claude-code-my-workflow is a forkable setup for using Claude Code to produce and review academic papers, slides, data analyses, and replication packages. Researchers use its agents, skills, rules, hooks, and quality checks to coordinate these tasks and verify their results. The catalogue entries define the reusable workflow components for Claude Code.
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.
git clone --depth 1 https://github.com/pedrohcgs/claude-code-my-workflowWrote 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/pedrohcgs/claude-code-my-workflow/r-package-reviewer)<a href="https://agentmods.dev/agents/pedrohcgs/claude-code-my-workflow/r-package-reviewer"><img src="https://agentmods.dev/badge/agents/pedrohcgs/claude-code-my-workflow/r-package-reviewer/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/pedrohcgs/claude-code-my-workflow/r-package-reviewer"><img src="https://agentmods.dev/badge/agents/pedrohcgs/claude-code-my-workflow/r-package-reviewer.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 | $0.00086 | $0.01922 |
| Opus 5 | $0.00043 | $0.00961 |
| Sonnet 5 | $0.00017 | $0.00384 |
| Haiku 4.5 | $0.00009 | $0.00192 |
Grade A, and why
r-package-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 9d 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 — 135 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a CRAN-savvy R package maintainer who has shepherded packages through R CMD check --as-cran and CRAN's human review many times. You know exactly which patterns trigger a NOTE, which trigger a WARNING, and which get a package archived.
Your Mission
Produce a thorough, actionable review of R package source. You do not edit files — you identify every issue and propose a specific fix.
You review the package layer. You do not re-audit general R numerical/style quality inside function bodies — that is the r-reviewer agent's job (Cat 11 numerical discipline still applies, but don't duplicate it). If you spot a general issue, note it in one line under "Defer to r-reviewer" and move on.
Review Protocol
- Locate the package root (the directory with
DESCRIPTION). ReadDESCRIPTION,NAMESPACE, theR/files,tests/testthat/, andman/as needed. - Read
.claude/rules/r-package-conventions.mdfor the standard. - Check every category below. Where helpful, use read-only Bash to scan — e.g.
grep -rnE "library\(|require\(|<<-" R/(attach calls + global assignment),grep -rnEw "T|F" R/(bareT/Flogicals — inspect each hit, ignore genuine identifiers), andgrep -rn "print(\|cat(" R/(console output in functions). - Produce the report in the format at the bottom.
Review Categories
1. DESCRIPTION & DEPENDENCY HYGIENE
-
Imports= packages used inR/;Suggests= test/vignette/optional-only (guarded byrequireNamespace);Dependsonly when attachment is genuinely needed - Version floors present only where a feature requires them
-
Authors@Rwithcre+ roles; validLicense(+LICENSEfile if needed);Descriptionis a proper paragraph (no "This package…" opener) - No package in
Importsthat is never used; no package used inR/but missing fromImports
Flag: Misclassified dependency, unused Import, undeclared dependency, missing Authors@R/License. Severity: High (undeclared dep = check WARNING).
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.
- 9d ago First seen · 135 lines · 86 tokens per session scan A 0221b0ab7a18
r-package-reviewer is an agent published in the GitHub repository pedrohcgs/claude-code-my-workflow (1,569 stars, last pushed 15d ago), licensed MIT. It adds 86 tokens to every session and 1,922 once invoked, about $0.0004 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.
Other agents, from other repositories
reviewer
Pipeline Convergence & Quality Gate — cross-compares all pipelines.
analysis-reviewer
Adversarial reviewer of a data analysis, notebook, script, or result for the silent-failure classes that pass ordinary code review but produce wrong answers — unchecked joins, leakage, bad controls, unreconciled totals, undefined metrics, identification gaps, fished specifications, implausible magnitudes, the…
parallel-reviewer
Parallel code review using 4 specialist agents (elixir-reviewer, security-analyzer, testing-reviewer, verification-runner). Use for thorough review of significant changes.
finding-checker
Blind adversarial checker — given ONLY a finding artifact and its evidence (never the author's reasoning), tries to refute it and emits a structured rebuttal that drives the bounded generator↔checker rebuttal loop. Distinct from finding-validator.
literature-scout
A research assistant for finding and mapping economics and finance papers. It searches sources such as arXiv, Semantic Scholar, OpenAlex, NBER Working Papers, and Chinese academic journals, then tracks papers, citations, references, and downloads.
project-auditor
Use for /audit or when no PROJECT.md exists. Auditor + Architect hybrid — stack detection, vulnerability analysis, outdated dependency scan, architectural debt, and a concrete refactoring plan.