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 skills/markmhendrickson/neotoma/advisorynpx skills add markmhendrickson/neotoma --skill advisorygit clone --depth 1 https://github.com/markmhendrickson/neotomaWrote 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/markmhendrickson/neotoma/advisory)<a href="https://agentmods.dev/skills/markmhendrickson/neotoma/advisory"><img src="https://agentmods.dev/badge/skills/markmhendrickson/neotoma/advisory.svg" alt="Measured on agentmods" 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 | $0.00055 | $0.02525 |
| Opus 5 | $0.00028 | $0.01262 |
| Sonnet 5 | $0.00011 | $0.00505 |
| Haiku 4.5 | $0.00006 | $0.00252 |
Grade A, and why
advisory 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 6d 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 — 317 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Advisory
Use this skill to manage the full security advisory lifecycle. It enforces atomicity — advisory files, the README index, practices.md, GitHub issues, and the GHSA are updated together so nothing drifts.
Two modes:
/advisory new— File a new advisory for a discovered vulnerability/advisory close <slug> <version>— Mark an existing open advisory fixed in a release
When to Use
- A vulnerability has been identified and needs a disclosure record
- A fix has shipped for an open advisory and the record needs to be closed out
practices.mdis out of date with the current advisory set
Invoke with /advisory new or /advisory close <slug> <version>.
Constraints (apply throughout)
- MUST NOT include attack vector specifics, exploit steps, or payload details in any repo markdown file (
docs/security/advisories/,practices.md, GitHub issues). Those belong in the GHSA, which is private until coordinated disclosure. - Sanitized content describes: what category of bug, what prerequisites, what data is accessible, what the severity is, and what the fix entails — without explaining how to perform the access.
- MUST commit advisory files, README update, and practices.md update atomically in a single commit.
- MAY use
SKIP_TESTS=1on commit only when pre-existing, unrelated test failures on the branch would otherwise block the pre-commit hook for this docs-only change. Do not skip tests when your change could plausibly affect them.
Mode: /advisory new
Step 1: Gather inputs
Collect the following before writing anything:
| Field | Notes |
|---|---|
| Slug | <YYYY-MM-DD>-<short-kebab-description> — date is discovery date |
| CVE class | Category of vulnerability (e.g., tenant isolation bypass, auth middleware gap) |
| Affected version(s) | Which released tag(s) contain the bug |
| Prerequisites | What the attacker needs — be specific but sanitized |
| Impact | What data/functionality is exposed — no exploit steps |
| Severity | Low / Medium / High with reasoning |
| Remediation approach | What the fix entails — high level |
| Tracking issues | GitHub issue numbers for fix and gate gaps (create if they don't exist) |
| Gate gap | Which security gate(s) failed to catch this and why |
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.
- 6d ago First seen · 317 lines · 55 tokens per session scan A e5574482d617
advisory is a skill published in the GitHub repository markmhendrickson/neotoma (31 stars, last pushed 2d ago), licensed MIT. It adds 55 tokens to every session and 2,525 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 2026-08-30.
Other skills, from other repositories
security-observability
只读查询 agent-sec-cli 已落盘的历史安全事件记录，并据此生成会话级安全复盘。仅当用户显式要求查看或审计已发生的安全事件、安全告警、安全审计记录，或要求按 session/run/trace/时间/类别筛选与统计已有安全事件，或要求复盘某次会话的安全判定时使用。不用于扫描新内容：检查代码安全性用 code-scanner，检测 prompt 注入用 prompt-scanner，审查 Skill 安全状态用 skill-ledger。不要因为对话中出现“安全”“工具调用”等字样、或为了主动自查而触发。.
add-backend
Guide for adding a backend (Rust or Python) to the agent-sec-core security middleware. Use when creating new backends, integrating Rust or Python code into the security middleware, or extending with new backend actions.
skill-ledger
Skill 安全状态查看、风险暴露审查、用户决策、快速扫描认证与可选深度扫描。支持用户主动查看或扫描单个/全部 Skill；当用户要求 agent 安装 Skill 且安装成功后，必须自动对最终本地目录执行快速扫描认证。.
regex-mastery
Use this skill when writing regular expressions, debugging pattern matching,optimizing regex performance, or implementing text validation. Triggers on regex, regular expressions, pattern matching, lookahead, lookbehind, named groups, capture groups, backreferences, and any task requiring text pattern matching.
prompt-scanner
使用 agent-sec-cli 扫描 prompt 文本中的注入攻击和越狱尝试，返回结构化 JSON 扫描结果。当用户提到 prompt 安全、prompt 注入检测、越狱检测、提示词攻击检测，或者需要判断一段文本是否包含恶意 prompt 注入时，都应使用此技能。即使用户没有明确说"扫描"，只要涉及评估 prompt 文本的安全性，也应触发此技能。.
agentsight-bugfix
AgentSight fix issues 流程。了解问题 → 复现验证 → 根因分析 → 编码修复 → 验证修复，五阶段标准化调试迭代循环。确保 AI agent 遵循最小改动、逐轮验证的修复规范。.