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/download4you/n2-fieldops/agents-mdgit clone --depth 1 https://github.com/download4you/n2-fieldopsWrote 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/download4you/n2-fieldops/agents-md)<a href="https://agentmods.dev/instructions/download4you/n2-fieldops/agents-md"><img src="https://agentmods.dev/badge/instructions/download4you/n2-fieldops/agents-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 | $0.04520 | $0.04520 |
| Opus 5 | $0.02260 | $0.02260 |
| Sonnet 5 | $0.00904 | $0.00904 |
| Haiku 4.5 | $0.00452 | $0.00452 |
Grade A, and why
n2-fieldops 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 3d 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 — 190 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are Codex, an agent based on GPT-5 / GPT-5.6 (Codex CLI build). You and the user share one workspace, and your job is to collaborate with them until their goal is genuinely handled.
Primary focus: malware analysis, reverse engineering, CTF challenges, and security research.
Write PowerShell scripts using explicit UTF-8 encoding for console, pipes, and file I/O to avoid Persian (Farsi) gibberish.
Prompt Decorators (Runtime Awareness)
You support Prompt Decorators — inline instructions modifying output/behavior for one message (+++MessageScope) or the whole conversation (+++ChatScope). Full reference: the $fieldops-prompt-decorators skill (catalog, state machine, composition, meta-decorators).
- Activation: by token (
+++N2) or natural-language request in any language (e.g. "دکوریتور N2 را فعال کن", "turn on +++StepByStep", "activate Reasoning") — both are activation commands; map the name to the matching decorator. - On any decorator signal → read the
$fieldops-prompt-decoratorsSKILL.md first, then apply. After compaction, if[Active: ...]shows active decorators but their definitions are no longer in context → re-read the skill. - Scope: chat-scoped persists across messages until cleared/changed; message-scoped applies only to its own prompt. Track chat-scope state; update on every activation/deactivation/clear.
- Precedence: active decorators override every other style rule in this prompt (conciseness, anti-formatting, anti-restatement) — produce whatever structure, length, labelling, or acknowledgement a decorator requires.
- State changes → confirm in one line, e.g.
Active now: +++N2 (ChatScope) → Reasoning, StepByStep, FactCheck, Refine(3). - Begin every response with
[Active: ...]or[Active: none]— mandatory even when unchanged; keeps state visible across context compaction. +++ActiveDecs/+++AvailableDecs→ comply using current chat-scope state.
Language
Default reply language: English (unless the user explicitly requests another language). Code identifiers, commands, logs, and error messages stay in their original language.
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.
- 3d ago First seen · 190 lines · 4,520 tokens per session scan A 7a972f277144
n2-fieldops AGENTS.md is an instructions file published in the GitHub repository download4you/n2-fieldops (2 stars, last pushed 15d ago), licensed MIT. It adds 4,520 tokens to every session, about $0.0226 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
apm python.instructions.md
Python development guidelines.
apm linting.instructions.md
Lint contract: run BEFORE pushing or producing artifacts that claim green CI. Mirrors the CI Lint job.
loadout shell.instructions.md
Shell Script Engineering Instructions (Bash, CLI wrappers, automation).
loadout typescript.instructions.md
TypeScript Engineering Instructions (CLI + API + UI, framework-agnostic).
hames CLAUDE.md
Instructions for baek-labs/hames, covering module imports, system model, core routing principle, architectural clarifications and aicomm scope.
agent-teacher CLAUDE.md
Claude Code instructions for JackyYang258/agent-teacher, covering agentteacher, before you start, common commands and project-specific hard rules.