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/nolindnaidoo/envsync-le/gemini-mdgit clone --depth 1 https://github.com/nolindnaidoo/envsync-leWrote 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/nolindnaidoo/envsync-le/gemini-md)<a href="https://agentmods.dev/instructions/nolindnaidoo/envsync-le/gemini-md"><img src="https://agentmods.dev/badge/instructions/nolindnaidoo/envsync-le/gemini-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 | $0.00410 | $0.00410 |
| Opus 5 | $0.00205 | $0.00205 |
| Sonnet 5 | $0.00082 | $0.00082 |
| Haiku 4.5 | $0.00041 | $0.00041 |
Grade A, and why
envsync-le GEMINI.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 4d 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.
This is a copy
100% identical to regex-le copilot-instructions.md — 4 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
What it actually says
Contributor and agent instructions
Read AGENTS.md before writing any code. It carries the engineering standard this repository is held to — control flow, error handling, immutability, structure — plus the architecture, the invariants and why each one exists. CLAUDE.md is the short version: gates and traps.
This file exists only to route you there. It is deliberately thin: the standard lives in one place so it cannot drift between tools.
Non-negotiables
- Guard clauses first. No
else, noelse if— two branches are an early return, many are a lookup table. - Nesting stops at two levels inside a function.
- Immutable by default:
readonly,ReadonlyArray,Object.freeze. Never mutate a parameter. - Composition, never inheritance. Factory functions returning frozen objects, dependencies passed in as a typed bag.
- Logic never touches
vscode.window.*;ui/renders andcommands/orchestrates. - Never report success you did not achieve — check what the API returned.
- Errors are descriptive and never swallowed.
- Comments explain why, never what.
- Commits are conventional (
fix:,feat:,docs:…), imperative, and enforced by a hook and by CI.
Before you commit
bun run typecheck && bun run lint && bun run test
Coverage floors are a backstop against an untested module, not a target: they sit well below where the code actually is and are never raised to track it. Every claim in a README or manifest must be provable against the code.
Provable is about behaviour and numbers, not availability. An install line for a release you are about to make is staged, not forbidden — write it, and let the release commit be what makes it true.
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.
- 4d ago First seen · 41 lines · 410 tokens per session scan A 7f13ecc338eb
envsync-le GEMINI.md is an instructions file published in the GitHub repository nolindnaidoo/envsync-le (1 stars, last pushed 3d ago), licensed MIT. It adds 410 tokens to every session, about $0.0020 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to regex-le copilot-instructions.md, differing in 4 lines, and is treated as a copy.
Other instructions, from other repositories
weaverse AGENTS.md
AGENTS.md instructions for Weaverse/weaverse, covering agents.md - weaverse sdks development guide, project overview, quick reference, single package commands and monorepo architecture.
blazediff AGENTS.md
Instructions for teimurjan/blazediff, covering blazediff agent rules, hard rules, quick commands and pointers.
critique AGENTS.md
AGENTS.md instructions for remorses/critique, covering opentui, using unreleased opentui versions, bun, react and rules.
json-difference CLAUDE.md
Instructions for lukascivil/json-difference, covering claude.md, general guidelines for working with nx, scaffolding & generators, when to use nxdocs and repository overview.
fastapi-react-admin CLAUDE.md
Claude Code instructions for yilecoding/fastapi-react-admin, covering claude.md, 按任务导航, 让这套文档不腐烂：pnpm ctx:check, 这套文档怎么自己长大 and 结构.
json-difference AGENTS.md
Instructions for lukascivil/json-difference, covering general guidelines for working with nx, scaffolding & generators and when to use nxdocs.