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/claude-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/claude-md)<a href="https://agentmods.dev/instructions/download4you/n2-fieldops/claude-md"><img src="https://agentmods.dev/badge/instructions/download4you/n2-fieldops/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 5.1 | $0.00632 | $0.00632 |
| Opus 5 | $0.00316 | $0.00316 |
| Sonnet 5 | $0.00126 | $0.00126 |
| Haiku 4.5 | $0.00063 | $0.00063 |
Grade A, and why
n2-fieldops 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 5d 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 — 63 lines — stays where its author put it; the contents beside it link to each section on GitHub.
n2-fieldops contributor profile
This repository is a text-first Agent Skills distribution, not a conventional
application. The canonical install surface is the 17 root-level directories whose
names start with fieldops- and contain SKILL.md.
Runtime surfaces
AGENTS.mdis the durable Codex profile.KIMI.mdis the durable Kimi profile.- Root
fieldops-*directories are the shared Claude/Codex/CC Switch skills. claude-plugin-template/contains only native-Claude metadata and profile sources; it must not containSKILL.mdfiles because CC Switch scans recursively.scripts/build_release.pygenerates the complete native Claude plugin and the release archives underdist/.
Required checks
py -3 -m unittest discover -s tests -v
py -3 scripts/build_release.py --check
py -3 scripts/build_release.py --output-dir dist
When the Claude CLI is available, validate the generated package:
claude plugin validate .\dist\n2-fieldops-claude-plugin --strict
claude plugin validate .\dist\n2-fieldops-claude-marketplace --strict
The release is versioned by VERSION. The initial public release is 1.0.0; for
every release, the tag must be v<VERSION> and the GitHub release title must be
n2-fieldops <VERSION>.
Editing rules
- Preserve unrelated user changes and inspect
git statusbefore editing. - Use focused, reviewable patches. Do not add a second
SKILL.mdtree under a visible repository directory. - Keep each skill self-contained: references and scripts stay beneath its own skill
directory, and every technique file is listed by that skill's
SKILL.md. - Keep CTF attribution, per-skill
LICENSE, and pinnedUPSTREAM.mdfiles intact. - Keep root skill prose portable. Codex-only invocation tokens may be used in
AGENTS.mdand user docs, but skill bodies should use neutral skill names so Claude can consume the same canonical tree. - Do not copy platform-owned files from
$CODEX_HOME/skills/.systeminto this repo.
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.
- 5d ago First seen · 63 lines · 632 tokens per session scan A 091a94df11fa
n2-fieldops CLAUDE.md is an instructions file published in the GitHub repository download4you/n2-fieldops (2 stars, last pushed 16d ago), licensed MIT. It adds 632 tokens to every session, about $0.0032 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.
loadout shell.instructions.md
Shell Script Engineering Instructions (Bash, CLI wrappers, automation).
loadout typescript.instructions.md
TypeScript Engineering Instructions (CLI + API + UI, framework-agnostic).
agent-teacher CLAUDE.md
Claude Code instructions for JackyYang258/agent-teacher, covering agentteacher, before you start, common commands and project-specific hard rules.
rules-with-receipts AGENTS.md
Instructions for ralfyishere/rules-with-receipts, covering agents.md — for ai agents that land in this repo, what this is, if you are installing the pack into a project, if you are working in a project that already has the pack and if you are evaluating claims about this pack.
ai-agent-rules-generator ui-design.instructions.md
Glitch Payment Gateway admin UI design rules — mandatory element & component reference for WooCommerce settings.