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/marcoporcellato/matryca-plumber/02-python-standardsgit clone --depth 1 https://github.com/MarcoPorcellato/matryca-plumberWhat 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 | $0.00000 | $0.00329 |
| Opus 5 | $0.00000 | $0.00164 |
| Sonnet 5 | $0.00000 | $0.00066 |
| Haiku 4.5 | $0.00000 | $0.00033 |
Grade A, and why
02-python-standards 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.
What it actually says
Dependency management and developer experience
- Dependency Management & DX: Strictly use
uv(neverpip). - Always instruct the user to run
make checkto validate code (formatting, linting, mypy strict, pytest). Code is not ready until all tests pass with zero warnings.
Runtime and quality
- Python: target 3.12+.
- Types: annotate public APIs;
mypymust type-check the package on--strictmode. - Validation: use Pydantic models for config, JSON payloads, and boundaries.
- Architecture: layer boundaries and Clean Code checklist — see
12-clean-code-architecture.mdcanddocs/CLEAN_CODE_ARCHITECTURE.md.
Concurrency and I/O (File System Safety)
- Optimistic Concurrency: Matryca runs in the background. Before overwriting any
.mdfile, you MUST check if the file'smtimehas changed since it was read. Useatomic_write_bytes_if_unchangedto prevent data loss if the user is typing in Logseq. - Zero-Byte / Ghost Files: Always implement early-exit guards for empty or whitespace-only files to prevent crashes.
Observability
- Use structured logging via
loguru. - Do not log full note bodies to stdout.
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 · 22 lines · 0 tokens per session scan A 0e7d00cc6fd0
02-python-standards is a cursor rule published in the GitHub repository MarcoPorcellato/matryca-plumber (96 stars, last pushed 2d ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 329 tokens. 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
aionforge-memory
Aionforge Memory cadence and vocabulary — recall first, capture as you go, track tasks as work items.
debug-capture-pipeline
Debug llm-wiki-memory capture/recall — flush breadcrumbs, daily-vs-compile lag, failed-distill stash recovery, embedding cache, hook wiring. Use when memory didn't capture, doesn't recall, or a hook/cron looks broken.
chronos
Time-awareness for coding agents. Consult shell clock + file mtimes before reasoning about "when" or "how long ago". No hooks on Cursor — degraded mode only.
codebase
Forensic codebase brief for AI agents.
session-memory
Use at conversation wrap-up or when the user explicitly indicates end-of-session — capture residual lessons not captured in-flight.
titanclip-monorepo
TitanClip pnpm monorepo layout, scripts, and scoping.