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 agentmods add skills/pedrohcgs/claude-code-my-workflow/deep-auditnpx skills add pedrohcgs/claude-code-my-workflow --skill deep-auditgit 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/deep-audit)<a href="https://agentmods.dev/skills/pedrohcgs/claude-code-my-workflow/deep-audit"><img src="https://agentmods.dev/badge/skills/pedrohcgs/claude-code-my-workflow/deep-audit.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 | $0.00117 | $0.02416 |
| Opus 5 | $0.00059 | $0.01208 |
| Sonnet 5 | $0.00023 | $0.00483 |
| Haiku 4.5 | $0.00012 | $0.00242 |
Grade A, and why
deep-audit 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.
How it starts
The opening of the file, as written. The whole thing — 91 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Deep adversarial audit
A convergent alternative to slow round-by-round review. Instead of one reviewer finding one or two issues per pass, fan out many independent skeptics over the whole artifact at once, adjudicate what they find, fix everything confirmed, and re-verify. Modeled on the multi-agent methodology behind hard formal-proof efforts (diverse independent portfolio, adversarial throughout, concrete evidence only, synthesize-challenge-repeat).
When to reach for this
- The artifact is dense enough that a single review keeps surfacing new issues each pass (the tell that round-by-round is the wrong tool).
- Correctness is the priority and the cost of a missed defect is high (a paper going to a top venue, a proof, a security-sensitive change, a migration).
- The user asked to "fix ALL of it", "be deeper", "converge faster", "100% rock solid".
Requires the user to have opted into multi-agent orchestration (they asked for a workflow / deep audit / to fan out agents, or ultracode is on). If they haven't, propose it and its rough cost first.
The method
1. Decompose (diverse portfolio). Break the artifact into components by idea, not by section: each independent claim, lemma, estimator, subsystem, invariant. Add cross-cutting failure-mode lenses (see below). Aim for coverage such that every load-bearing claim is attacked by at least one agent that is looking straight at it. Don't tell the agents your favored reading — preserve independence so they don't all converge on the same attractive-but-wrong conclusion.
2. Fan out adversarial finders (one per component). Each finder is prompted to refute, defaulting to "there is a bug," and must ground every claim in the actual text/code (read it, don't paraphrase from memory). Hard rules, borrowed from what works:
- Concrete findings only. Every finding = exact location (file:line / label + quoted text) + one-sentence defect + a failing case (specific inputs/configuration → wrong output, or the exact missing hypothesis).
- Reject status reports, "looks fine", "this is standard/routine", vague optimism, and "the global step is straightforward."
- A fix that re-imposes the same difficulty elsewhere, or assumes its own conclusion, is not a fix — flag it.
- If, after genuinely attacking, nothing is found, the agent must state the specific attacks it ran and why each closed — not just "clean."
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 91 lines · 117 tokens per session scan A fa20122dbf2a
deep-audit is a skill published in the GitHub repository pedrohcgs/claude-code-my-workflow (1,563 stars, last pushed 12d ago), licensed MIT. It adds 117 tokens to every session and 2,416 once invoked, about $0.0006 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 skills, from other repositories
paper-workflow
经管 / 社科实证论文全流程 meta-orchestrator：把选题、设计、数据、估计、方法闸门、 表图、写作、去 AI 味、质量门、修订、投稿与复盘编排成 Stage 0–9 可断点续跑流水线。 本 skill 不重复实现子能力，而是按阶段调用既有 skill 或并行 subagent，并在 Stage 3–4 路由 Python/StatsPAI、Stata、R 三种分析后端，Stage 9 交付一份含正文+表+图+参考文献的 Word 全文定稿（09submission/main.docx，另可出 .tex）。触发：/paper-workflow、 帮我写一篇实证论文、从选题到投稿、端到端 empirical…
econ-management-paper-polish
Writing, revision, review, evidence, journal adaptation, and method-safety support for economics, management, finance, accounting, marketing, information systems, public administration, and related business-school papers. Routes by discipline, subfield, language, method, outlet, section, and task mode while preserving…
did-causal
Use this Skill when the user needs to estimate causal treatment effects using difference-in-differences (DID) designs: two-way fixed effects (TWFE) regression, parallel trends pre-testing, Callaway-Sant'Anna staggered adoption estimator, and Goodman-Bacon decomposition. Covers both Python (linearmodels) and R (did…
solid-principles
SOLID principles checklist with Java examples. Use when a class has too many responsibilities, an abstraction leaks, or a dependency points the wrong way, and when the user asks about Single Responsibility, Open/Closed, Liskov, Interface Segregation or Dependency Inversion. For naming, duplication and method length…
architecture-review
Analyze Java project architecture at macro level - package structure, module boundaries, dependency direction, and layering. Use when user asks "review architecture", "check structure", "package organization", or when evaluating if a codebase follows clean architecture principles.
boundaries
Analyze Phoenix context boundaries and module coupling via mix xref. Use when checking cross-context calls, validating dependencies, before splitting modules, or reviewing architecture.