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.
npx skills add pedrohcgs/claude-code-my-workflow --skill respond-to-refereesgit 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/skills/pedrohcgs/claude-code-my-workflow/respond-to-referees)<a href="https://agentmods.dev/skills/pedrohcgs/claude-code-my-workflow/respond-to-referees"><img src="https://agentmods.dev/badge/skills/pedrohcgs/claude-code-my-workflow/respond-to-referees/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/pedrohcgs/claude-code-my-workflow/respond-to-referees"><img src="https://agentmods.dev/badge/skills/pedrohcgs/claude-code-my-workflow/respond-to-referees.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Agent Snooping · line 129 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
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 | $0.00070 | $0.02168 |
| Opus 5 | $0.00035 | $0.01084 |
| Sonnet 5 | $0.00014 | $0.00434 |
| Haiku 4.5 | $0.00007 | $0.00217 |
Grade A, and why
respond-to-referees 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 6d 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- respond-to-referees — 97% identical, 6 lines differ
How it starts
The opening of the file, as written. The whole thing — 145 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Respond to Referees
Produce a complete response-to-referees document by cross-referencing the referee report against the revised manuscript. Classify every concern, draft a courteous response for each, and flag anything unaddressed before submission.
Inputs
$0— path to the referee report$1— path to the revised manuscript
Supported formats and how to read them. In the commands below, FILE stands for the input path being converted — either $0 (referee report) or $1 (revised manuscript). Always use mktemp for the temp file (not a predictable /tmp/... name) so paths with spaces and concurrent runs don't collide, and so untrusted FILE paths can't clobber other temp files via symlink races.
| Format | How to extract text |
|---|---|
.tex, .qmd, .md, .txt |
Read directly with the Read tool. |
.pdf |
TMP=$(mktemp --suffix=.txt) && pdftotext "FILE" "$TMP" (poppler-utils; use mktemp -t ... on macOS if --suffix is unsupported). Grep "$TMP". |
.docx |
TMP=$(mktemp --suffix=.txt) && pandoc "FILE" -t plain -o "$TMP" (or docx2txt "FILE" "$TMP"). Grep "$TMP". |
.html |
TMP=$(mktemp --suffix=.txt) && pandoc "FILE" -t plain -o "$TMP". Grep "$TMP". |
If a required tool is missing or extraction fails, ask the user to provide a plain-text version (.txt or .md) and stop.
Workflow
Step 0: Convert Inputs to Plain Text
Before any parsing or grep, convert non-text inputs (.pdf, .docx, .html) to plain text using the table above. Keep both the temp text file (for grep) and the original (for citation page references).
Step 1: Parse the Referee Report
- Read the report end-to-end.
- Decompose into discrete numbered concerns. Common patterns:
- Numbered or bulleted enumerations ("1.", "(a)", "Comment 1", etc.).
- Section headers ("Major comments", "Minor comments").
- Implicit concerns embedded in prose paragraphs — extract these too.
- For each concern, capture:
- Concern ID (R{n}.{m} = referee n, comment m)
- Severity the referee assigned (major / minor / typographic)
- Verbatim quote of the most representative sentence (~25 words max)
- One-line summary in your own words
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.
- 6d ago First seen · 145 lines · 70 tokens per session scan A 346fe4e065d0
respond-to-referees is a skill published in the GitHub repository pedrohcgs/claude-code-my-workflow (1,569 stars, last pushed 16d ago), licensed MIT. It adds 70 tokens to every session and 2,168 once invoked, about $0.0003 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 2026-09-03.
Other skills, from other repositories
fin-paper-figure
Generate academic-quality figures (>=300 DPI) for economics and finance papers.
fin-paper-writing
A workflow for turning a research outline and study design into a complete economics or finance paper. It coordinates drafting, figure creation, consistency checks, review rounds, LaTeX compilation, and submission checks.
fin-viz-launch
A tool for turning research data and a written description into academic charts. It can choose a suitable chart type, create plotting code with matplotlib or seaborn, and save the result as a high-resolution PDF, SVG, or PNG.
fin-data-acquisition
A data-preparation workflow for financial research. It reads variable definitions from a completed research design and produces data-acquisition work plus executable Python or Stata regression scripts.
fin-lit-review
A systematic literature-review workflow for economics and finance. It searches several academic sources, maps how papers cite one another, and organizes the main findings and research gaps.
fin-submit-check
A pre-submission checklist for an academic paper and its LaTeX files. It checks journal requirements such as anonymous authorship, length, spacing, margins, citations, figures, data availability, and other submission details.