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 instructions/anmolnagpal/devops-skills/claude-mdgit clone --depth 1 https://github.com/anmolnagpal/devops-skillsWrote 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.
[](https://agentmods.dev/instructions/anmolnagpal/devops-skills/claude-md)<a href="https://agentmods.dev/instructions/anmolnagpal/devops-skills/claude-md"><img src="https://agentmods.dev/badge/instructions/anmolnagpal/devops-skills/claude-md.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.03536 | $0.03536 |
| Opus 5 | $0.01768 | $0.01768 |
| Sonnet 5 | $0.00707 | $0.00707 |
| Haiku 4.5 | $0.00354 | $0.00354 |
Grade B, and why
devops-skills CLAUDE.md scanned grade B with 2 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 4d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
- `scripts/set-aws-profile.sh` uses inline Python to patch `~/.claude/settings.json`; it updates `AWS_PROFILE` for `eks-mcp-server` and `billing-mcp-server` Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
/bin/bash -c "$(curl -fsSL .../bootstrap.sh)" -- --all # claude + cursor + codex How it starts
The opening of the file, as written. The whole thing — 230 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
Git workflow (MUST follow)
These rules apply to every push originating from this repo. They override default agent behavior.
- Never push directly to
main. Always create a branch (feat/<name>,fix/<name>,chore/<name>) and open a pull request. - No
Co-Authored-Bytrailers. No "🤖 Generated with Claude Code" footers. No AI attribution of any kind in commit messages or PR bodies. Commits read as authored solely by the user. - Use the repo's
git config user.name/user.email. Do not set or override identity per-commit. If unset, ask the user before configuring. - One logical change per branch / PR. Don't bundle unrelated edits.
- Commit message format — imperative subject (≤72 chars), blank line, body explaining the why. Example:
Pin Bun install to the oven-sh tap Bare `brew install bun` resolves to wrong formula on some Homebrew versions. Use the official tap explicitly so installs are deterministic. - Confirm before pushing. If the agent (Claude / Cursor / Codex) is about to push, list the commit summary + diff stat and ask "OK to push?" first.
- Never
--forcepush to a shared branch. Force-push only to your own short-lived feature branches, and only after confirming with the user. - PR before merge. Even for your own commits — open a PR, let CI run, then merge.
Writing style
- Never use em dash (—) or literal double-hyphen (--) in output, code comments, commit messages, docs, or skill content. Use commas, periods, or parentheses instead.
- Never use common AI filler words: delve, leverage, robust, seamless, utilize, foster, tapestry, testament, boasts, elevate, unlock, unleash, dive in, game-changer, in today's world, it's important to note. Use plain direct words instead.
Dependency / tool versions
- Before adding or pinning any dependency, package, tool version, or base image (Python, Go, Rust, Bash tooling, npm, Docker images, GitHub Actions, Terraform providers/modules, etc), check GitHub releases/tags or the official registry for the latest stable version first, then use that version. Do not guess or use a remembered/training-data version.
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.
- 4d ago First seen · 230 lines · 3,536 tokens per session scan B 7d50f65b0334
devops-skills CLAUDE.md is an instructions file published in the GitHub repository anmolnagpal/devops-skills (8 stars, last pushed 5d ago), licensed MIT. It adds 3,536 tokens to every session, about $0.0177 per session on Opus 5. A static security scan graded it B with 2 findings (reads agent configuration directories, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other instructions, from other repositories
aidevops codacy.instructions.md
Configuration for AI behavior when interacting with Codacy's MCP Server.
aws-bench AGENTS.md
AGENTS.md instructions for aws-bench/aws-bench, covering agents.md, setup, commands, project structure and code style.
drawio-ai-kit AGENTS.md
Instructions for sparklabx/drawio-ai-kit, covering repository guidelines, tech stack & runtime and code conventions & common patterns.
spring-ai-agentcore AGENTS.md
AGENTS.md instructions for spring-ai-community/spring-ai-agentcore, covering agents.md, project overview, architecture, key components and artifact store classes.
awsmux AGENTS.md
Instructions for 0hardik1/awsmux, covering agents.md, what awsmux is, build, test, verify, layout and the safety model — invariants you must not weaken.
trellis AGENTS.md
Instructions for craigcossairt/trellis, covering agents.md , project, what i need from agents, current state - source of truth pointers and tech stack.