A specialist coding agent for PyMAPDL, the Python interface to Ansys MAPDL engineering software. It handles features, bugs, performance work, and API design within that repository.

Changing PyMAPDL code, fixing its bugs, improving performance, designing APIs, and running its test and CI-like environments.

It provides project-specific rules for generated files, local or remote connections, dependencies, tests, and Docker-based checks.

developer — Agent by ansys

Install

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.

agentmods

npx agentmods add agents/ansys/pymapdl/developer

Clone the repo

git clone --depth 1 https://github.com/ansys/pymapdl

Per session 29 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 596 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. Scan, not verified.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00029	$0.00596
Opus 5	$0.00015	$0.00298
Sonnet 5	$0.00006	$0.00119
Haiku 4.5	$0.00003	$0.00060

Measured yesterday against content hash 0a9c81d7a69c, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

developer 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 yesterday.

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.

.github/agents/developer.agent.md · 63 lines

How it starts

The opening of the file, as written. The whole thing — 63 lines — stays where its author put it; the contents beside it link to each section on GitHub.

PyMAPDL Developer Agent

Architecture constraints

Do not modify src/ansys/mapdl/core/_commands/ — auto-generated from MAPDL source.
Override MAPDL commands in _MapdlCommandExtended in src/ansys/mapdl/core/mapdl_extended.py.
Connection modes: local vs remote; grpc (default) vs console (console is discouraged, Linux-only).

Dependencies

Runtime deps: [project.dependencies] in pyproject.toml.
Test/doc extras: exact pins (==) under [project.optional-dependencies].
Run uv lock after changes; don't commit unrelated uv.lock changes.

Commands

uv run pre-commit install           # once
uv run pre-commit run --all-files   # before every commit
uv run pytest                       # tests (set PYMAPDL_START_INSTANCE=False to connect to an existing instance instead of launching MAPDL)

CI-like testing via tox + Docker

The repo provides tox envs that spin up MAPDL (and optionally DPF) Docker containers and run the full test matrix, matching CI. Use uvx so the pinned venv is used, as CI does.

Key envs:

Env	Purpose
`docker-run-mapdl`	Start MAPDL container in background
`docker-run-mapdl-dpf`	Start MAPDL + DPF containers
`docker-stop-mapdl`	Stop/remove MAPDL containers
`docker-stop-mapdl-dpf`	Stop/remove MAPDL+DPF containers
`docker-test-local`	Run tests against local Docker images
`docker-test-remote`	Run tests mirroring CI (remote images)
`docker-test-local-build`	Rebuild the local-host image without running tests
`docker-test-remote-build`	Rebuild the remote-host image without running tests

Each directory that needs env vars contains an example.env. Copy to .env and edit — tox loads it automatically.

# Example (Unix/macOS)
export PYMAPDL_PORT=50052 PYMAPDL_START_INSTANCE=True
uvx tox -e docker-run-mapdl
uvx tox -e docker-test-local
uvx tox -e docker-stop-mapdl

Workflow

Implement -> add/update numpydoc docstrings -> run pre-commit again
Delegate tests to tester agent (≥90% coverage required)
Delegate docs (docstring and Sphinx documentation) to documentation agent
Submit for reviewer agent approval

Read the full file on GitHub · 63 lines

Changes

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.

yesterday First seen · 63 lines · 29 tokens per session scan A 0a9c81d7a69c

Subscribe to this mod's changes

developer is an agent published in the GitHub repository ansys/pymapdl (513 stars, last pushed 2d ago), licensed MIT. It adds 29 tokens to every session and 596 once invoked, about $0.0001 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.

Backend and APIs Debugging Testing ansys apdl mesh numerical-simulation python structural-mechanics

strategic-advisor

Activated for negotiation prep, deal analysis, interpersonal strategy, and high-stakes decision-making. Combines game theory with psychological awareness.

winstonkoh87/Athena-Public · 31 tokens

fsl-vacuity-reviewer

Use PROACTIVELY after adding or changing a .fsl spec under specs/ or examples/. Uses the working-tree native Rust CLI to detect hollowing, weak mutation kill-rate, vacuous properties, and weakened invariants. Read-only on specs; may run verifier commands.

ymm-oss/fsl · 64 tokens

developer