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.
git clone --depth 1 https://github.com/MarcoPorcellato/matryca-plumberWrote 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/marcoporcellato/matryca-plumber/11-prompt-maintainer)<a href="https://agentmods.dev/rules/marcoporcellato/matryca-plumber/11-prompt-maintainer"><img src="https://agentmods.dev/badge/rules/marcoporcellato/matryca-plumber/11-prompt-maintainer/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/rules/marcoporcellato/matryca-plumber/11-prompt-maintainer"><img src="https://agentmods.dev/badge/rules/marcoporcellato/matryca-plumber/11-prompt-maintainer.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00014 | $0.00454 |
| Opus 5 | $0.00007 | $0.00227 |
| Sonnet 5 | $0.00003 | $0.00091 |
| Haiku 4.5 | $0.00001 | $0.00045 |
Grade A, and why
11-prompt-maintainer 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 9d 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
Prompt maintainer checklist (Matryca Plumber)
Load on demand when editing Tier-1 prompts, docs/openspec/agent/ fragments, or MCP tool contracts.
Rule routing: Complements 06-auto-changelog.mdc, 07-env-example.mdc, AGENTS.md.
Trigger → Azione
| Hai modificato | Devi eseguire |
|---|---|
docs/openspec/agent/*.md |
make build-system-prompt && make check-system-prompt |
src/agent/**/prompts.py, src/graph/**/prompts.py (builder Tier-1A) |
uv run pytest tests/test_daemon_prompts.py --update-prompt-hashes → git add tests/prompt_hash_snapshots.json |
src/agent/**/prompts.py (builder Tier-1B writer) |
Come sopra + verifica che nessuna stringa contenga English only |
mcp_server.py (docstrings tool) |
Aggiorna docs/openspec/agent/mcp-tools.md (+ tool-reference.md se serve) → make build-system-prompt; alla release MCP sync anche llms.txt §2 |
tests/prompt_hash_snapshots.json |
Il commit message deve contenere prompt(<builder>): <motivo> |
Non fare
- Non editare
SYSTEM_PROMPT.mddirettamente — è generato (<!-- GENERATED — do not edit -->). - Non aggiungere frammenti
docs/openspec/agent/*.mdsenza riga in_assembly_order.txt—make check-system-promptfallisce. - Non aggiungere stringhe system inline in
llm_client.py— usa un builder di dominio che importa solosrc/agent/prompts/core.py. - Non impostare
alwaysApply: truesu nuove rule senza approvazione esplicita.
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.
- 9d ago First seen · 28 lines · 14 tokens per session scan A d407854efb05
11-prompt-maintainer is a cursor rule published in the GitHub repository MarcoPorcellato/matryca-plumber (97 stars, last pushed today), licensed Apache-2.0. It adds 14 tokens to every session and 454 once invoked, about $0.0001 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
json-prompt-design
Protects MOTO prompt wording and defines cross-cutting JSON response invariants.
python-app
Here's how the python application is organized.
react
Cursor rule "react" from iloveitaly/llm-ide-rules, covering react, mock data, react hook form and styling.
react-router
Cursor rule "react-router" from iloveitaly/llm-ide-rules, covering react router, loading mock data, how to use clientloader and loading backend data.
llm-integration
A set of rules for connecting an application to a large language model and writing prompts for it.
aionforge-memory
Aionforge Memory cadence and vocabulary — recall first, capture as you go, track tasks as work items.