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 jacksonnnzzz/leam-opt-mcp --skill leam-reconstructgit clone --depth 1 https://github.com/jacksonnnzzz/leam-opt-mcpWrote 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/jacksonnnzzz/leam-opt-mcp/leam-reconstruct)<a href="https://agentmods.dev/skills/jacksonnnzzz/leam-opt-mcp/leam-reconstruct"><img src="https://agentmods.dev/badge/skills/jacksonnnzzz/leam-opt-mcp/leam-reconstruct/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/jacksonnnzzz/leam-opt-mcp/leam-reconstruct"><img src="https://agentmods.dev/badge/skills/jacksonnnzzz/leam-opt-mcp/leam-reconstruct.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 | $0.00073 | $0.01009 |
| Opus 5.5 | $0.00029 | $0.00404 |
| Sonnet 5.5 | $0.00015 | $0.00202 |
| Haiku 4.5 | $0.00007 | $0.00101 |
Grade A, and why
leam-reconstruct 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 21d 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 — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.
LEAM antenna reconstruction
Use the installed LEAM Python backend as the implementation; this skill is its conversational interface. Follow the user's selected case, model provider, and requested stopping point. Respond in the user's language and lead with the practical result and unresolved evidence.
Locate the backend
Find the project root containing pyproject.toml with project name leam-opt-mcp and
src/antenna_mcp. When this skill is in its source checkout, that root is two directories
above its folder. Otherwise use the user's selected workspace; do not hard-code a machine path.
Use that project's virtual environment and explicit workspace path for all commands.
Read references/workflow.md for supported commands and feedback routes.
Read the project's docs/REPRODUCIBILITY_ASSESSMENT.md when interpreting or revising scores.
If a configured LEAM MCP tool provides the same operation, it may replace the CLI call.
Installing the skill does not install Python dependencies, configure model credentials, or supply AEDT.
Choose the requested operation
- Explain or assess: inspect the existing job and source, or extract the specifically selected design from supplied sources. Stop at assessment when that is what the user requested.
- Generate: carry accepted evidence through the existing generation/export workflow and return the versioned Python artifact and its actual execution instructions.
- Correct: distinguish source-evidence corrections, model-code corrections, and changes to the evaluation method. Apply the corresponding route in the reference.
- Validate in HFSS: use the existing execution/validation services only when the user requested execution. Resolve the intended project/design/port from current state. A prior project name or an open desktop alone does not identify the present execution target.
Make assessments reviewable
For each assessed antenna report:
- Which thesis/paper, chapter, figure, design variant, and job were assessed.
- Backend-reported score and grade, extraction mode, and six dimension scores.
- The most consequential gaps, with criterion ID, cited page/figure/table, and what would resolve them. Distinguish missing source information from information the extractor missed.
- What the user can do next and clickable paths to the report and source artifacts.
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.
- 21d ago First seen · 80 lines · 73 tokens per session scan A c49a27650d4d
leam-reconstruct is a skill published in the GitHub repository jacksonnnzzz/leam-opt-mcp (0 stars, last pushed 13d ago), licensed MIT. It adds 73 tokens to every session and 1,009 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 2026-09-24.
Other skills, from other repositories
instrument-data-to-allotrope
Convert laboratory instrument output files (PDF, CSV, Excel, TXT) to Allotrope Simple Model (ASM) JSON format or flattened 2D CSV. Use this skill when scientists need to standardize instrument data for LIMS systems, data lakes, or downstream analysis. Supports auto-detection of instrument types. Outputs include full…
matlab
Builds, reviews, migrates, and plans MATLAB or GNU Octave numerical workflows. Use for arrays, tabular/time data, tests, projects, graphics, MAT files, and explicit Python interoperability.
exploratory-data-analysis
Performs bounded, local exploratory analysis of explicitly supported scientific files. Supports redacted CSV/TSV/JSON profiles; optional NumPy, HDF5, FASTA/FASTQ, and basic image metadata inspection; missingness/leakage audits; outlier and transformation sensitivity; and rigorous EDA report scaffolds. Other domain…
phylogenetics
Builds and analyzes phylogenetic trees using MAFFT multiple sequence alignment, IQ-TREE maximum likelihood with ModelFinder and branch support, and FastTree approximate inference. Uses ETE3 for tree summaries and visualization. Applies to homologous nucleotide or protein sequences, microbial gene trees, protein…
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.
presenting-conference-talks
Generates conference presentation slides (Beamer LaTeX PDF and editable PPTX) from a compiled paper with speaker notes and talk script. Use when preparing oral talks, spotlight presentations, or invited talks for ML and systems conferences.