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/martinkuhne/devstack/agents-mdgit clone --depth 1 https://github.com/MartinKuhne/devstackWhat 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 | $0.00483 | $0.00483 |
| Opus 5 | $0.00242 | $0.00242 |
| Sonnet 5 | $0.00097 | $0.00097 |
| Haiku 4.5 | $0.00048 | $0.00048 |
Grade A, and why
devstack AGENTS.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 yesterday.
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 — 51 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Principles
Scope
Work only on the item described in the prompt. Do not modify unrelated code or create unrelated commits.
Development process
- Check the quality gates before beginning work. If there are compilation errors or tests fail, repair the tests before beginning work (unless instructed to pause tests). You are allowed to disable tests that test functionality that is no longer a requirement. If substantial test changes were needed, commit the changes and exit.
- Create a detailed plan and decompose implementations steps into units of work that can be done by an AI agent in less than 20 minutes
- Specify dependencies, test impact, architecture changes, risk
- Specify complexity on a scale of 1 to 10
- Create todos
- Execute the plan
- Check that all quality gates have passed
- Create a commit message with a summary of changes and commit
Quality Gates
All quality gates must pass before marking an item done and committing the changes, unless instructed to pause testing
- Build succeeds
- Unit tests pass
- No new lint errors or warnings
Libraries
- Prefer libraries over re-inventing the wheel
- Libraries must be under a permissive license and have no licensing cost
- Use the latest stable version applicable to the current framework version and other libraries which are already in use
- Always research the correct usage for the current version, using context7 or web search
Commits
- One focused commit per work item
- Write a clear commit message describing what changed and why
- Do not commit unrelated changes
Code quality
- One class per file
- All public and internal methods have a brief description
- Follow SOLID principles
- Say it once
- Do not put Client IDs and any passwords and secrets in the code
- Use immutable data structures, pure and honest functions
For additional context about technologies to be used, project structure, shell commands, and other important information, read the current plan
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.
- yesterday First seen · 51 lines · 483 tokens per session scan A 6eb6e1efb351
devstack AGENTS.md is an instructions file published in the GitHub repository MartinKuhne/devstack (2 stars, last pushed 21d ago), licensed MIT. It adds 483 tokens to every session, about $0.0024 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
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
buildNext
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
spec-kit AGENTS.md
Instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
langchain AGENTS.md
Instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.