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 rules/evoclaw/amplify/amplify-bootstrapgit clone --depth 1 https://github.com/EvoClaw/amplifyWhat 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 | $0.03470 | $0.03470 |
| Opus 5 | $0.01735 | $0.01735 |
| Sonnet 5 | $0.00694 | $0.00694 |
| Haiku 4.5 | $0.00347 | $0.00347 |
Grade A, and why
amplify-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.
How it starts
The opening of the file, as written. The whole thing — 224 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Amplify Bootstrap
You have Amplify — an agentic research automation framework.
IF A SKILL APPLIES TO YOUR TASK, YOU DO NOT HAVE A CHOICE. YOU MUST USE IT.
This is not negotiable. This is not optional. You cannot rationalize your way out of this.
⛔ ABSOLUTE RULE: ONE PHASE PER TURN — STOP AND WAIT
After completing a phase or reaching a gate:
- Present deliverables and/or gate checklist
- END YOUR RESPONSE — STOP GENERATING
- Wait for the user to reply with explicit approval
- Only then proceed to the next phase
NEVER execute Phase 0 + Phase 1 in one turn. NEVER skip Phase 2 (problem validation) — it is required for ALL types including Type D. NEVER skip Phase 5 (results integration) or its multi-agent discussion panel. NEVER auto-proceed to paper writing — user must explicitly say "ready for paper" or equivalent.
During Phase 6 (paper writing): present EACH SECTION individually and wait for user feedback before writing the next section.
If you find yourself executing more than one phase in a single response, YOU ARE VIOLATING THE MOST IMPORTANT RULE. Stop immediately.
Fast Mode
If the user says "fast mode", "快速模式", or "combine phases" at the start:
- Combine Phase 0 + Phase 1 into a single turn (but still present both deliverables)
- After each gate, still STOP and wait for approval (gates are never combined)
- Multi-agent deliberation rounds are reduced to max 3 (instead of 5)
- Per-section polishing rounds are reduced to max 2 (instead of 5)
Fast Mode does NOT skip any phase or gate. It only reduces stops and deliberation rounds.
How to Access Skills in Cursor
Use the Read tool on skill files located at ~/.cursor/skills/amplify/skills/{skill-name}/SKILL.md.
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.
- 2d ago First seen · 224 lines · 3,470 tokens per session scan A d52739ee031c
amplify-bootstrap is a cursor rule published in the GitHub repository EvoClaw/amplify (12 stars, last pushed 6mo ago), licensed MIT. It adds 3,470 tokens to every session, about $0.0174 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 cursor rules, from other repositories
clean-code
Apply language-agnostic clean-code discipline to all code writing, editing, reviewing, testing, and refactoring, including file placement, single responsibility, and verified completion.
skill-writer
Cursor rule "skill-writer" from theneoai/skill-writer, covering skill summary, §0 quick start — 5 common workflows, workflow a — "i want to create a new skill", workflow c — "my skill scored below 700 (fail)" and workflow d — "i want to deploy my skill".
angular-20
This rule provides comprehensive best practices and coding standards for Angular development, focusing on modern TypeScript, standalone components, signals, and performance optimizations.
dev-standard
Apache Superset development standards and guidelines for Cursor IDE.
cli-error-handling
CLI command error handling patterns.
prefer-direct-imports-over-module-mocks
Prefer extracting a testable core over vi.mock / vi.resetModules when unit tests need to reach production logic entangled with config, env, or singletons.