Borrowing it
Nothing to install: this file belongs to ainetx/FDD. 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/ainetx/FDD/main/AGENTS.mdgit clone --depth 1 https://github.com/ainetx/FDDWrote 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/ainetx/fdd/agents-md)<a href="https://agentmods.dev/instructions/ainetx/fdd/agents-md"><img src="https://agentmods.dev/badge/instructions/ainetx/fdd/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/ainetx/fdd/agents-md"><img src="https://agentmods.dev/badge/instructions/ainetx/fdd/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 | $0.01040 | $0.01040 |
| Opus 5.5 | $0.00416 | $0.00416 |
| Sonnet 5.5 | $0.00208 | $0.00208 |
| Haiku 4.5 | $0.00104 | $0.00104 |
Grade A, and why
FDD 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 2mo 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 — 124 lines — stays where its author put it; the contents beside it link to each section on GitHub.
FDD AI Agent Navigation
Version: 1.1
⚠️ MUST Instruction Semantics ⚠️
MUST = MANDATORY. NOT optional. NOT recommended. NOT suggested.
ALWAYS = MANDATORY. Equivalent to MUST. Used for action-gated instructions.
If you skip ANY MUST instruction:
- 🚫 Your execution is INVALID
- 🚫 Output must be DISCARDED
- 🚫 You are NOT following FDD
One skipped MUST = entire workflow FAILED
All MUST instructions are CRITICAL without exception.
Agent Acknowledgment
Before proceeding with ANY FDD work, confirm you understand:
- MUST = MANDATORY, not optional
- Skipping ANY MUST instruction = INVALID execution
- INVALID execution = output must be DISCARDED
- I will read ALL required files BEFORE proceeding
- I will follow workflows step-by-step WITHOUT shortcuts
- I will NOT create files without user confirmation (operation workflows)
- I will end EVERY response with a list of FDD files read while producing the response, why each file was read, and which initial instruction triggered opening each file
By proceeding with FDD work, I acknowledge and accept these requirements.
Navigation Rules
ALWAYS open and follow workflows/AGENTS.md WHEN receiving any task request
ALWAYS open and follow requirements/extension.md WHEN you see Extends: {file}
ALWAYS open and follow requirements/core.md WHEN modifying any FDD core files
ALWAYS use fdd adapter-info skill to discover FDD-Adapter location WHEN starting any FDD work
ALWAYS open and follow {adapter-directory}/AGENTS.md WHEN starting any FDD work
ALWAYS open and follow requirements/FDL.md WHEN you see FDL
ALWAYS open and follow requirements/workflow-selection.md WHEN selecting which workflow to execute
ALWAYS open and follow requirements/execution-protocol.md WHEN executing any workflow (FIRST)
ALWAYS open and follow requirements/workflow-execution.md WHEN executing any workflow
ALWAYS open and follow requirements/core-workflows.md WHEN creating or modifying workflow files
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.
- 2mo ago First seen · 124 lines · 1,040 tokens per session scan A b72b00fa2945
FDD AGENTS.md is an instructions file published in the GitHub repository ainetx/FDD (6 stars, last pushed 9mo ago), licensed MIT. It adds 1,040 tokens to every session, about $0.0042 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 2026-08-30.
FDD AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| FDD AGENTS.mdainetx/FDD | Instructions file | 6 | 9mo ago | MIT | A | 1,040 | Codex, OpenCode |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | yesterday | MIT | A | 7,461 | Codex, OpenCode |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | today | MIT | A | 4,680 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 5,516 | GitHub Copilot |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 3,093 | GitHub Copilot |
| deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness | Instructions file | 275k | 2d ago | MIT | A | 4,313 | Codex, OpenCode |