Triage Latency Regression

Triage Latency Regression is a skill for Claude Code, Codex from bregman-arie/devops-sre-skills. It costs 21 tokens per session (418 once invoked), scanned A, original, Apache-2.0.

A troubleshooting guide for increased p95 or p99 latency. These percentiles describe how slow requests are for the slower part of users, rather than showing only the average.

In plain words
What is it for?
Use it to investigate logs, metrics, and traces; check saturation and errors; compare before and after changes; and verify that response times return to normal.
Why use it?
It helps compare the change with deployments and dependencies, separate queueing from computation, and form a likely root-cause hypothesis quickly.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to investigate logs, metrics, and traces; check saturation and errors; compare before and after changes; and verify that response times return to normal.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/bregman-arie/devops-sre-skills/triage-latency-regression
Install

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.

Any agent
npx skills add bregman-arie/devops-sre-skills --skill triage-latency-regression
Clone the repo
git clone --depth 1 https://github.com/bregman-arie/devops-sre-skills

Made for: Claude Code, Codex.

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 Triage Latency Regression

README.md
[![agentmods](https://agentmods.dev/badge/skills/bregman-arie/devops-sre-skills/triage-latency-regression/github.svg)](https://agentmods.dev/skills/bregman-arie/devops-sre-skills/triage-latency-regression)
Your own site
<a href="https://agentmods.dev/skills/bregman-arie/devops-sre-skills/triage-latency-regression"><img src="https://agentmods.dev/badge/skills/bregman-arie/devops-sre-skills/triage-latency-regression/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 Triage Latency Regression

Your own site · 80×15
<a href="https://agentmods.dev/skills/bregman-arie/devops-sre-skills/triage-latency-regression"><img src="https://agentmods.dev/badge/skills/bregman-arie/devops-sre-skills/triage-latency-regression.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 21 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 418 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 $0.00021 $0.00418
Opus 5 $0.00010 $0.00209
Sonnet 5 $0.00004 $0.00084
Haiku 4.5 $0.00002 $0.00042

Measured 11d ago against content hash 9b7524e44afd, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

Triage Latency Regression 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 11d 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.

skills/observability/triage-latency-regression/SKILL.md · 69 lines

What it actually says

When to use

Use when p95/p99 latency increases and you need a fast root-cause hypothesis.

Preconditions

  • You have access to metrics, logs, and (ideally) traces.

Procedure

  1. Confirm scope: which endpoints/operations, which regions, which customers.
  2. Compare before/after: deployment markers, config changes, dependency status.
  3. Decompose: queueing vs compute vs dependency latency.
  4. Validate saturation: CPU, memory, GC, thread pools, connection pools.
  5. Correlate errors/timeouts with latency.

Decision points

  • Strong correlation with a deploy: consider rollback.
  • Dependency latency increase: mitigate with timeouts, caching, failover.
  • Saturation increase: scale, shed load, or reduce work.

Verification

  • Latency returns to baseline and stays stable across multiple windows.
  • Error rate does not regress.

Rollback / undo

  • Roll back the most recent change correlated with the regression.
  • Revert performance tuning if it degrades correctness.

Escalation

  • Escalate to dependency owners if external system is the bottleneck.
  • Escalate to service owners if code changes are required.

Examples

Example queries to adapt:

Compare p95 latency now vs 1h ago; split by route, status code, and upstream.
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. 11d ago First seen · 69 lines · 21 tokens per session scan A 9b7524e44afd

Subscribe to this mod's changes

Triage Latency Regression is a skill published in the GitHub repository bregman-arie/devops-sre-skills (22 stars, last pushed 5mo ago), licensed Apache-2.0. It adds 21 tokens to every session and 418 once invoked, about $0.0001 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 2026-08-30.