Borrowing it
Nothing to install: this file belongs to hermes-labs-ai/fidelis. 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/hermes-labs-ai/fidelis/main/GEMINI.mdgit clone --depth 1 https://github.com/hermes-labs-ai/fidelisWrote 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/hermes-labs-ai/fidelis/gemini-md)<a href="https://agentmods.dev/instructions/hermes-labs-ai/fidelis/gemini-md"><img src="https://agentmods.dev/badge/instructions/hermes-labs-ai/fidelis/gemini-md/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/instructions/hermes-labs-ai/fidelis/gemini-md"><img src="https://agentmods.dev/badge/instructions/hermes-labs-ai/fidelis/gemini-md.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 | $0.00332 | $0.00332 |
| Opus 5 | $0.00166 | $0.00166 |
| Sonnet 5 | $0.00066 | $0.00066 |
| Haiku 4.5 | $0.00033 | $0.00033 |
Grade A, and why
fidelis 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 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.
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
Fidelis Memory
This extension connects Gemini CLI to a Fidelis Memory server running on this machine. Fidelis stores the user's notes and decisions verbatim and retrieves them without an LLM. The tools below return the original passages, not summaries.
When to use the tools
fidelis_orient— call first when the user refers to prior work, a past decision, an earlier failure, an ongoing project, or something they "said" or "decided" before, even if the turn is not phrased as a question. It returns an evidence-bound orientation packet or explicitly abstains.fidelis_recall— retrieve the passages that answer a specific question about what was recorded. Quote qualifiers exactly as returned.fidelis_query— fast vector-only lookup when a short candidate list is enough.fidelis_health— check that the local server is reachable and how many memories it holds. Use it when another tool reports the server as unreachable.
Rules
- Ground answers about prior decisions in retrieved passages. Do not paraphrase a constraint or number that the retrieved text states exactly.
- If the tools report
fidelis-server unreachable, tell the user to start it withfidelis init(first run) orfidelis-serverand do not invent memory. - Unrelated turns do not need these tools.
Requirements and the full command reference live in the repository README: https://github.com/hermes-labs-ai/fidelis
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 · 32 lines · 332 tokens per session scan A 891460b4d803
fidelis GEMINI.md is an instructions file published in the GitHub repository hermes-labs-ai/fidelis (23 stars, last pushed today), licensed MIT. It adds 332 tokens to every session, about $0.0017 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 2026-09-13.
Other instructions, from other repositories
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).