What is agentwork-bootstrap?

A set of always-on Cursor project rules that explains the team's starting workflow, communication language, safety limits, and code-navigation conventions.

Use it as the project's startup guidance for coding tasks, shared documentation, temporary files, semantic code searches, and Git boundaries.

It gives agents consistent instructions for locating project guidance, handling risky actions, and deciding when to plan, execute, review, or commit.

agentwork-bootstrap — Cursor rule by zhagqn

Install

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.

agentmods

npx agentmods add rules/zhagqn/agentwork/agentwork-bootstrap

Clone the repo

git clone --depth 1 https://github.com/zhagqn/agentwork

Per session 525 This file is loaded in full into every session.

When invoked 525 The same file — it is already loaded in full.

Security scan A 0 findings. Scan, not verified.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00525	$0.00525
Opus 5	$0.00262	$0.00262
Sonnet 5	$0.00105	$0.00105
Haiku 4.5	$0.00052	$0.00052

Measured 2d ago against content hash 73cfe3e9c39f, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

agentwork-bootstrap 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 2d 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.

.agentwork/bootstrap/cursor/rules/agentwork-bootstrap.mdc · 41 lines

What it actually says

description: agentwork 启动规则（Cursor） globs: [] alwaysApply: true