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 svd-ai-lab/sim-plugin-openfoam --skill openfoamgit clone --depth 1 https://github.com/svd-ai-lab/sim-plugin-openfoamWrote 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/svd-ai-lab/sim-plugin-openfoam/openfoam)<a href="https://agentmods.dev/skills/svd-ai-lab/sim-plugin-openfoam/openfoam"><img src="https://agentmods.dev/badge/skills/svd-ai-lab/sim-plugin-openfoam/openfoam.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 | $0.00058 | $0.01952 |
| Opus 5 | $0.00029 | $0.00976 |
| Sonnet 5 | $0.00012 | $0.00390 |
| Haiku 4.5 | $0.00006 | $0.00195 |
Grade A, and why
openfoam-sim 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 — 162 lines — stays where its author put it; the contents beside it link to each section on GitHub.
openfoam-sim
You are driving OpenFOAM through sim-cli. This file is the index.
Detail lives in references/ — load progressively, only what the task needs.
How to load this skill
Don't read every reference up front — context is precious. Walk this list:
- Always read
references/case-setup.mdbefore authoring any case. - Pick a solver via
references/solver-selection.md. - Look up the fields & dictionaries you'll need in
references/field-and-dictionary-matrix.md. - For boundary conditions:
references/boundary-conditions.md. - If the case has turbulence:
references/turbulence-setup.md. - If the case is multiphase / VOF:
references/multiphase-vof.md. - If the case has heat or buoyancy:
references/heat-transfer.md(andreferences/conjugate-heat-transfer.mdfor solid+fluid). - For mesh generation:
references/mesh-and-blockmesh.md. - For schemes / solvers / relaxation:
references/numerics-and-schemes.md. - For runtime monitors / probes / forces:
references/function-objects.md. - For parallel execution and decomposition:
references/parallel-execution.md. - For runtime log diagnosis:
references/log-parsing-and-residuals.md. - For post-processing (sample lines, point queries, integrals):
references/post-processing.md. - For complete case skeletons by scenario:
references/case-recipes.md. - When something fails:
references/error-recovery.md— decision tree + fix sequences.
sim-cli integration (one-shot mode)
Most benchmark/single-shot use is one-shot:
# 1. Write your driver script. Conventionally `solve.py`.
# The script invokes blockMesh / solver / postProcess via subprocess,
# parses the result, and writes the answer to disk.
# 2. Run via sim-cli:
uv run sim run solve.py --solver openfoam
# sim wraps the script in a RunResult (exit_code, stdout, stderr, duration,
# errors) and stores it under `.sim/runs/`. Browse with:
uv run sim logs # list runs
uv run sim logs last # full last RunResult
uv run sim logs last --field exit_code
What ships with it
29 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.
- base/docs/parallel_test_results.md 7.1 KB
- base/docs/prompt_for_linux_claude.md 4.3 KB
- base/docs/tutorial_runner_v2.md 3.6 KB
- base/docs/tutorial_test_plan.md 7.6 KB
- base/docs/tutorial_test_results.md 10 KB
- references/boundary-conditions.md 7.3 KB
- references/case-recipes.md 9.3 KB
- references/case-setup.md 7.4 KB
- references/conjugate-heat-transfer.md 7.8 KB
- references/error-recovery.md 11 KB
- references/failure_patterns.md 8.7 KB
- references/field-and-dictionary-matrix.md 6.6 KB
- references/function-objects.md 7.3 KB
- references/heat-transfer.md 7.4 KB
- references/log-parsing-and-residuals.md 8.1 KB
- references/mesh-and-blockmesh.md 7.5 KB
- references/multiphase-vof.md 8.3 KB
- references/numerics-and-schemes.md 9.3 KB
- references/parallel-execution.md 5.9 KB
- references/post-processing.md 8.4 KB
- references/solver-selection.md 6.1 KB
- references/turbulence-setup.md 7.0 KB
- solver/v2206/notes.md 329 B
- solver/v2312/notes.md 207 B
- solver/v2406/notes.md 333 B
- tests/fixtures/cavity_setup.sh 142 B runs code
- tests/fixtures/empty.foam 0 B
- tests/fixtures/hello_foam.py 81 B runs code
- tests/test_driver.py 8.3 KB runs code
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 · 162 lines · 58 tokens per session scan A 679e92b1aa5c
openfoam-sim is a skill published in the GitHub repository svd-ai-lab/sim-plugin-openfoam (5 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 58 tokens to every session and 1,952 once invoked, about $0.0003 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 2026-08-31.
Other skills, from other repositories
abaqus-sim
Use when the user asks Codex, Claude Code, ChatGPT-style coding agents, or another AI agent to automate, inspect, run, or debug Abaqus through sim-cli. Supports Abaqus/CAE noGUI workflows, batch jobs, model inspection, ODB diagnostics, bounded execution, artifact reporting, and troubleshooting. Requires a user-owned…
sim-cli
Cross-solver operating discipline for sim-cli workflows — tool choice, input classification, acceptance semantics, and escalation rules that apply across solvers. Use alongside the solver's own plugin skill, which is self-contained for solver-specific work; this skill carries only the shared rules.
workbench-sim
Use when the user asks Codex, Claude Code, ChatGPT-style coding agents, or another AI agent to connect to Ansys Workbench through sim-cli. Supports Workbench journal execution, project inspection, persistent sessions, Mechanical handoff, bounded execution, artifact reporting, and troubleshooting. Requires a user-owned…
neuroskill-bci
Use live BCI cognitive and mood state from NeuroSkill.
saelens
Train sparse autoencoders to interpret model features.
ast-grep
AST-aware structural code search and rewrite via ast-grep.