agentmods.dev

opensips-mcp-server: Agent for Claude Code

.claude/agents/opensips-incident-responder.md

opensips-incident-responder is an agent for Claude Code from OpenSIPS/opensips-mcp-server. It costs 46 tokens per session (721 once invoked), scanned A, original, Apache-2.0.

An incident-response agent for OpenSIPS, software that routes internet phone calls, when a live production problem is affecting calls or registrations. It checks the running system first, then investigates configuration fixes.

In plain words
What is it for?
It investigates failed calls, dropped registrations, one-way audio, crashes, traffic spikes, 503 errors, registration storms, media problems, TLS errors, worker issues, memory pressure, and clustered nodes.
Why use it?
It helps stabilise an outage before changing configuration and uses runtime evidence to narrow down likely causes.

Agent for Claude Code

Written for Claude Code: installed under .claude/.

This is OpenSIPS/opensips-mcp-server's own configuration. It tells Claude Code how to work on opensips-mcp-server itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything opensips-mcp-server configures →

not rated 10repo 6mo ago A scan 46 tokens original Apache-2.0
View source ↗ OpenSIPS/opensips-mcp-server
Reuse

Borrowing it

Nothing to install: this file belongs to OpenSIPS/opensips-mcp-server. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/OpenSIPS/opensips-mcp-server/main/.claude/agents/opensips-incident-responder.md
Clone the repo
git clone --depth 1 https://github.com/OpenSIPS/opensips-mcp-server

Made for: Claude Code.

Wrote 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.

agentmods badge for opensips-incident-responder

README.md
[![agentmods](https://agentmods.dev/badge/agents/opensips/opensips-mcp-server/opensips-incident-responder/github.svg)](https://agentmods.dev/agents/opensips/opensips-mcp-server/opensips-incident-responder)
Your own site
<a href="https://agentmods.dev/agents/opensips/opensips-mcp-server/opensips-incident-responder"><img src="https://agentmods.dev/badge/agents/opensips/opensips-mcp-server/opensips-incident-responder/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.

agentmods 80×15 button for opensips-incident-responder

Your own site · 80×15
<a href="https://agentmods.dev/agents/opensips/opensips-mcp-server/opensips-incident-responder"><img src="https://agentmods.dev/badge/agents/opensips/opensips-mcp-server/opensips-incident-responder.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 46 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 721 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00046 $0.00721
Opus 5.5 $0.00018 $0.00288
Sonnet 5.5 $0.00009 $0.00144
Haiku 4.5 $0.00005 $0.00072

Measured 2mo ago against content hash 4f9ae72a2239, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

opensips-incident-responder 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.

.claude/agents/opensips-incident-responder.md · 45 lines

What it actually says

You are on-call for OpenSIPS. Stabilise first, fix root cause second.

Stabilisation phase

  1. health_check — is the process alive and serving MI?
  2. get_process_list — any stuck workers? Zombies?
  3. get_memory_stats — shared memory fragmentation or OOM risk?
  4. get_statistics group=core / tm / sl — reply code distribution now vs baseline
  5. cluster_status if clustered — any node offline?

Symptom-specific branches

Traffic spike / 503s:

  • pike_list_blocked — flood? Unblock legitimate sources
  • ratelimit_status — are we throttling?
  • dispatcher_list_db / lb_list — destinations still up?

Registration storm:

  • ul_dump — contact count trend
  • registrar_stats — failure/success rate

Media breakage:

  • rtpengine_show — sessions allocated, ports exhausted?
  • tls_handshake_errors if TLS-adjacent

Crash / restart loop:

  • docker_logs (if containerised) — last error lines
  • get_uptime — how often restarting

Output format

  • Incident summary (one sentence)
  • Current state (evidence lines from tools)
  • Stabilisation action (what to run now to stop the bleed)
  • Root cause candidates (top 3, ranked by evidence)
  • Fix plan (ordered steps, including rollback)

Do not apply config changes in production without explicit user confirmation. Runtime MI commands (unblock, reload, resize) are okay after triage.

Changes

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.

  1. 2mo ago First seen · 45 lines · 46 tokens per session scan A 4f9ae72a2239

Subscribe to this mod's changes

opensips-incident-responder is an agent published in the GitHub repository OpenSIPS/opensips-mcp-server (10 stars, last pushed 6mo ago), licensed Apache-2.0. It adds 46 tokens to every session and 721 once invoked, about $0.0002 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.

Debugging
Related

opensips-incident-responder compared with agents from other repositories

opensips-incident-responder next to 6 agents from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
opensips-incident-responderOpenSIPS/opensips-mcp-serverAgent106mo agoApache-2.0A46Claude Code
review-obsidian-guidelinesuphy/obsidian-reminderAgent662yesterdayMITA63Claude Code
debuggerTT-Wang/forgeAgent353d agoMITA17Claude Code
debuggerbostonaholic/rpikitAgent204d agoMITA28Claude Code
loom-advisorcosmix/loomAgent655d agoMITA53Claude Code
evolve-retrospectivemickeyyaya/evolve-loopAgent6yesterdayApache-2.0A51Claude Code
type-reconstructormarcosd4h/DeepExtractRuntimeAgent211mo agoMITA63Claude Code