Gini Agent is a personal AI-agent runtime that manages conversations, runs, tasks, approvals, memory, skills, jobs, tools, traces, audit events, and runtime health across its clients. It is for an agent that can remember, learn from task outcomes, and operate through desktop or mobile interfaces with user controls. Catalogue add-ons extend the runtime with skills and instructions.
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/open-curiosity/gini-agent/agents-mdgit clone --depth 1 https://github.com/Open-Curiosity/gini-agentWrote 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/open-curiosity/gini-agent/agents-md)<a href="https://agentmods.dev/instructions/open-curiosity/gini-agent/agents-md"><img src="https://agentmods.dev/badge/instructions/open-curiosity/gini-agent/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 | $0.03639 | $0.03639 |
| Opus 5 | $0.01819 | $0.01819 |
| Sonnet 5 | $0.00728 | $0.00728 |
| Haiku 4.5 | $0.00364 | $0.00364 |
Grade A, and why
gini-agent 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 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.
How it starts
The opening of the file, as written. The whole thing — 168 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Gini Agent Instructions
These instructions apply to the whole repository unless a nested AGENTS.md overrides them for a subtree.
Shape
Gini is a Bun TypeScript personal agent runtime. The gateway owns durable state and execution; CLI, Next.js, future mobile, MCP, messaging, and scripts are clients of the same /api/* contract.
The repository is a Bun workspaces monorepo: the root package.json is a private workspace root (single bun.lock, shared dependency versions via the workspace catalog), with packages/runtime (@gini/runtime, the gateway + CLI), packages/web (@gini/web, the Next.js control plane), and packages/mobile (@gini/mobile, the Expo app). Bundled skills/, docs/, scripts/, vendor/, and patches/ live at the repository root, which the runtime discovers by walking up to the workspace marker (projectRoot() in packages/runtime/src/paths.ts). Run bun install once at the root — it covers every package. See ADR bun-workspaces-monorepo.md.
Start with README.md for the docs index. Keep docs/whitepaper.md, docs/architecture-overview.md, focused docs, and docs/adr/ in sync with architecture changes.
ADRs
Keep ADRs current when architecture changes.
- Update an existing ADR when the original decision still stands but implementation details, consequences, or acceptance checks changed.
- Add a new ADR for a significant architecture decision, trust boundary, persistence model, process shape, provider strategy, client contract, or operational workflow.
- If a change makes an ADR obsolete, mark the old decision as superseded and link to the replacement ADR.
- ADRs should be forward-looking. Don't write removal logs — context for what was deleted belongs in git history and PR descriptions, not in an ADR. If two ADRs overlap because of a consolidation, merge the canonical forward-looking content into one and delete the redundant ADR (instead of leaving both).
- ADRs are named by slug (
docs/adr/<slug>.md), no number prefix. Pick the slug carefully and never rename it once merged — the filename is the citation key. - Always cite an ADR by its full filename including
.mdso the reference is unambiguously a file:see ADR agent-memory-isolation.mdin prose and code comments, and[Per-Agent Memory Isolation](docs/adr/agent-memory-isolation.md)for markdown links.
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 · 168 lines · 3,639 tokens per session scan A b008caa6c720
gini-agent AGENTS.md is an instructions file published in the GitHub repository Open-Curiosity/gini-agent (1,869 stars, last pushed 1mo ago), licensed MIT. It adds 3,639 tokens to every session, about $0.0182 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
gno AGENTS.md
AGENTS.md instructions for gmickel/gno, covering knowledge cutoff warning, apis - bun first!, must use bun, acceptable node:\ (no bun equivalent) and testing.
Vibelution AGENTS.md
AGENTS.md instructions for CCDawn/Vibelution, covering vibelution agent rules, 1. identity and priority, 2. global red lines, 3. start and routing and 3.0 每任务先 router.
linggen CLAUDE.md
Claude Code instructions for linggen/linggen, covering claude.md, doc and spec, build, test, run, architecture and configuration.
Bamboo-agent AGENTS.md
AGENTS.md instructions for bigduu/Bamboo-agent: Read README.md for the product boundary. Use this canonical Jiandu memory contract.
Bamboo-agent CLAUDE.md
Claude Code instructions for bigduu/Bamboo-agent: Read README.md and AGENTS.md, then follow their canonical Jiandu memory contract. Do not revive Bamboo-owned memory storage, indexes, Dream bytes, embeddings, compatibility layers, or a duplicated action catalog.
nimblebrain CLAUDE.md
Claude Code instructions for NimbleBrainInc/nimblebrain, a project described as: Self-hosted platform for MCP Apps and agent automations — tools, interactive UIs, scheduled runs, multi-agent delegation.