Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/olibartfast/neuriplo-infernpx agentmods add rules/olibartfast/neuriplo-infer/new-task-type-checklistWrote 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/olibartfast/neuriplo-infer/new-task-type-checklist)<a href="https://agentmods.dev/rules/olibartfast/neuriplo-infer/new-task-type-checklist"><img src="https://agentmods.dev/badge/rules/olibartfast/neuriplo-infer/new-task-type-checklist/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/olibartfast/neuriplo-infer/new-task-type-checklist"><img src="https://agentmods.dev/badge/rules/olibartfast/neuriplo-infer/new-task-type-checklist.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 | $0.00622 | $0.00622 |
| Opus 5 | $0.00311 | $0.00311 |
| Sonnet 5 | $0.00124 | $0.00124 |
| Haiku 4.5 | $0.00062 | $0.00062 |
Grade A, and why
new-task-type-checklist 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.
How it starts
The opening of the file, as written. The whole thing — 55 lines — stays where its author put it; the contents beside it link to each section on GitHub.
New task / model wiring checklist
When a new neuriplo-tasks task type or model family is added (e.g. EdgeCrafter
ecdet/ecseg/ecpose), these steps are easy to forget. Do them before
finishing:
1. Sync supported-model-types docs (automatic — do not hand-edit)
README.md (between <!-- SUPPORTED_MODEL_TYPES:START/END -->) and
docs/generated/supported-model-types.md are generated from the neuriplo-tasks
README. Never edit the marker block by hand. Instead run:
python3 scripts/sync_supported_model_types.py \
--neuriplo-tasks-readme /path/to/neuriplo-tasks/README.md # or build/_deps/neuriplo-tasks-src/README.md
Verify with --check (this is exactly what ci.yml enforces — a stale block
fails CI):
python3 scripts/sync_supported_model_types.py --neuriplo-tasks-readme <path> --check
2. Update the ## Key Features bullet in README.md (manual — not auto-synced)
The task-category list in the ## Key Features bullet is not updated by the
sync script. When a new task category is added in neuriplo-tasks (e.g. a
brand-new domain like "Gaussian Splatting" or "Image Understanding / VLM"), add
it to the parenthesized list on the first ## Key Features bullet in
README.md. New model types within an existing category (e.g. a new detection
model prefix) do not need this update.
3. Keep task routing aligned with neuriplo-tasks TaskFactory
getTaskTypeForModel (app/src/NeuriploInferTaskRouting.cpp) must map every new
type string to the same TaskType that neuriplo_tasks::TaskFactory builds.
Prefer substring rules that mirror the factory (e.g. find("pose"),
find("seg")) so model-family prefixes like ecpose/yolo*pose route to
PoseEstimation, not the Detection default.
4. Wire + advertise any new e2e preset
If you add a preset to docker_run_inference_e2e_example.sh, also add it to
list_presets, the e2e-example-emulation.yml CI matrix, and a dry-run block
in app/test/test_docker_run_inference_e2e_example.sh.
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 · 55 lines · 622 tokens per session scan A 0b498b159959
new-task-type-checklist is a cursor rule published in the GitHub repository olibartfast/neuriplo-infer (104 stars, last pushed 3d ago), licensed MIT. It adds 622 tokens to every session, about $0.0031 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
ponytail
Ponytail, lazy senior dev mode. Always pick the simplest solution that works.
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-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.