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.
Borrowing it
Nothing to install: this file belongs to pedrohcgs/claude-code-my-workflow. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/pedrohcgs/claude-code-my-workflow/main/CLAUDE.mdgit 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/instructions/pedrohcgs/claude-code-my-workflow/claude-md)<a href="https://agentmods.dev/instructions/pedrohcgs/claude-code-my-workflow/claude-md"><img src="https://agentmods.dev/badge/instructions/pedrohcgs/claude-code-my-workflow/claude-md/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/instructions/pedrohcgs/claude-code-my-workflow/claude-md"><img src="https://agentmods.dev/badge/instructions/pedrohcgs/claude-code-my-workflow/claude-md.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 | $0.02333 | $0.02333 |
| Opus 5.5 | $0.00933 | $0.00933 |
| Sonnet 5.5 | $0.00467 | $0.00467 |
| Haiku 4.5 | $0.00233 | $0.00233 |
Grade A, and why
claude-code-my-workflow CLAUDE.md 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 28d 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 — 166 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.MD -- Academic Project Development with Claude Code
Project: [YOUR PROJECT NAME] Institution: [YOUR INSTITUTION] Branch: main
Scope Discipline
Do exactly what was asked — nothing adjacent. Do not add README files, build scripts,
.gitignore edits, helper utilities, or extra tooling that was not requested. If an addition
looks valuable, list it as a suggestion at the end and let the user decide.
A request for a codebook is a request for a codebook. Delivering a codebook plus a README plus build scripts plus gitignore edits means the user now has to review four things to accept one, and the usual outcome is that all four get thrown away.
Before adding anything not named in the request, ask. One line is cheaper than a revert.
Core Principles
- Plan first -- enter plan mode before non-trivial tasks; save plans to
quality_reports/plans/ - Verify after -- when a task changes a
.tex,.qmd, or.Rfile, compile or render it and confirm the output before reporting done - Single source of truth -- Beamer
.texis authoritative; Quarto.qmdderives from it - Quality gates -- nothing ships below 80/100
- [LEARN] tags -- when corrected, save
[LEARN:category] wrong → rightto MEMORY.md
Cross-session context lives in MEMORY.md; past plans, specs, and session logs are in quality_reports/.
How we verify — the references and rules that carry the verification discipline:
verification-ladder.md— the seven rungs, from qualify the checker to the external oracle, and how the review loop converges.external-oracle-process.md— running an independent frontier-model referee (Claude Code → another vendor's model via the Oracle CLI; current targets in its §2) and adjudicating what it returns.provenance-and-ground-truth.md— naming and pinning your oracles, classifying divergence, and the clean-room boundary.review-fencing.md— reviewer independence is a property of the environment, not an instruction: a neutral copy outside the checkout, prior verdicts withheld, and the answer keys the repo already commits fenced off.release-engineering.md— shipping research software: message and silent-resolution censuses, frozen feature matrices for ports, hash-claimed inherited tests, and downstream consumers pinned by commit SHA.
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.
- 28d ago Changed · +1 lines · +95 tokens per session a4cd39514cc1
- 1mo ago First seen · 165 lines · 2,238 tokens per session scan A 98855aa3b751
claude-code-my-workflow CLAUDE.md is an instructions file published in the GitHub repository pedrohcgs/claude-code-my-workflow (1,668 stars, last pushed 28d ago), licensed MIT. It adds 2,333 tokens to every session, about $0.0093 per session on Opus 5.5. 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 instructions, from other repositories
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
deno copilot-instructions.md
Copilot instructions for denoland/deno, covering deno development guide for github copilot, network access, high level overview, key directories and key files to understand first.