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 instructions/secure-ssid/hpe-networking-mcp/agents-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/instructions/secure-ssid/hpe-networking-mcp/agents-md)<a href="https://agentmods.dev/instructions/secure-ssid/hpe-networking-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/secure-ssid/hpe-networking-mcp/agents-md.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 | $0.03981 | $0.03981 |
| Opus 5 | $0.01990 | $0.01990 |
| Sonnet 5 | $0.00796 | $0.00796 |
| Haiku 4.5 | $0.00398 | $0.00398 |
Grade A, and why
hpe-networking-mcp AGENTS.md 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 today.
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 — 356 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent guidance for hpe-networking-mcp
This repository is managed by pika. The contract at
.project/contract.yaml declares the active profiles, the verification
commands, and the repository conventions; .project/profiles.lock pins
the exact profile packs in use.
Working in this repository
- Keep the contract, the lock, and the documentation spine in sync with every change.
- Record any deliberate deviation from a naming rule in
.project/exceptions.yaml; each record needs a rule ID, a rationale, an owner, and a review condition. - Never bypass the verification ladder: run
pika checkbefore declaring work done.
Conventions
- Branches:
{type}/{slug}with types feat, fix, docs, refactor, chore. - Pull requests stay draft until checks pass.
- Merge strategy: squash.
Driving pika
pika is a kernel that decides whether your changes are safe to keep. You propose; it verifies and commits. Nothing you assert counts as evidence — only a green verification ladder does.
Pick the command
| Situation | Command |
|---|---|
| Checks are failing and you want them fixed | pika improve |
| You have a goal to implement | pika work "<goal>" |
| A previous run was interrupted | pika resume <work-id> |
| A run or transaction was killed and left a lock | pika recover --apply |
| You want to know what is wrong before acting | pika doctor |
| You do not understand a rule, gate, or error code | pika explain <id> |
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.
- today First seen · 356 lines · 3,981 tokens per session scan A 4b5c1304d7a3
hpe-networking-mcp AGENTS.md is an instructions file published in the GitHub repository secure-ssid/hpe-networking-mcp (1 stars, last pushed yesterday), licensed MIT. It adds 3,981 tokens to every session, about $0.0199 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 2026-09-05.
Other instructions, from other repositories
mcp-java-sdk-examples AGENTS.md
AGENTS.md instructions for thought2code/mcp-java-sdk-examples, covering git commit rules and commit message format.
mcp-mssql AGENTS.md
AGENTS.md instructions for alyiox/mcp-mssql, covering agent instructions, commit messages, header, body and release tags.
hop CLAUDE.md
Instructions for danmartuszewski/hop: Use conventional commit format with imperative mood.
aruba-central-mcp copilot-instructions.md
Copilot instructions for shigechika/aruba-central-mcp, covering repository overview, build & validate, what to focus review on in this repo, 5. test conventions and 6. main.py shuts down via os.exit(0) on purpose.
aruba-central-mcp CLAUDE.md
Claude Code instructions for shigechika/aruba-central-mcp, covering claude.md, commands, architecture and conventions.
Anytype-MCP CLAUDE.md
Claude Code instructions for ohneben/Anytype-MCP, covering project instructions, github: always use the mcp tools, never raw http, why, creating a pull request and attribution: do not add it.