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/run-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/run-ldm-task)<a href="https://agentmods.dev/skills/yzailab/large-discovery-models/run-ldm-task"><img src="https://agentmods.dev/badge/skills/yzailab/large-discovery-models/run-ldm-task/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/skills/yzailab/large-discovery-models/run-ldm-task"><img src="https://agentmods.dev/badge/skills/yzailab/large-discovery-models/run-ldm-task.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00102 | $0.01751 |
| Opus 5.5 | $0.00041 | $0.00700 |
| Sonnet 5.5 | $0.00020 | $0.00350 |
| Haiku 4.5 | $0.00010 | $0.00175 |
Grade A, and why
run-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 2mo 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 — 164 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Run An Existing LDM Task
Execute registered tasks through their checked-in configs and the shared runner.
Preserve task configuration unless the user asks for an edit. Use temporary
--set overrides only when they do not violate a selected experiment-contract
profile.
Read references/built-in-tasks.md when running
nanogpt, small_molecule, or antibody. For another task, read its
tasks/<task_id>/README.md and task.json instead of inventing flags.
Resolve The Run
-
Work from the repository root.
-
Identify the task, config, requested mode, budget, and acquisition function from the request. If the config is unspecified, list configs with:
python scripts/run_ldm_tts.py --list -
Read the selected config,
tasks/<task_id>/task.json, and the relevant task README. Also readexperiment.jsonwhen present. Confirm that the config'staskmatches the intended task. -
Classify the runtime implementation:
- Engine-native: the executed task path calls
ldm_tts.campaign.run_campaignwith aCampaignRecipe; expect the shared lifecycle, budget, event, checkpoint, status, and summary artifacts. All built-in tasks (nanogpt,small_molecule,antibody,llm_kv_adaptive_quantization,causal_discovery_discrete,ai4bio_mutation_effect_prediction) are engine-native. - Compatibility: only legacy or experimental tasks use a task-specific
loop or
run_budgeted_search; follow their README for artifacts, counters, and resume behavior. - Emitting
LDMTaskSpecdoes not by itself make a task engine-native. Verify the executed code path rather than inferring runtime ownership from names.
- Engine-native: the executed task path calls
-
Classify the requested execution level:
- Inspect: list or explain configs; make no run.
- Mock: local deterministic execution with no model or evaluator.
- Contract: validate resolution and task specification without objective
evaluation; use runner
--dry-runfirst, then task-level dry/zero work if documented. - Tiny real: one or a few real proposals and evaluations.
- Full real: the checked-in or explicitly overridden production budget.
-
Do not silently promote a mock/contract request to a real run. Do not launch a full real budget merely because a tiny real run succeeds.
What ships with it
2 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.
- 2mo ago First seen · 164 lines · 102 tokens per session scan A 6d6fd030588b
run-ldm-task is a skill published in the GitHub repository yzailab/Large-Discovery-Models (34 stars, last pushed 1mo ago), licensed MIT. It adds 102 tokens to every session and 1,751 once invoked, about $0.0004 per session on Opus 5.5. 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
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…