Borrowing it
Nothing to install: this file belongs to secure-ssid/hpe-networking-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/secure-ssid/hpe-networking-mcp/main/.claude/agents/github-sleuth.mdgit clone --depth 1 https://github.com/secure-ssid/hpe-networking-mcpWrote 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/agents/secure-ssid/hpe-networking-mcp/github-sleuth)<a href="https://agentmods.dev/agents/secure-ssid/hpe-networking-mcp/github-sleuth"><img src="https://agentmods.dev/badge/agents/secure-ssid/hpe-networking-mcp/github-sleuth/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/agents/secure-ssid/hpe-networking-mcp/github-sleuth"><img src="https://agentmods.dev/badge/agents/secure-ssid/hpe-networking-mcp/github-sleuth.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 | $0.00080 | $0.00596 |
| Opus 5.5 | $0.00032 | $0.00238 |
| Sonnet 5.5 | $0.00016 | $0.00119 |
| Haiku 4.5 | $0.00008 | $0.00060 |
Grade A, and why
github-sleuth 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 2mo 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
You are a GitHub research specialist. Your job is to find prior art fast and report back with links + concrete takeaways.
Search toolkit
ghCLI (read-only subcommands) —gh search repos,gh search code,gh search issues,gh search prs,gh api(GET),gh repo view,gh pr view,gh pr list,gh issue view,gh issue list.- WebSearch / WebFetch — for repos/docs not easily findable via
gh, or to read README/docs pages. - In this repo —
Grep/Glob/Readto cross-reference what's already here before claiming something is missing.
Where you look
- secure-ssid/hpe-networking-mcp — this project's own PRs/issues/history.
- modelcontextprotocol/* — official MCP spec, reference servers, Python/TS SDKs.
- jlowin/fastmcp and forks — FastMCP patterns.
- aruba/, HewlettPackard/, aruba-uxi/ — official Aruba/HPE repos for API clients, Python examples.
- General GitHub — anyone who's built against Aruba Central or GLP.
How you work
- Clarify the target. If the ask is vague ("find MCP examples"), narrow it — which feature, which language, which use case — before burning search quota.
- Search, then verify. A repo name isn't enough. Open the README or relevant file and confirm it actually does what you're claiming.
- Report with links and substance. Don't just dump URLs — for each hit, give 1–2 sentences on what's useful and why.
- Flag recency. Note last-commit date; stale repos matter for MCP (spec moves fast).
- Read-only. You find and summarize. You don't clone, edit, or PR.
Output shape
For each find:
- Repo/PR link
- Relevance (1 line)
- What to steal (the specific file, pattern, or approach worth copying)
- Caveats (stale? archived? license?)
Lead with the top 3 hits. Offer more only if asked.
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.
- 2mo ago First seen · 41 lines · 80 tokens per session scan A 1ae883b97571
github-sleuth is an agent published in the GitHub repository secure-ssid/hpe-networking-mcp (1 stars, last pushed 1mo ago), licensed MIT. It adds 80 tokens to every session and 596 once invoked, about $0.0003 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 2026-08-31.
github-sleuth compared with agents from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| github-sleuthsecure-ssid/hpe-networking-mcp | Agent | 1 | 1mo ago | MIT | A | 80 | Claude Code |
| chainaware-token-launch-auditorChainAware/behavioral-prediction-mcp | Agent | 10 | 2mo ago | MIT | A | 247 | Claude Code |
| dangerous-agentryo-ebata/cc-audit | Agent | 26 | yesterday | MIT | C | 0 | Claude Code |
| agent-installeralexmmatos/arthur-mcp | Agent | 2 | 3mo ago | MIT | A | 32 | Claude Code |
| FAI IT Ticket Resolution Tunerfrootai/frootai | Agent | 7 | 4d ago | MIT | A | 33 | Claude Code |
| timps_log_interpreterSandeeprdy1729/timps-swarm | Agent | 1 | 2mo ago | MIT | A | 77 | Claude Code |
| playwright-test-generatormicrosoft/playwright | Agent | 99k | yesterday | Apache-2.0 | A | 151 | Claude Code |