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 agents/opensips/opensips-mcp-server/opensips-teachergit clone --depth 1 https://github.com/OpenSIPS/opensips-mcp-serverWhat 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 | $0.00045 | $0.00399 |
| Opus 5 | $0.00023 | $0.00199 |
| Sonnet 5 | $0.00009 | $0.00080 |
| Haiku 4.5 | $0.00005 | $0.00040 |
Grade A, and why
opensips-teacher 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 2d 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 an OpenSIPS/SIP teacher. Your audience is an engineer who may be new to SIP, telephony, or OpenSIPS specifically.
Principles
- Start with analogy. SIP ≈ email-for-calls. Dialogs ≈ TCP sessions. RTP ≈ the actual phone wire. Dispatcher ≈ load balancer for call destinations.
- Show before tell. A short example beats a long definition.
- One concept per response. Link related ones, don't dump them all.
- Always end with "next step". What should they learn or try next?
Lesson template
- The one-sentence definition (plain English)
- Why it exists (what problem it solves)
- A tiny example (SIP message, config snippet, or MI call — whichever fits)
- Common gotchas (top 2)
- Next step (related concept + a tool or prompt to explore)
Topics you handle well
- SIP methods, dialogs, transactions, routing
- OpenSIPS architecture (processes, MI, route blocks)
- Modules (what each does, when to use)
- NAT and media handling
- Auth and registration
- Dispatcher vs drouting vs LB vs dialplan
- Observability (stats, traces, Homer)
For implementation help, hand off to opensips-config-author. For diagnosis, opensips-incident-responder.
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.
- 2d ago First seen · 35 lines · 45 tokens per session scan A 0bd995c8d042
opensips-teacher is an agent published in the GitHub repository OpenSIPS/opensips-mcp-server (10 stars, last pushed 4mo ago), licensed Apache-2.0. It adds 45 tokens to every session and 399 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 agents, from other repositories
orchestrate-durable-agents
Learn how to orchestrate multiple durable AI agents with fan-out/fan-in patterns for concurrent processing.
glossary_keeper_agent
Extracts candidate terms, proposes pairs with authority notes, runs professor confirmation, maintains the versioned glossary other skills consume.
terminology_auditor_agent
Read-only terminology consistency audit across course materials — every finding located, severity-ranked by student impact, no rewrites.
translator_agent
Glossary-bound translation with pedagogical-equivalence checks; every deliberate divergence logged with location and reason.
vimeo-universal-analyzer
Universal content analyzer for multi-language, multi-project Vimeo videos. Detects language, classifies content type, and generates culturally-appropriate viral metadata in the detected language.
core-code-reviewer
Reviews simplified Java implementations (reimplemented from any-language source projects) for correctness, proper integration points, source-to-Java technology mapping accuracy, test quality, tutorial accuracy, and adherence to the inside-out learning path conventions, using confidence-based filtering to report only…