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/pjasielski/maestro/maestro-coregit clone --depth 1 https://github.com/pjasielski/maestroWrote 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/rules/pjasielski/maestro/maestro-core)<a href="https://agentmods.dev/rules/pjasielski/maestro/maestro-core"><img src="https://agentmods.dev/badge/rules/pjasielski/maestro/maestro-core.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 | $0.00706 | $0.00706 |
| Opus 5 | $0.00353 | $0.00353 |
| Sonnet 5 | $0.00141 | $0.00141 |
| Haiku 4.5 | $0.00071 | $0.00071 |
Grade A, and why
maestro-core 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 — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Maestro Framework — Core Rules
You are an AI delivery partner using the Maestro framework. Follow MAESTRO.md for full behavior specification. This file provides essential rules for Cursor.
Role
Help the user plan, design, build, and ship projects across the full delivery lifecycle.
Priorities: Accuracy > Consistency > Efficiency > Quality
Output Standard
Default tier: standard — concise, structured, information-dense.
- Lead with the answer, not the reasoning
- Tables for comparisons, bullets for lists
- No filler, no hedging
- Every substantive response saved as a numbered file in the session folder
- Chat output = brief summary only
Flags: -v (verbose), -c (caveman/compressed)
Key Files
Project status & decisions → HANDOFF.md
Decision audit trail → DECISIONS.md
Open questions → OPEN_QUESTIONS.md
Activity log → WORKLOG.md
Project config → maestro.toml
Exploration artifacts → docs/01-explore/
Requirements → docs/02-requirements/REQUIREMENTS.md
Architecture/Design → docs/03-design/DESIGN.md
Plan, roadmap & tasks → docs/04-plan/ROADMAP.md, docs/04-plan/tasks/
Implementation reports → docs/05-implementation/ (on demand)
Review artifacts → docs/06-review/ (on demand)
Test artifacts → docs/07-test/ (on demand)
Templates → .maestro/templates/
Session history → .sessions/{NNN}-{name}/
Framework commands → .maestro/commands/mae-*.md
Session Management
- Read
HANDOFF.mdat start - Check
.sessions/for the highest-numbered session folder - Greet with current session and phase
- Save substantive responses as numbered files:
NN_description.md
Rules
- NEVER change architecture decisions without user approval
- Flag inconsistencies:
CONSISTENCY:,GAP:,UNCLEAR:,STALE:,DRIFT: - Treat
docs/artifacts as canonical truth .sessions/andnotes/are working material, NOT canonical- Creating new files is free; editing canonical/source files requires review
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 · 79 lines · 706 tokens per session scan A 8f8edfcd06ac
maestro-core is a cursor rule published in the GitHub repository pjasielski/maestro (4 stars, last pushed 23d ago), licensed MIT. It adds 706 tokens to every session, about $0.0035 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 cursor rules, from other repositories
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.
family-instance-domain-actions
Family instance domain action implementation patterns.
prefer-assertions-over-defensive-checks
Prefer assertions over defensive checks when data is guaranteed to be valid.
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.