0.00377 |
| Haiku 4.5 | $0.00007 | $0.00188 |
Grade A, and why
skill-security 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 9d 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 — 246 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Scope: scan a skill package (SKILL.md + any associated scripts) for security vulnerabilities before installation. Covers 64 patterns across 16 categories using SkillSpector (NVIDIA, Apache 2.0).
Out of scope: application security audits (use /security-audit instead), scanning the project's own source code, fixing identified vulnerabilities.
Do NOT modify any file during the scan.
Step 0 — Preflight: verify SkillSpector availability
Check availability in this order and announce which execution path will be used:
Path A — SkillSpector (pip)
python3 --version 2>&1 | head -1
pip show skillspector 2>&1 | grep -E "^(Name|Version):"
If both return successfully (Python 3.12+ AND skillspector installed): proceed with Path A. Announce: Using SkillSpector [version] via pip.
Path B — Docker fallback
If Path A is not available:
docker --version 2>&1 | head -1
docker image ls skillspector 2>&1 | grep -c skillspector
If Docker is available: instruct the user to build the image if not already built:
Docker image not found. Build it with:
git clone https://github.com/NVIDIA/skillspector.git /tmp/skillspector
docker build -t skillspector /tmp/skillspector
Then re-run this skill.
If the image exists: proceed with Path B. Announce: Using SkillSpector via Docker.
Neither available
If neither Path A nor Path B is usable, stop and output:
SkillSpector is not available. Install it with one of:
pip install skillspector # requires Python 3.12+
pipx install skillspector # isolated install
Or build the Docker image:
git clone https://github.com/NVIDIA/skillspector.git /tmp/skillspector
docker build -t skillspector /tmp/skillspector
Then re-run: /skill-security [path]
Do not proceed further.
Step 1 — Resolve scan target
Parse $ARGUMENTS for a path and the --llm flag.
| Argument pattern | Scan target | LLM mode |
|---|---|---|
| (none) | Current directory (.) |
disabled |
./path/to/skill/ |
Specified directory | disabled |
./SKILL.md |
Specified file | disabled |
--llm |
Current directory | enabled |
./path/to/skill/ --llm |
Specified directory | enabled |
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.
- 9d ago First seen · 246 lines · 69 tokens per session scan A 5b92a9033236
skill-security is a skill published in the GitHub repository marcoguillermaz/Tierward (4 stars, last pushed 2d ago), licensed MIT. It adds 69 tokens to every session and 1,883 once invoked, about $0.0003 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 skills, from other repositories
harness-engineering
Use when the user asks to improve, fix, or build their repository's AI harness — AGENTS.md, rules, skills, commands, hooks, guardrails, CI sensors — or to act on harness-score audit findings and raise their maturity level.
codex-hud
Show Codex workspace context with local config, git state, hooks, and project hints. Standalone mode can show an expanded snapshot; patched Codex TUI footer mode is single-line. Use when the user says "codex-hud", "show Codex HUD", "status HUD", "workspace snapshot", or asks for richer Codex context.
address-conductor-comment
A workflow for handling pending Conductor code-review comments, including reading their discussion and assigning changes to subagents when appropriate.
explain-comment
A skill that reads a specified file or code range and adds explanatory comments in Japanese. The comments use a question style and focus on important logic, design choices, and side effects.
saleae-mcp-debugger
Use this skill for hardware-in-the-loop firmware capture and decode workflows through the Saleae Logic 2 MCP server.
build-feature
Full pipeline: evaluation -> spec -> implementation -> review -> QA.