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/hackmods/cursor-proxmox-mcp/api-coveragegit clone --depth 1 https://github.com/hackmods/cursor-proxmox-mcpWhat 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 | $0.00289 | $0.00289 |
| Opus 5 | $0.00144 | $0.00144 |
| Sonnet 5 | $0.00058 | $0.00058 |
| Haiku 4.5 | $0.00029 | $0.00029 |
Grade A, and why
api-coverage 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 yesterday.
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
API coverage tracking
When adding, renaming, or removing MCP tools:
- Update
.cursor/research/proxmox-api-coverage.mdstatus (done/planned/excluded). - If closing or changing a roadmap item, update
.cursor/research/next-expansion.md. - Note non-obvious API quirks in
.cursor/research/changelog-notes.md. - Record design choices in
.cursor/research/decisions.mdwhen changing patterns. - Keep
tests/expected_tools.pyin sync withserver.py_setup_tools(). - Follow
keep-docs-aligned.mdcfor README / definitions / SETUP when auth or install changes. - Auth/privsep quirks belong in
changelog-notes.md+decisions.md(see D8) and.cursor/rules/proxmox-auth.mdc. - Append a row to
.cursor/research/revisions.mdfor agent-visible behavior changes. - If the change came from lab/agent feedback, append to
.cursor/research/agent-feedback-log.md(symptoms → root cause → fix → out of scope).
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.
- yesterday First seen · 20 lines · 289 tokens per session scan A e574bb744184
api-coverage is a cursor rule published in the GitHub repository hackmods/cursor-proxmox-mcp (1 stars, last pushed 15d ago), licensed MIT. It adds 289 tokens to every session, about $0.0014 per session on Opus 5. A static security scan graded it A with 0 findings. It comes from a forked repository.
Other cursor rules, from other repositories
lians-memory
Current Lians task, control policy, and bounded context.
architecture-for-apps
ArchiPy clean architecture for apps — layers, import direction, and base types.
config-and-di
ArchiPy BaseConfig, FastAPIConfig/uvicorn, and DI container wiring.
using-archipy-utils
ArchiPy helpers/utils — pure utilities, AppUtils FastAPI/gRPC factories.
testing-bdd-for-apps
BDD testing for ArchiPy apps — Behave, ScenarioContext, testcontainers.
using-archipy-adapters
Using and writing adapters in ArchiPy apps — extras, ports, mocks, boundary errors.