Borrowing it
Nothing to install: this file belongs to greenmtnsun/GitEasy. 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/greenmtnsun/GitEasy/main/.claude/skills/air-gap-discipline/SKILL.mdgit clone --depth 1 https://github.com/greenmtnsun/GitEasyWrote 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/skills/greenmtnsun/giteasy/air-gap-discipline)<a href="https://agentmods.dev/skills/greenmtnsun/giteasy/air-gap-discipline"><img src="https://agentmods.dev/badge/skills/greenmtnsun/giteasy/air-gap-discipline/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/skills/greenmtnsun/giteasy/air-gap-discipline"><img src="https://agentmods.dev/badge/skills/greenmtnsun/giteasy/air-gap-discipline.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 | $0.00079 | $0.00972 |
| Opus 5.5 | $0.00032 | $0.00389 |
| Sonnet 5.5 | $0.00016 | $0.00194 |
| Haiku 4.5 | $0.00008 | $0.00097 |
Grade B, and why
air-gap-discipline scanned grade B with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured today.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
> See also: `software-creation` for the broader discipline. `module-suite` for cross-product strategy. The `air-gap-sentinel` hook (in `~/.claude/settings.json`) is the safety net. How it starts
The opening of the file, as written. The whole thing — 63 lines — stays where its author put it; the contents beside it link to each section on GitHub.
See also:
software-creationfor the broader discipline.module-suitefor cross-product strategy. Theair-gap-sentinelhook (in~/.claude/settings.json) is the safety net.
Air-gap discipline
Suite source ships across multiple environments — Keith's personal machine, CI runners, future enterprise customers, eventually paid distribution. Code does not know which environment it is in. That single rule drives the rest.
The three rules
1. Environment blindness
Code does not test for environment. No if ($env:COMPUTERNAME -eq 'KEITHWORK'). No "if I am on the build server, do X." Configuration that varies by environment lives in:
- the user
$PROFILE(per-user override) - the configuration registry (per-module — see ModuleWorkshop DR-011)
- explicit parameters at invocation
If a function genuinely needs to behave differently in two environments, that behavior is a parameter, not an $env: check.
2. Zero metadata leakage
The following do not appear in source files:
- Machine names (
KEITHWORK01,BUILDSRV02, anything that names a real host) - Domain prefixes (
WORKDOMAIN\username,\\WORKDOMAIN\share) - IPv4 addresses outside loopback (
127.x.x.x), the reserved0.0.0.0/8block (RFC 1122), the limited broadcast255.255.255.255, link-local (169.254.x.x), or the RFC 5737 documentation ranges (192.0.2.x,198.51.100.x,203.0.113.x) - Internal URLs that name a specific organization
- Service-account names tied to one environment
- UNC paths beyond placeholders
When example data is needed, use generic placeholders: \\SERVER01\share, 192.0.2.1 (TEST-NET-1, RFC 5737 — explicitly reserved for documentation), example.com, [email protected].
3. Standalone integrity
Each module is independently runnable. No cross-module imports of code; integration goes through the JSON schema (see module-suite skill). Modules share patterns (DNA), not code.
When this skill triggers
- New file or edit under
C:\Sysadmin\Scripts\ - Code review of a module being prepared for distribution
- Schema or rendering changes that may surface environment-specific data
- Pre-release audit (pairs with
release-auditonce that skill lands)
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.
- today First seen · 63 lines · 79 tokens per session scan B d4add0f6577e
air-gap-discipline is a skill published in the GitHub repository greenmtnsun/GitEasy (1 stars, last pushed yesterday), licensed MPL-2.0. It adds 79 tokens to every session and 972 once invoked, about $0.0003 per session on Opus 5.5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-11-18.
air-gap-discipline compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| air-gap-disciplinegreenmtnsun/GitEasy | Skill | 1 | yesterday | MPL-2.0 | B | 79 | Claude Code |
| imagegenopenai/codex | Skill | 136k | today | Apache-2.0 | A | 113 | Codex |
| local-ai-agentsmicrosoft/ai-agents-for-beginners | Skill | 80k | yesterday | MIT | A | 200 | Claude Code, Codex |
| playwright-climicrosoft/playwright | Skill | 101k | today | Apache-2.0 | A | 19 | Claude Code |
| browser-automationopenclaw/openclaw | Skill | 395k | today | MIT | A | 36 | Claude Code |
| free-llm-apismnfst/awesome-free-llm-apis | Skill | 14k | today | CC0-1.0 | A | 113 | Claude Code, Codex |
| next-cache-components-adoptionvercel/next.js | Skill | 144k | today | MIT | A | 95 | Claude Code |