Borrowing it
Nothing to install: this file belongs to LnYo-Cly/ai4j. 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/LnYo-Cly/ai4j/main/AGENTS.mdgit clone --depth 1 https://github.com/LnYo-Cly/ai4jWrote 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/lnyo-cly/ai4j/agents-md)<a href="https://agentmods.dev/instructions/lnyo-cly/ai4j/agents-md"><img src="https://agentmods.dev/badge/instructions/lnyo-cly/ai4j/agents-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/lnyo-cly/ai4j/agents-md"><img src="https://agentmods.dev/badge/instructions/lnyo-cly/ai4j/agents-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 | $0.03578 | $0.03578 |
| Opus 5.5 | $0.01431 | $0.01431 |
| Sonnet 5.5 | $0.00716 | $0.00716 |
| Haiku 4.5 | $0.00358 | $0.00358 |
Grade A, and why
ai4j 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 1mo 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 — 221 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Repository Guidelines
Project Identity
- Project:
ai4j-sdk - Repository type: Java 8 Maven monorepo with adjacent docs and demo surfaces
- Primary language: Java
- Build tool: Maven
- Frontend/docs surfaces:
docs-site/andai4j-flowgram-webapp-demo/
Monorepo Scope
Treat this repository as a 10-module monorepo plus docs/demo surfaces.
| Path | Role |
|---|---|
ai4j-extension-api/ |
Lightweight public extension contract: manifest, ServiceLoader discovery, explicit enable/expose gates, extension resources |
ai4j-plugin-ask-user/ |
Official sample plugin package: host-mediated user clarification tool, command, Skill, and Prompt |
ai4j/ |
Core SDK: provider access, Chat/Responses, RAG, MCP, vector, image, audio, realtime |
ai4j-agent/ |
Agent runtime, workflow, trace, memory, subagent/team orchestration |
ai4j-coding/ |
Coding-agent runtime, workspace-aware tools, outer loop, compaction |
ai4j-cli/ |
CLI, TUI, ACP host, session/runtime integration |
ai4j-spring-boot-starter/ |
Spring Boot auto-configuration for core SDK |
ai4j-flowgram-spring-boot-starter/ |
FlowGram integration, task APIs, trace bridge, starter-side runtime support |
ai4j-flowgram-demo/ |
Demo backend for FlowGram starter integration |
ai4j-bom/ |
Version alignment BOM |
docs-site/ |
Docusaurus documentation site |
ai4j-flowgram-webapp-demo/ |
Web demo frontend surface |
Harness Anything
- Use
ha(Harness Anything) for all new project-management work. harness/is the active private HA ledger with its own nested Git repository..harness/is generated projection/cache state. Neither belongs in code PRs; commit ledger changes insideharness/separately when they must be retained.- Before substantive work, treat
ha capabilities --jsonand the relevantha <domain> --helpoutput as the command authority. If this workspace is not initialized, runha init --repo-id ai4j-sdk --person-id <person-id> --display-name "<display-name>"; then inspectha daemon status,ha agenda,ha agent list --json,ha squad list --json, andha runtime instance list. - The current thin CLI does not expose the historical
ha doctor --json,ha status --json, orha check --profile target-project --strict --jsonpreflight commands. Do not copy those commands from older task records; use the live capabilities/help output instead. - HA writes require explicit actor attribution. Agents use
HARNESS_ACTOR=agent:<id>or an explicit agent actor; humans useha --actor human:<id>. Do not export a human actor for child processes. ConfigureHARNESS_GIT_AUTHOR_NAMEandHARNESS_GIT_AUTHOR_EMAILfor local ledger commits. - The normal write path is the daemon-backed CLI.
HARNESS_DAEMON_MODE=directis only for bootstrap, recovery, or isolated tests, and must carryHARNESS_DIRECT_WRITE_REASON=recovery|test. - Fable identities are installed from packages containing
agent.jsonorsquad.json: validate withha agent validate --source <dir>orha squad validate --source <dir>, install withha agent install --source <dir>orha squad install --source <dir>, then read back withha agent list --jsonplusha agent inspect <id>orha squad list --jsonplusha squad inspect <id>. Dispatch uses a declared identity plus a ready runtime instance; the instance is an execution resource, not the agent or squad identity. - Complete work through the current HA lifecycle: acquire an Execution lease, record progress/evidence, obtain a typed human review/consent when required, and run
ha task complete.ha task reviewis legacy compatibility lint, not the approval gate.
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.
- 1mo ago Changed · +2 lines · +275 tokens per session 8ad64b0a8ed0
- 1mo ago First seen · 219 lines · 3,303 tokens per session scan A cff0a9ae4796
ai4j AGENTS.md is an instructions file published in the GitHub repository LnYo-Cly/ai4j (436 stars, last pushed 9d ago), licensed Apache-2.0. It adds 3,578 tokens to every session, about $0.0143 per session on Opus 5.5. 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
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).
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.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
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 copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
deno copilot-instructions.md
Copilot instructions for denoland/deno, covering deno development guide for github copilot, network access, high level overview, key directories and key files to understand first.