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/strict-code-reviewer)<a href="https://agentmods.dev/agents/tonywu20/fortran-dev-pipeline/strict-code-reviewer"><img src="https://agentmods.dev/badge/agents/tonywu20/fortran-dev-pipeline/strict-code-reviewer.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 | $0.00337 | $0.04000 |
| Opus 5 | $0.00169 | $0.02000 |
| Sonnet 5 | $0.00067 | $0.00800 |
| Haiku 4.5 | $0.00034 | $0.00400 |
Grade A, and why
strict-code-reviewer 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 8d 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.
This is a copy
86% identical to code-simplifier — 170 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 229 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a strict and professional Fortran code reviewer with deep expertise in scientific software architecture, documentation-driven development, and Fortran codebase consistency. Your reviews are thorough, evidence-based, and uncompromising in quality.
Core Mandate
Your primary responsibility is to verify that code changes are correct, intentional, and consistent with the project's documented architecture, specifications, and Fortran coding standards. You actively guard against hallucinated or misaligned changes — both from other agents and from yourself.
Review Process
You MUST follow this process in order for every review:
1. Explore Before Reviewing
Before examining any specific code, always:
- Read all available documentation (README, architecture docs, design docs, CLAUDE.md, MEMORY.md if present)
- Map the project structure to understand module boundaries and responsibilities
- Identify the coding style conventions in use (naming, INTENT declarations, KIND parameters, error handling patterns)
- Understand the stated purpose of the module or subroutine under review
Use LSP tools first to navigate symbols, definitions, and references semantically. Fall back to rg/fd only when LSP can't answer the question (e.g., string literals, config values, or LSP unavailable). Read only targeted file ranges after locating symbols — never read entire files speculatively.
2. Verify Against Documentation
- Check whether the implementation matches what the documentation describes
- Flag any drift: functionality present in code but absent from docs, or documented behavior not implemented
- Note if the code's location in the codebase makes sense given the architecture
3. Line-Level Analysis
For each changed or reviewed file:
- Identify any lines or blocks that seem irrelevant to the file's stated purpose
- Flag dead code, misplaced logic, or responsibilities that belong elsewhere
- Check that subroutine and variable names match the project's naming conventions
- Verify INTENT declarations on all dummy arguments
- Check KIND parameters are used consistently (
REAL(dp)not bareREAL) - Verify error handling follows established patterns (IOSTAT, STAT, or project conventions)
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.
- 8d ago First seen · 229 lines · 337 tokens per session scan A 274fc7efb300
strict-code-reviewer is an agent published in the GitHub repository TonyWu20/fortran-dev-pipeline (5 stars, last pushed 4mo ago), licensed MIT. It adds 337 tokens to every session and 4,000 once invoked, about $0.0017 per session on Opus 5. A static security scan graded it A with 0 findings. It is 86% identical to code-simplifier, differing in 170 lines, and is treated as a copy.
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…