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/yzailab/Large-Discovery-Modelsnpx agentmods add skills/yzailab/large-discovery-models/register-ldm-taskWrote 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/skills/yzailab/large-discovery-models/register-ldm-task)<a href="https://agentmods.dev/skills/yzailab/large-discovery-models/register-ldm-task"><img src="https://agentmods.dev/badge/skills/yzailab/large-discovery-models/register-ldm-task.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 5.1 | $0.00086 | $0.02148 |
| Opus 5 | $0.00043 | $0.01074 |
| Sonnet 5 | $0.00017 | $0.00430 |
| Haiku 4.5 | $0.00009 | $0.00215 |
Grade A, and why
register-ldm-task 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 6d 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 — 185 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Register And Qualify An LDM Task
Build a domain adapter through the manifest-driven task seam, then qualify its scientific and operational contract before calling it production-ready.
Read references/task-contract.md before editing.
Read references/qualification.md before adding a
real config or launching an external evaluator. Treat tasks/README.md as the
authoritative human-facing repository contract when present.
Establish The Contract
Before scaffolding, discover or ask for:
- the candidate domain and its parser/validator boundary;
- each reservoir-expansion action and whether it emits candidates, configures a generator, edits a candidate, or updates the expansion schema;
- the surrogate representation, dimension policy, encoder, and version;
- the benchmark source URL, immutable commit, and task path;
- the proposal provider kind, whether it requires endpoint preflight, and whether accepted actions support fine-tuning collection;
- reported, optimized, and diagnostic metrics with directions;
- one expensive evaluation and its official per-candidate limits;
- search, LLM-attempt, expensive-evaluation, and baseline budgets;
- required datasets, artifacts, binaries, accelerators, and seed observations;
- resume expectations, comparison axis, and required run artifacts.
Do not infer an official budget from a smoke run. Record unknowns explicitly and
keep experiment.json at qualification: draft until primary-source evidence
and real evaluator checks support qualified.
Implement Registration
-
Inspect
tasks/README.md,ldm_tts/registration/registry.py, the closest task, and the domain benchmark. -
Select a lowercase Python
task_id. Confirmtasks/<task_id>/andconfig/<task_id>/do not already exist. -
Run the non-overwriting scaffolder:
python scripts/scaffold_task.py <task_id> --description "<one-line description>"
What ships with it
3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 6d ago First seen · 185 lines · 86 tokens per session scan A f476ca8f1c6b
register-ldm-task is a skill published in the GitHub repository yzailab/Large-Discovery-Models (30 stars, last pushed 11d ago), licensed MIT. It adds 86 tokens to every session and 2,148 once invoked, about $0.0004 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 skills, from other repositories
research-engineer
An uncompromising Academic Research Engineer. Operates with absolute scientific rigor, objective criticism, and zero flair. Focuses on theoretical correctness, formal verification, and optimal implementation across any required technology.
train-pose
Train/evaluate WiFi pose models honestly — camera-supervised (MediaPipe + CSI) and camera-free (WiFlow), always checked against the mean-pose baseline before any PCK is quoted.
experiment-audit
Audit experiment integrity before claiming results. Uses cross-model review (external reviewer backend) to check for fake ground truth, score normalization fraud, phantom results, and insufficient scope. Use when user says "审计实验", "check experiment integrity", "audit results", "实验诚实度", or after experiments complete…
i4h-catheter-navigation-e2e
End-to-end smoke for catheter navigation covering setup, digital twin, DRR, and unit tests. Use when asked to run the full catheter workflow smoke or demo the v0.7 pipeline.
i4h-catheter-navigation-render-drr
Render a single DRR fluoroscopy frame from a CT cache or synthetic phantom. Use when asked to render DRR, generate a fluoro image, or smoke-test the Slang renderer.
i4h-catheter-navigation-smoke
Run CPU-only fluorosim smoke tests (imports, preprocessing, CLI parsers). Use when asked to smoke-test catheter navigation in CI or without a GPU.