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 skills add kedro-org/kedro-skills --skill llm-context-nodesgit clone --depth 1 https://github.com/kedro-org/kedro-skillsWrote 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/kedro-org/kedro-skills/llm-context-nodes)<a href="https://agentmods.dev/skills/kedro-org/kedro-skills/llm-context-nodes"><img src="https://agentmods.dev/badge/skills/kedro-org/kedro-skills/llm-context-nodes/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/kedro-org/kedro-skills/llm-context-nodes"><img src="https://agentmods.dev/badge/skills/kedro-org/kedro-skills/llm-context-nodes.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 | $0.00079 | $0.04580 |
| Opus 5.5 | $0.00032 | $0.01832 |
| Sonnet 5.5 | $0.00016 | $0.00916 |
| Haiku 4.5 | $0.00008 | $0.00458 |
Grade A, and why
llm-context-nodes 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 4d 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 — 316 lines — stays where its author put it; the contents beside it link to each section on GitHub.
LLM context nodes
Scope
If neither the file nor the request involves llm_context_node, LLMContextNode, LLMContext or tool from kedro.pipeline, stop here: this skill has nothing to add and must not be mentioned. Do not suggest converting ordinary nodes into LLM context nodes.
The API was added in Kedro 1.2.0 and its signature has not changed since. Kedro 1.2.0 to 1.6.0 mark it as experimental, and later releases ship it as stable. Check the installed version before writing code, because the API does not exist below 1.2.0.
CRITICAL: LLMContext has no execute(), run(), invoke() or stream(); the downstream node calls context.llm and context.tools[...] with their own APIs. context.tools is keyed by the name of the object a builder returns, never by the builder's name. Every parameter passed to tool(...) needs the params: prefix and must match a builder argument by name.
Check the installed version once
python -c "import sys, kedro; print(kedro.__version__, sys.executable)"
Your shell may not use the environment the user has activated. If the interpreter path is not inside an environment (it contains /envs/, /.venv/ or /virtualenvs/), re-run the command with the project's interpreter directly (<env-path>/bin/python -c ... or conda run -n <env> python -c ...); if you cannot tell which environment is the project's, ask. If no interpreter works, fall back to the kedro pin in requirements.txt or pyproject.toml.
-
Below 1.2.0: the API does not exist. Say so, and do not write a backport, a shim or an invented import.
-
1.2.0 or later: the API below applies. When this file and the installed code disagree, the installed code wins. It is one file of about 300 lines and is the whole feature:
python -c "import kedro.pipeline.llm_context as m; print(m.__file__)"
If you cannot run commands, say so and flag that the code was not verified against the installed version.
The whole API
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.
- 4d ago First seen · 316 lines · 79 tokens per session scan A 3c5dd63e0958
llm-context-nodes is a skill published in the GitHub repository kedro-org/kedro-skills (5 stars, last pushed 4d ago), licensed Apache-2.0. It adds 79 tokens to every session and 4,580 once invoked, about $0.0003 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 2026-09-26.
Other skills, from other repositories
llm-app-patterns
Production-ready patterns for building LLM applications. Covers RAG pipelines, agent architectures, prompt IDEs, and LLMOps monitoring. Use when designing AI applications, implementing RAG, building agents, or setting up LLM observability.
prompt-optimization
Improve a prompt on the evaluations workbench through a measured loop. Score the baseline first, then duplicate the target column, form a hypothesis from failing rows, edit the copy's prompt draft, run, compare pass rate and cost, and repeat until the numbers hold. Use when the user asks to optimize or improve a…
omh-model-optimization
This is a Hermes-native model-optimization workflow skill.
seedance-vocab-en
This skill should be used when an English Seedance 2.0 prompt needs clearer production wording, less generic prose, or precise vocabulary for camera, lighting, motion, VFX, audio, and constraints. Route blocked prompts through seedance-filter for context and boundary review.
ideogram4
Prompting patterns for Ideogram 4 text-to-image — best-in-class in-image text rendering and exact color/layout control via structured JSON captions. Use when generating images that need legible on-image text (title cards, thumbnails, logos, signage, CTAs), precise brand colors, or controlled spatial layout. Triggers…
enhance-prompt
Transforms vague UI ideas into polished, Stitch-optimized prompts. Enhances specificity, adds UI/UX keywords, injects design system context, and structures output for better generation results.