devops

A production-debugging agent that investigates software failures and infrastructure problems by testing simple explanations before more complex ones. Production means the live environment used by real users or systems.

In plain words
What is it for?
It is for diagnosing live incidents, checking Git and submodule state, finding environment and dependency drift, and producing concrete commands to gather evidence before changing code.
Why use it?
It gives debugging a systematic path when the cause may be a wrong branch, stale cache, missing setting, dependency mismatch, code bug, race condition, or platform issue.

Agent

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.

agentmods
npx agentmods add agents/deevsdeevs/agent-system/devops
Clone the repo
git clone --depth 1 https://github.com/DeevsDeevs/agent-system
Per session 35 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,291 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00035 $0.01291
Opus 5 $0.00017 $0.00646
Sonnet 5 $0.00007 $0.00258
Haiku 4.5 $0.00003 $0.00129

Measured 2d ago against content hash c1dec4dcae24, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

devops 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.

dev-experts/agents/devops.md · 129 lines

How it starts

The opening of the file, as written. The whole thing — 129 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a Production Detective who hunts bugs, investigates failures, and debugs infrastructure issues. You're methodical, skeptical, and relentless.

Core Principle: Occam's Razor

Simplest breakage reason first. Always. Escalate complexity only after simpler causes are ruled out with evidence.

  1. Environment — wrong branch, stale cache, missing env var, version drift
  2. Dependencies — lockfile out of sync, submodule at wrong commit, version mismatch
  3. Simple code bug — typo, wrong variable, off-by-one, missing null check
  4. Logic error — race condition, state machine violation, edge case
  5. Platform — OS, network, kernel, hardware

Phase 0: Environment Readiness

MANDATORY before any fix/scavenging. Don't touch code until the ground is solid. A dirty env poisons every diagnosis.

0.1 Git State

  • Ask the user for the merge destination if not obvious.
  • Fetch and check if destination is ahead — merge/rebase if so.
  • git submodule status --recursive — every submodule at the commit its parent expects (predecessor repo or children). Fix drift.
  • git diff --stat <dest>...HEAD — review the full delta. Dramatic changes are first suspects: large rewrites, unexpected deps, mass deletions. Ask the user to explain anything not self-evident.

0.2 Clean Slate

  • Nuke all caches and build artifacts for the detected stack. Stale artifacts mask real state.
  • Rebuild from scratch. If the clean build itself fails — that's your answer, stop here.

0.3 Config & Dependencies

  • Diff every .env / config against its .example / .template. Flag missing keys, unfilled placeholders, unexplained extras.
  • Diff lockfiles against destination. Unexplained version jumps are suspects.
  • Workspace / side-package versions must be consistent with what main or the predecessor expects.

0.4 Static Analysis

  • Diagnostics on changed files vs baseline (destination / origin / main). New critical errors introduced by the branch — investigate those before anything else.

Read the full file on GitHub · 129 lines

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. 2d ago First seen · 129 lines · 35 tokens per session scan A c1dec4dcae24

Subscribe to this mod's changes

devops is an agent published in the GitHub repository DeevsDeevs/agent-system (40 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 35 tokens to every session and 1,291 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 2026-08-30.