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/diegosouzapw/omniglyph/gemini-mdgit clone --depth 1 https://github.com/diegosouzapw/OmniGlyphWrote 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/diegosouzapw/omniglyph/gemini-md)<a href="https://agentmods.dev/instructions/diegosouzapw/omniglyph/gemini-md"><img src="https://agentmods.dev/badge/instructions/diegosouzapw/omniglyph/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 | $0.00398 | $0.00398 |
| Opus 5 | $0.00199 | $0.00199 |
| Sonnet 5 | $0.00080 | $0.00080 |
| Haiku 4.5 | $0.00040 | $0.00040 |
Grade A, and why
OmniGlyph 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 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.
What it actually says
OmniGlyph — Guidelines for Gemini-based agents
Scope: rules for Gemini-based assistants. For Claude Code, see
CLAUDE.md. The canonical, tool-agnostic guide isAGENTS.md— read it first; this file only adds Gemini-specific emphasis. If anything here conflicts withAGENTS.md,AGENTS.mdwins.
Non-negotiables (mirror of AGENTS.md)
- Strict TDD. Write the failing test first, watch it fail for the right reason, then the minimal implementation. No production code without a test.
- Measurement before claims. Any number in code comments or docs must have a
receipt in
benchmarks/*/results/*.jsonl. Never hand-edit those files. - Never weaken a gate or a test to go green. The fail-closed model gate and the profitability gate exist because of measured failures. Loosening them requires new benchmark receipts, not code edits.
- Never commit secrets. API keys live in env vars only — never in files, fixtures, or JSONL results.
- English is the source of truth. Docs prose is English; translations live
under
docs/i18n/<locale>/. Moving or renaming a doc means updating every relative link —npx vitest run tests/docs-integrity.test.tsmust pass. - No AI attribution trailers in commits, PRs, or the CHANGELOG.
File placement
- Tests go under
tests/only — never in the project root. - One-off or experimental scripts go under
scripts/— never loose in the root.
Validation before you claim done
pnpm run lint && pnpm run typecheck && pnpm test && pnpm run build
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 · 34 lines · 398 tokens per session scan A cd88eeaa574b
OmniGlyph GEMINI.md is an instructions file published in the GitHub repository diegosouzapw/OmniGlyph (106 stars, last pushed 4d ago), licensed MIT. It adds 398 tokens to every session, about $0.0020 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 2026-08-30.
Other instructions, from other repositories
headroom copilot-instructions.md
Copilot instructions for headroomlabs-ai/headroom: When performing a pull request review in this repository.
tokenfold AGENTS.md
AGENTS.md instructions for snchimata/tokenfold, covering repository guidelines, working principles, repository map, implementation conventions and validation.
distil CLAUDE.md
Claude Code instructions for munhq/distil, covering distil — context optimization for llm agents, what this is, consumption modes, architecture and layers (src/layers/).
densely CLAUDE.md
Instructions for alibaizhanov/densely: Behavioral guidelines to reduce common LLM coding mistakes. Merge with project-specific instructions as needed.
botmux CLAUDE.md
Claude Code instructions for deepcoldy/botmux, covering botmux, 构建 & 运行, bun 开发链路, worktree 的 nodemodules：共享还是独立（改前必读） and 编译态（单文件二进制）注意.
SearChat CLAUDE.md
Claude Code instructions for yokingma/SearChat, covering claude.md, project overview, architecture, monorepo structure and key technologies.