Borrowing it
Nothing to install: this file belongs to joshuaswarren/remnic. 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/joshuaswarren/remnic/main/AGENTS.mdgit clone --depth 1 https://github.com/joshuaswarren/remnicWrote 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/joshuaswarren/remnic/agents-md)<a href="https://agentmods.dev/instructions/joshuaswarren/remnic/agents-md"><img src="https://agentmods.dev/badge/instructions/joshuaswarren/remnic/agents-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 | $0.31441 | $0.31441 |
| Opus 5 | $0.15720 | $0.15720 |
| Sonnet 5 | $0.06288 | $0.06288 |
| Haiku 4.5 | $0.03144 | $0.03144 |
Grade A, and why
remnic AGENTS.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 8d 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 — 2,493 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Remnic - Agent Guide
PUBLIC, OPEN-SOURCE REPOSITORY. Remnic is a public open-source project. Everything pushed to GitHub — commits, issues, PRs, review comments — is world-readable. Never include PII or operator-specific infrastructure details (hostnames, internal IPs, usernames/home paths, client or project names, memory IDs or memory content, links to private repos/docs). Write issues and PRs for the general case: describe the reproducing deployment shape and design fixes that benefit all users, not one operator's setup. Full rules: "PUBLIC REPOSITORY — Privacy Policy" below.
Architecture Boundaries (Non-Negotiable)
Remnic is a multi-platform memory system. Keep these boundaries intact on every change:
@remnic/core,@remnic/server, and@remnic/cliown Remnic's core behavior. Core memory semantics, storage, retrieval, extraction, governance, and standalone operation must live there.- Core and standalone paths must not depend on OpenClaw, Hermes, or any future host. Host integrations may consume core. Core must not reach back into host SDKs, config shapes, or runtime lifecycles.
- Platform-specific behavior belongs in platform adapters only.
OpenClaw-specific code belongs in
packages/plugin-openclawplus the current rootsrc/compatibility wiring that still hosts OpenClaw runtime entrypoints today. Hermes-specific code belongs inpackages/plugin-hermes. Keep host logic thin and translation-focused. - Do not reinvent host-native features. If OpenClaw, Hermes, or another platform already provides a runtime capability, plugin hook, command surface, or extension primitive, use that real upstream contract instead of recreating a parallel Remnic abstraction.
- Verify host behavior against current upstream source and docs before implementing it. Issue text, old local docs, or remembered APIs are not enough for host-facing work.
- Desktop-capture subsystems obey the same split:
packages/remnic-core/src/activity/andpackages/remnic-core/src/meetings/are host-agnostic core subsystems, while the capture packages (@remnic/capture-audio,@remnic/capture-screen) and the meeting/wearable connectors (@remnic/connector-*) are optional adapters that consume core and never the reverse (umbrella #1896).
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.
- 8d ago First seen · 2,493 lines · 31,441 tokens per session scan A 9a36aced9bb3
remnic AGENTS.md is an instructions file published in the GitHub repository joshuaswarren/remnic (193 stars, last pushed yesterday), licensed MIT. It adds 31,441 tokens to every session, about $0.1572 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
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).
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).
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.
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.