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/rez-f/aws-devops-study-kb/claude-mdgit clone --depth 1 https://github.com/rez-f/aws-devops-study-kbWrote 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/rez-f/aws-devops-study-kb/claude-md)<a href="https://agentmods.dev/instructions/rez-f/aws-devops-study-kb/claude-md"><img src="https://agentmods.dev/badge/instructions/rez-f/aws-devops-study-kb/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 | $0.02007 | $0.02007 |
| Opus 5 | $0.01004 | $0.01004 |
| Sonnet 5 | $0.00401 | $0.00401 |
| Haiku 4.5 | $0.00201 | $0.00201 |
Grade A, and why
aws-devops-study-kb CLAUDE.md 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 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.
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.
How it starts
The opening of the file, as written. The whole thing — 116 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.
What this is
A personal memo knowledge base for AWS DevOps Engineer Professional exam prep. AI agents (Claude
Code, OpenWebUI, or any other MCP- or OpenAPI-compatible agent, e.g. a custom Telegram bot) write
well-structured memos here as a side effect of answering study questions — the user never authors
memos by hand. No folders: everything is a flat, tagged, full-text-searchable list. See
README.md for the component overview and docs/tag-conventions.md / docs/deployment.md for
tagging rules and the Docker Compose + Cloudflare Tunnel deployment.
Commands
npm run dev # tsx watch src/server.ts — http://localhost:8000
npm test # vitest run — all suites
npx vitest run test/api.test.ts # one suite
npx vitest run -t "creates a memo" # by test name (any file)
npx vitest watch # watch mode while iterating
npm run typecheck # tsc --noEmit
npm run build # tsc + copies src/web/public assets into dist/web/public
npm run generate:openapi # writes openapi/generated.json from the live zod schemas
npm run migrate # runs migrations/*.sql standalone against DB_PATH (or ./data/memos.db)
docker compose up -d --build app # build+run just the app service (no cloudflared token needed)
Minimum env for local dev: API_BEARER_TOKEN, SESSION_COOKIE_SECRET (dev fallbacks exist in
src/core/config.ts but shouldn't be relied on past local testing). See .env.example.
Agent behavior policy (src/core/agentPolicy.ts) is a second "single source of truth" file
alongside schemas.ts — one text block ("search before answering, save afterward unprompted, use
the tag convention") surfaced via MCP's protocol-level instructions field (src/mcp/server.ts)
and appended to the OpenAPI spec's info.description (src/api/app.ts). This only nudges
clients that read either field; see docs/agent-persona.md for the explicit system-prompt text
that actually needs to be configured per agent surface (not part of this codebase).
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 · 116 lines · 2,007 tokens per session scan A 13dbd9468ff6
aws-devops-study-kb CLAUDE.md is an instructions file published in the GitHub repository rez-f/aws-devops-study-kb (1 stars, last pushed 15d ago), licensed MIT. It adds 2,007 tokens to every session, about $0.0100 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 2026-08-31.
Other instructions, from other repositories
Ech0 CLAUDE.md
Claude Code instructions for lin-snow/Ech0, covering claude.md, project overview, common commands, backend (repo root) and other modules.
Ech0 AGENTS.md
AGENTS.md instructions for lin-snow/Ech0, covering agents.md, what this is, commands you'll need, backend (run from repo root) and frontend (just web … from repo root, or pnpm from web/).
flashcards-open-source-app AGENTS.md
Instructions for kirill-markin/flashcards-open-source-app, covering flashcards-open-source-app, product direction, platform plan, testing philosophy and release gates and monitoring.
cloud-finops-skills CLAUDE.md
Claude Code instructions for OptimNow/cloud-finops-skills, covering claude.md, what this repo is, repository structure, content update pipeline and lessons learned.
ai-tutorials CLAUDE.md
Claude Code instructions for ravsau/ai-tutorials, covering ai-tutorials, what this project does, key technologies, main structure and how to run.
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.