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/yujiachen-y/agent-bundle/agents-mdgit clone --depth 1 https://github.com/yujiachen-y/agent-bundleWrote 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/yujiachen-y/agent-bundle/agents-md)<a href="https://agentmods.dev/instructions/yujiachen-y/agent-bundle/agents-md"><img src="https://agentmods.dev/badge/instructions/yujiachen-y/agent-bundle/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 | $0.01098 | $0.01098 |
| Opus 5 | $0.00549 | $0.00549 |
| Sonnet 5 | $0.00220 | $0.00220 |
| Haiku 4.5 | $0.00110 | $0.00110 |
Grade A, and why
agent-bundle 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 4d 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 — 101 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Project-level instructions for AI agents working in this repository. CLAUDE.md is a symlink to this file.
Project Overview
TypeScript/Node.js CLI tool and framework for defining, developing, and shipping AI agent skills. Uses pnpm, targets ES2022/NodeNext. Includes WebUI and HTTP service interfaces.
Key Commands
pnpm install # install dependencies
pnpm build # compile TypeScript + copy webui assets
pnpm test # unit tests with coverage (vitest)
pnpm run lint # eslint
pnpm run quality # lint + duplicate check + test
pre-commit run --all-files # all quality gates
Port Allocation (prefix × 1000 + suffix)
All services use a prefix/suffix port scheme defined in src/cli/serve/worktree-port.ts:
Port = prefix × 1000 + suffix
suffix (last 3 digits): stable service identity
000 = serve / dev (CLI main service + all config-only demos)
005 = demo/personalized-recommend (standalone server)
006 = demo/observability-demo (standalone server)
… new standalone demos increment from 007
Config-only demos (code-formatter, financial-plugin, data-analyst-e2b) run
through `agent-bundle dev` and share suffix 0. Only standalone servers that
call `resolveServicePort(suffix)` directly in their own `main.ts` need a
dedicated suffix.
prefix: worktree isolation
3 = main repo (ports 3000–3999, backward-compatible)
10–63 = worktrees (hash-based, ports 10000–63999)
Port Priority
--portCLI flag → used directly.PORTenvironment variable → used directly (checked insideresolveServicePort).- Auto-computed
prefix × 1000 + suffix; collision rotates prefix (never suffix).
For Agents: Adding a New Demo
- Pick the next available suffix (currently 7 — only needed for standalone servers that call
resolveServicePortdirectly). - Call
resolveServicePort(<suffix>)in yourmain.ts. - Update the suffix table above.
- Never hardcode a port number in new server code.
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.
- 4d ago First seen · 101 lines · 1,098 tokens per session scan A b9246f33e353
agent-bundle AGENTS.md is an instructions file published in the GitHub repository yujiachen-y/agent-bundle (10 stars, last pushed 2mo ago), licensed MIT. It adds 1,098 tokens to every session, about $0.0055 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 2026-08-31.
Other instructions, from other repositories
OpenSandbox AGENTS.md
AGENTS.md instructions for opensandbox-group/OpenSandbox, covering opensandbox agents, repository map, routing, working principles and guardrails.
agentos CLAUDE.md
Claude Code instructions for rivet-dev/agentos, covering agentos, boundaries, security model, sqlite schema ownership and runtime and registry.
OpenSandbox CLAUDE.md
Claude Code instructions for opensandbox-group/OpenSandbox: See AGENTS.md for all rules, routing, and conventions.
agent-safehouse AGENTS.md
AGENTS.md instructions for eugene1g/agent-safehouse, covering agent safehouse: llm quick reference, what this project is, fast working rules, core commands and generate policy only (prints temp policy path).
agent-sandbox AGENTS.md
AGENTS.md instructions for kubernetes-sigs/agent-sandbox, covering agents.md, project summary, repository layout, agent skills and build, test, lint.
agent-sandbox copilot-instructions.md
Copilot instructions for kubernetes-sigs/agent-sandbox: Project Context & Architecture: Refer to AGENTS.md for full project background, module layout, toolchain versions, and core conventions.