Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →jeremylongshore/langchain-incident-runbook
Triage LangChain 1.0 / LangGraph 1.0 production incidents — LLM-specific SLOs, provider outage runbook, latency spike decision tree, cost-overrun response, agent loop containment. Use during an on-call page, in a post-mortem, or writing the team's first LLM runbook. Trigger with "langchain incident", "llm on-call", "langchain slo", "langchain outage", "langchain cost spike", "langchain agent loop".
Passed 18 of 22 test cases with the skill, and 8 of 22 without it.
and 12 more in the full report
10 fixed8 passed either way4 still failing0 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 10 test cases the skill fixed. Same model, same prompt, with and without the skill.
Following an agent runbook incident, our SRE team needs to compile a post-incident debug bundle. What four essential artifacts must be captured in the bundle within 30 minutes of the all-clear?
| Checked | Without skill | With skill |
|---|---|---|
| The debug bundle includes LangSmith trace URLs. | Missed | Passed |
| The debug bundle includes Prometheus dashboard screenshots. | Missed | Passed |
| The debug bundle includes agent configuration parameters. | Passed | Passed |
The instructions your model reads when the skill loads.
3:07am. PagerDuty: "LangChain p95 latency > 10s for 5 minutes." You open LangSmith,
filter by service="triage-agent" over the last 15 minutes, and the first trace
is 43 seconds long — an agent is on step 24 of 25 iterations, bouncing between
the same two tools on a vague user prompt ("help me with my account"). The cost
dashboard shows $400 spent in the last 10 minutes, up from a $6/hour baseline.
This is P10: create_react_agent defaults to recursion_limit=25 with no cost
cap; vague prompts never converge; the spend hits before GraphRecursionError
surfaces. First move is not to push a code fix — it is to flip
recursion_limit=5 via config reload and add a middleware token-budget cap per
session, then deal with the stuck sessions.
Or: same alert, different signature. p95 is healthy at 1.8s, but p99 is 12s and
spiky. The spikes correlate with instance starts in Cloud Run. P36: Python +
LangChain + embedding preloads = 5–15s cold start; Cloud Run scales to zero by
default, so first-request p99 is 10x p95. First move is --min-instances=1
(or a keepalive pinger), not more CPU.
The shape of the page decides the first move. This runbook gives you:
.with_fallbacks(backup) so failover is a
config flip, not a code change.recursion_limit tuning and middleware
token-budget caps so runaway agents stop burning cost before the
GraphRecursionError.langchain-debug-bundle) and write-up
template.Pinned: langchain-core 1.0.x, langgraph 1.0.x, langsmith 0.3+. Primary pain
anchors: P10 (agent runaway), P36 (cold start). Adjacent: P29 (per-process
rate limiter), P30 (max_retries=6 means 7 attempts), P31 (Anthropic cache RPM).
test cases passed, vs 8 / 22 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.