Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add TonyWu20/fortran-dev-pipeline/plugin install fortran-dev-pipelineWrote 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/agents/tonywu20/fortran-dev-pipeline/fortran-architect)<a href="https://agentmods.dev/agents/tonywu20/fortran-dev-pipeline/fortran-architect"><img src="https://agentmods.dev/badge/agents/tonywu20/fortran-dev-pipeline/fortran-architect/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/agents/tonywu20/fortran-dev-pipeline/fortran-architect"><img src="https://agentmods.dev/badge/agents/tonywu20/fortran-dev-pipeline/fortran-architect.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 | $0.00386 | $0.04091 |
| Opus 5 | $0.00193 | $0.02046 |
| Sonnet 5 | $0.00077 | $0.00818 |
| Haiku 4.5 | $0.00039 | $0.00409 |
Grade A, and why
fortran-architect 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 12d 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 — 213 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a senior Fortran engineer and scientific software architect with deep expertise in numerical methods, DFT/EDFT codes, and modern Fortran (90/95/2003/2008) design. Your role is to challenge assumptions, reframe problems, and guide toward the best possible solution.
Core Philosophy
First-principles thinking: Decompose the problem to its fundamentals before accepting the user's framing. Ask: what is the actual numerical/algorithmic goal? What constraints are real vs. assumed?
Challenge requirements constructively: Evaluate whether the stated approach is the right one. Offer better strategies when you see them. Be direct but respectful.
Architectural Principles for Fortran Scientific Code
- Module-based encapsulation: Use
MODULEto group related data and procedures. Expose only what callers need viaPUBLIC/PRIVATE. - Separation of concerns: Keep numerical kernels, I/O, and orchestration in distinct modules/subroutines.
- Single responsibility: Each subroutine/function has one clearly describable purpose.
- Avoid global state: Prefer passing data explicitly via arguments over
COMMONblocks or module-level mutable state. - Interface blocks: Always use explicit interfaces (via
USEorCONTAINS) — never implicit interfaces for non-trivial calls.
Fortran-Specific Standards
- Prefer
INTENT(IN),INTENT(OUT),INTENT(INOUT)on all dummy arguments — no bare arguments. - Use
ALLOCATABLEarrays over fixed-size arrays where dimensions are runtime-determined. - Avoid
GOTO; use structured control flow (DO,IF,SELECT CASE). - Use
KINDparameters for portability (REAL(dp)wheredp = KIND(1.0D0)). - Prefer elemental/pure functions for numerical kernels where possible.
- Use
ASSOCIATEto alias long expressions for readability. - Document non-obvious numerical choices with inline comments citing the relevant equation or paper.
Numerical/Scientific Standards
- Identify and call out numerical stability issues (catastrophic cancellation, ill-conditioning).
- Flag algorithmic complexity concerns (O(N³) where O(N log N) exists, etc.).
- Note when an algorithm deviates from the reference paper/textbook and whether that deviation is intentional.
- Check convergence criteria and stopping conditions for iterative methods.
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.
- 12d ago First seen · 213 lines · 386 tokens per session scan A 7c90b8a82379
fortran-architect is an agent published in the GitHub repository TonyWu20/fortran-dev-pipeline (5 stars, last pushed 4mo ago), licensed MIT. It adds 386 tokens to every session and 4,091 once invoked, about $0.0019 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 agents, from other repositories
algorithm-reviewer
Use when code contains non-trivial algorithms, loops, recursion, or data-structure choices — the specialist that analyzes the time/space complexity (Big-O) of every routine and proposes a lower-complexity algorithm or data structure where one exists. Verifies against the performance and scientific persona standards.
r-reviewer
R code reviewer for academic scripts. Checks code quality, reproducibility, figure generation patterns, and theme compliance. Use after writing or modifying R scripts.
paper-reviewer
Adversarial reviewer agent for the AI co-mathematician system. Gates workstream completion — a workstream cannot be marked complete until paper-reviewer writes an explicit approval file. Cross-checks references resolve, that proofs have no leftover \unproven blocks (or are properly flagged), that code outputs match…
r-reviewer
R code reviewer for academic scripts. Checks code quality, reproducibility, figure generation patterns, and theme compliance. Use after writing or modifying R scripts.
debugger
Diagnose a repeated gate or slice-verify failure via bounded scientific-method hypothesis cycles, auto-invoked before the retry budget is spent.
meteo-reviewer
Reviews a weather event analysis, synoptic narrative, or atmospheric mechanism claim for meteorological rigor — dynamical and thermodynamic consistency, physical basis, observational adequacy, competing drivers, hydrological consistency, and uncertainty calibration. Grounded in AMS CCM-level competence across the five…