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 telagod/code-abyss --skill analyzing-securitygit clone --depth 1 https://github.com/telagod/code-abyssWrote 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/telagod/code-abyss/analyzing-security)<a href="https://agentmods.dev/skills/telagod/code-abyss/analyzing-security"><img src="https://agentmods.dev/badge/skills/telagod/code-abyss/analyzing-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/telagod/code-abyss/analyzing-security"><img src="https://agentmods.dev/badge/skills/telagod/code-abyss/analyzing-security.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00062 | $0.01008 |
| Opus 5.5 | $0.00025 | $0.00403 |
| Sonnet 5.5 | $0.00012 | $0.00202 |
| Haiku 4.5 | $0.00006 | $0.00101 |
Grade A, and why
analyzing-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 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.
What it actually says
安全校验关卡
判断先于执行：决定「是否做 / 选什么 / 如何取舍」（栈、方案、架构、权衡）前，先读领域判断内核
skills/_kernel/security/SKILL.md——它管 judgment，本秘典管 execution；冲突时以内核判断为准。
自动化扫描捕捉模式，但严重度判定与处置取决于上下文——sink、信任边界、补偿控制。
何时使用
| 场景 | 必跑 | 理由 |
|---|---|---|
| 新模块落地 | ✅ | 引入新攻击面 |
| 安全相关变更 | ✅ | 直接触及威胁面 |
| 重构完成 | ✅ | 防止重构引入退化 |
| 提交前（含敏感数据/外部输入处理） | ✅ | 最后一道闸 |
| 攻防任务交付 | ✅ | 验收前自检 |
| 仅文档/样式改动 | ❌ | 无攻击面变化 |
何时不使用
- 依赖更新（用 SCA 工具如
npm audit、pip-audit，不是模式扫描） - 运行时漏洞（用 DAST，不是静态扫描）
- 配置审计（用 CIS Benchmark 或专用工具）
解读输出
严重度（critical / high / medium / low）+ 类别（注入 / 敏感信息 / XSS / 反序列化 / 路径遍历 / SSRF / 弱加密 / 不安全随机 / 调试残留）。
必修
- Critical（SQL 注入、命令注入、硬编码密钥、AWS Key、私钥）→ 阻断交付，无例外。
- High（XSS、反序列化、路径遍历、SSRF）→ 修复或显式接受风险（需 DESIGN.md 留痕 + 补偿控制）。
上下文降级条件
- Medium/Low 可在 DESIGN.md 标注「已知/已评估」后保留。判据：
- 弱加密 MD5/SHA1 用于非安全场景（如 hash bucket）→ 可接受
random用于非安全场景（如 jitter）→ 可接受- 调试残留在 dev-only 构建 → 可接受，prod 构建必须剔除
假阳处理
每条规则均有 excludePattern，若仍误报：
- 检查命中文本是否真为 sink（看上下文，不只是模式）
- 若确认假阳，在 DESIGN.md 记录 + 行内注释（
// nosec: <规则 ID> <理由>）
与其他 skill 联动
- 命中 critical/high → 同步触发 securing-systems 路由的对应秘典（如 SQL 注入查
pentest.md） - 新模块场景 → 与 verifying-modules 串行，先扫安全再校验文档
- 变更场景 → 与 analyzing-changes 串行，先看变更范围再决定扫描深度
使用
node scripts/security_scanner.js <路径> # 默认全扫
node scripts/security_scanner.js <路径> -v # 详细，含命中代码片段
node scripts/security_scanner.js <路径> --json # 机读格式，供 CI
node scripts/security_scanner.js <路径> --exclude vendor,dist
完整规则矩阵、危险模式速查、误报豁免清单详见 references/rules.md。
收口
Critical/High 必修后方可交付。安全决策须于 DESIGN.md 记录：威胁模型、信任边界、已知风险、补偿控制。
What ships with it
3 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.
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 · 75 lines · 62 tokens per session scan A b8e9c03d60ec
analyzing-security is a skill published in the GitHub repository telagod/code-abyss (243 stars, last pushed 3mo ago), licensed MIT. It adds 62 tokens to every session and 1,008 once invoked, about $0.0002 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 2026-08-30.
Other skills, from other repositories
code-review
Use when the user EXPLICITLY asks for a lightweight pass, or for feedback/audit modes. Triggers: 'quick review', 'light review', 'look over this', '--quick', 'check my work', 'self-review before PR', 'review my code', 'audit this code', 'PR comments to address', 'reviewer said', 'address feedback', 'review PR #X…
fact-checking
Use when verifying technical claims in code, docs, or comments before merge. Triggers: 'is this claim correct', 'verify this', 'fact check', 'is this accurate', 'check these assertions', 'are these comments true'. NOT for: checking if AI hallucinated references (use dehallucination).
adversarial-review
Use when dispatching a subagent to re-check work against external feedback (PR review comments, audit findings, multi-comment review cycles, 'did I really address X' verifications). Triggers: 'verify all the review comments are addressed', 'check that I really fixed all the audit findings', 'did I miss anything from…
executing-plans
Use when you have an implementation plan ready to execute. Triggers: 'run the plan', 'start building', 'execute the tasks', 'implement the steps', 'next task in the plan', 'work through the plan'. Also invoked by develop after planning phase completes. NOT for: creating plans (use writing-plans).
distilling-prs
Use when triaging, categorizing, or summarizing PR changes to decide where human attention should go. Triggers: 'summarize this PR', 'what changed in PR #X', 'triage PR', 'which files need review', 'PR overview', 'categorize changes', or pasting a PR URL. NOT for: judging code quality or producing findings on a branch…
reviewing-prs
Load before dispatching any subagent to review or triage a pull request, to pick the correct file version for the branch and worktree state. Required by: advanced-code-review (PR mode), code-review (--pr), distilling-prs (Phase 2), each of which names this skill at its dispatch point. Also use directly when: 'review…