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/jesusconwellpy/secagent-skills/secagent-knowledgenpx skills add JesusConwellpy/secagent-skills --skill secagent-knowledgegit clone --depth 1 https://github.com/JesusConwellpy/secagent-skillsWrote 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/jesusconwellpy/secagent-skills/secagent-knowledge)<a href="https://agentmods.dev/skills/jesusconwellpy/secagent-skills/secagent-knowledge"><img src="https://agentmods.dev/badge/skills/jesusconwellpy/secagent-skills/secagent-knowledge.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 | $0.00037 | $0.01382 |
| Opus 5 | $0.00018 | $0.00691 |
| Sonnet 5 | $0.00007 | $0.00276 |
| Haiku 4.5 | $0.00004 | $0.00138 |
Grade A, and why
secagent-knowledge 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 5d 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 — 161 lines — stays where its author put it; the contents beside it link to each section on GitHub.
SecAgent Knowledge — Local LLM-Wiki
Loading this SKILL gives you a complete local knowledge management system. This is not documentation — you actually create and maintain a structured wiki.
Bootstrap (first load)
1. Determine wiki root:
WIKI_ROOT = {workspace}/wiki
2. Create directory skeleton:
mkdir -p {WIKI_ROOT}/entities/{ips,domains,cves,tools}
mkdir -p {WIKI_ROOT}/concepts/{attack-methods,defense-tech,design-patterns}
mkdir -p {WIKI_ROOT}/discoveries/{scan-results,vuln-findings,pocs}
mkdir -p {WIKI_ROOT}/synthesis/{reports,analysis,summaries}
3. Initialize INDEX.md at {WIKI_ROOT}/INDEX.md:
"# Wiki Index\n\nLast updated: {timestamp}\n\n## Entities\n\n## Discoveries\n\n## Synthesis\n"
4. Confirm: "Wiki ready at {WIKI_ROOT}. Starting knowledge production."
The Knowledge Loop: Produce → Structure → Retrieve → Reuse
Produce (on every discovery)
Trigger → Action:
IP + port + service found → write entities/ips/{ip}.md
Product + version identified → search CVEs first, then write entities/cves/{cve-id}.md
CVE matched → write entities/cves/{cve-id}.md
Vulnerability confirmed → write discoveries/vuln-findings/F{###}.md
PoC successful → write discoveries/pocs/{finding-id}-poc.md
Sub-agent returns results → extract findings → write to matching directory
Attack pattern identified → write concepts/attack-methods/{technique}.md
File naming: use entity identifiers (IP, CVE ID, Finding ID), not descriptive titles.
After each write: append to the matching section in INDEX.md.
Structure (write with exact templates)
IP Entry (wiki/entities/ips/{ip}.md):
# {ip}
- **First seen**: {timestamp}
- **Last seen**: {timestamp}
- **Hostname**: {hostname or "unknown"}
- **OS**: {os or "unknown"}
## Open Ports
| Port | Service | Version | CVE |
|------|---------|---------|-----|
| {port} | {service} | {version} | {cve or "—"} |
## Findings
- [{finding-id}](../discoveries/vuln-findings/{finding-id}.md): {one-line summary}
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.
- 5d ago First seen · 161 lines · 37 tokens per session scan A 727f4cb722ce
secagent-knowledge is a skill published in the GitHub repository JesusConwellpy/secagent-skills (2 stars, last pushed 3mo ago), licensed MIT. It adds 37 tokens to every session and 1,382 once invoked, about $0.0002 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
osint-recon
OSINT 开源情报收集知识库 — 四维信息收集模型(服务器→网站→域名→人员),维度四(人员信息)条件触发.
secknowledge-skill
Web+AI 安全测试知识库。融合 WooYun 88,636 案例 + 先知 L1-L4 方法论 + GAARM 150 风险 OWASP Top 10 (LLM/ASI/WSTG)。 TRIGGER when 任务是实战安全测试:渗透测试、漏洞挖掘/利用、红队攻防、安全审计 (SAST/DAST)、 CTF、AI/LLM 安全测试 (Prompt 注入/越狱/MCP/Agent/沙箱逃逸)。用户明确给出测试目标 (URL/代码/模型/Agent 架构) 且意图是"测试/审计/挖漏洞/利用"。 DO NOT trigger: 安全概念讨论("什么是 XSS"、"SQL 注入原理是什么")→ 普通问答 非安全性质的 code…
performing-ai-assisted-vulnerability-discovery
Using LLMs to accelerate vulnerability research and pentest workflows — generating syntax-valid fuzzing seeds and evolving grammars, fine-tuned mutation dictionaries, parallel agent-based proof-of-vulnerability generation, and evidence-driven passive analysis of real HTTP traffic via the Burp MCP server. Covers…
client-reverse
客户端逆向与Burp重放 — 复杂客户端签名恢复、加密还原、请求链追踪、稳定重放,适用于已授权安卓App渗透测试、浏览器JS签名、桌面客户端逆向.
rapid-checklist
渗透速查与Payload — 快速Payload家族、绕过提醒、验证顺序、常见测试卡片,适用于已知测试方向后快速查找.
redteam-cors-miscfg-detail-pack
Domain routing and boundary guidance for authorized CORS misconfiguration testing, including reflected origins, null origins, subdomain trust, and credential exposure. Use when a task belongs to the CORS testing domain and needs scope, evidence, pivot, or exit criteria.