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 automateyournetwork/netclaw --skill cisco-psirt-advisoriesgit clone --depth 1 https://github.com/automateyournetwork/netclawWrote 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/automateyournetwork/netclaw/cisco-psirt-advisories)<a href="https://agentmods.dev/skills/automateyournetwork/netclaw/cisco-psirt-advisories"><img src="https://agentmods.dev/badge/skills/automateyournetwork/netclaw/cisco-psirt-advisories/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/automateyournetwork/netclaw/cisco-psirt-advisories"><img src="https://agentmods.dev/badge/skills/automateyournetwork/netclaw/cisco-psirt-advisories.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 | $0.00093 | $0.02443 |
| Opus 5 | $0.00046 | $0.01222 |
| Sonnet 5 | $0.00019 | $0.00489 |
| Haiku 4.5 | $0.00009 | $0.00244 |
Grade A, and why
cisco-psirt-advisories 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 13d 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 — 206 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Cisco PSIRT Advisory Checks
Answers one question well: is the software this device is running affected by a Cisco security advisory?
Read this first — an empty result is not a clean bill of health
Every tool returns one of five outcome values. Two of them look similar in the data
and mean completely different things:
outcome |
What it means |
|---|---|
advisories_found |
Cisco has published advisories for this version |
none_published |
Cisco has published nothing for this version — NOT "the device is secure" |
normalisation_failed |
The version could not be parsed. Nothing was checked. |
unsupported_ostype |
Not a PSIRT OS family (includes iosxr and every non-Cisco platform) |
api_error |
Auth failure, rate limit, or a version Cisco has no record of |
Never report "no advisories" as "not vulnerable". none_published means Cisco has
published nothing matching that exact version string. It says nothing about
unpatched-but-unpublished issues, configuration weaknesses, or anything outside Cisco's
PSIRT process.
Never treat normalisation_failed or api_error as good news. Both mean the question
went unasked. In a fleet sweep, check the outcome_summary counts before telling anyone
the fleet is clean — devices in those two buckets were never checked at all.
The two-step chain
This server never contacts a device. It has no transport, no credentials for your network, and no way to read a version. You supply the version:
Step 1 — read the version off the device.
# Cisco platforms: pyATS
python3 $MCP_CALL "python3 -u $PYATS_MCP_SCRIPT" run_show_command \
'{"device_name":"cat9k-1","command":"show version"}'
# Anything else, or when pyATS has no parser: the multivendor CLI driver
python3 $MCP_CALL "python3 -u $MULTIVENDOR_MCP_SCRIPT" device_run_command \
'{"device":"rtr-1","command":"show version"}'
Step 2 — pass it here. Full show version output is fine; the banner is parsed.
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.
- 13d ago First seen · 206 lines · 93 tokens per session scan A 5ac9595b9f9b
cisco-psirt-advisories is a skill published in the GitHub repository automateyournetwork/netclaw (657 stars, last pushed 6d ago), licensed Apache-2.0. It adds 93 tokens to every session and 2,443 once invoked, about $0.0005 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…