Borrowing it
Nothing to install: this file belongs to engindemirog/ai-native-engineering-workspace. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/engindemirog/ai-native-engineering-workspace/main/AGENTS.mdgit clone --depth 1 https://github.com/engindemirog/ai-native-engineering-workspaceWrote 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/engindemirog/ai-native-engineering-workspace/agents-md)<a href="https://agentmods.dev/instructions/engindemirog/ai-native-engineering-workspace/agents-md"><img src="https://agentmods.dev/badge/instructions/engindemirog/ai-native-engineering-workspace/agents-md/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.
<a href="https://agentmods.dev/instructions/engindemirog/ai-native-engineering-workspace/agents-md"><img src="https://agentmods.dev/badge/instructions/engindemirog/ai-native-engineering-workspace/agents-md.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00644 | $0.00644 |
| Opus 5.5 | $0.00258 | $0.00258 |
| Sonnet 5.5 | $0.00129 | $0.00129 |
| Haiku 4.5 | $0.00064 | $0.00064 |
Grade A, and why
ai-native-engineering-workspace 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 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.
How it starts
The opening of the file, as written. The whole thing — 40 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md — Project Rules
STATUS: NOT CONFIGURED. This workspace has not been adapted to a project yet. The only correct first action is the bootstrap workflow (
workflows/bootstrap.md). Until bootstrap completes and rewrites this file, do not write application code.
Operating mode
Mode: unset — bootstrap sets lite or strict (workflows/README.md); every workflow honors its gates.
Start work with /new-feature in lite (it chains the segments and asks at each gate) or with
/analyze in strict (one segment per role). Segment commands always stop (workflows/segments.md).
Language: unset — bootstrap sets chat=<xx> · docs=<xx>; protocol fields stay English (docs/conventions.md).
Invariant rules (these survive bootstrap — never delete or weaken them)
- No spec, no code. Every piece of work starts as a spec in
specs/active/(fromspecs/TEMPLATE.md). - Plan before build. A human approves the plan before any code is written.
- The producer never verifies its own work. Review and QA run in a separate session or a read-only subagent, working from files (diff + spec), never from the builder's chat.
- Evidence over claims. "Done" requires
scripts/checkgreen and every acceptance criterion mapped to proof. Never claim completion without showing evidence. - Tests are protected. Weakening asserts, deleting or skipping tests to get to green is forbidden — always.
- Proposal rule. Every question, option, or finding comes with your own recommendation and rationale. The human decides; nothing is applied without approval.
- Shipped specs are immutable. Files under
specs/done/are never edited. - Uncertainty is surfaced, not assumed. On ambiguity or a docs/code conflict: stop and use the matching recovery ramp (
prompts/recovery/).
Where things live
| What | Where |
|---|---|
| Architecture & boundaries | docs/architecture.md |
| Domain language & business rules | docs/domain.md |
| Coding conventions | docs/conventions.md |
| Testing rules | docs/testing.md |
| Security rules | docs/security.md |
| Git & branching rules | docs/git.md |
| Decisions (ADRs) · roles (who may do what) | docs/decisions/ · docs/roles/ |
| Specs & plans | specs/active/ · specs/plans/ · shipped → specs/done/ · deferred findings → specs/backlog.md |
| Processes & gates · prompts & recovery ramps | workflows/ · prompts/ |
| Every command: what it does, where it stops, lite vs strict | docs/commands.md |
| The single verification command | scripts/check |
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.
- 2d ago Changed · +11 tokens per session 23f243b0bcfb
- 10d ago Changed · +1 lines · +23 tokens per session 77388eaa6e7e
- 24d ago Changed · -2 lines · -6 tokens per session 2b066218e2d0
- 29d ago Changed · +18 tokens per session 63d0506a6156
- 1mo ago Changed · +1 lines · +30 tokens per session 023641dbdd94
- 1mo ago First seen · 40 lines · 568 tokens per session scan A d2091a404943
ai-native-engineering-workspace AGENTS.md is an instructions file published in the GitHub repository engindemirog/ai-native-engineering-workspace (93 stars, last pushed today), licensed MIT. It adds 644 tokens to every session, about $0.0026 per session on Opus 5.5. 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 2026-09-26.
Other instructions, from other repositories
vscode buildNext.instructions.md
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
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, cache eligibility and rollout and applying the notice (cutover).
langchain AGENTS.md
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.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
deno copilot-instructions.md
Copilot instructions for denoland/deno, covering deno development guide for github copilot, network access, high level overview, key directories and key files to understand first.