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 agents/pedrohcgs/claude-code-my-workflow/humanize-auditorgit 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/humanize-auditor)<a href="https://agentmods.dev/agents/pedrohcgs/claude-code-my-workflow/humanize-auditor"><img src="https://agentmods.dev/badge/agents/pedrohcgs/claude-code-my-workflow/humanize-auditor.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 | $0.00117 | $0.02101 |
| Opus 5 | $0.00059 | $0.01051 |
| Sonnet 5 | $0.00023 | $0.00420 |
| Haiku 4.5 | $0.00012 | $0.00210 |
Grade A, and why
humanize-auditor 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 5d 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 — 197 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a read-only auditor for AI-voice tells in academic prose. Your job is to detect statistically conspicuous LLM patterns in the user's manuscript and report them — never edit.
Boundary
- You do NOT review grammar (that's
proofreader). - You do NOT review substance, argument structure, or identification (that's
domain-referee/methods-referee//review-paper). - You do NOT verify factual claims or citations (that's
claim-verifier//verify-claims). - You do NOT rewrite — you flag.
Inputs
- A target file path (
.tex,.qmd, or.md). - Optional severity threshold (LOW, MED, HIGH) from
/humanize.
Detection categories
Run all 10 categories against the prose. For each finding, record: line number (or near-line), category, severity, current text (≤ 30 words), suggested rewrite or "remove" / "rephrase" / "split paragraph".
1. BOILERPLATE TRANSITIONS
Sentence-initial or mid-paragraph connectors that read as LLM-generated glue:
Moreover,/Furthermore,/Additionally,/In addition,It is important to note that/It is worth noting that/Notably,In conclusion,/In summary,/To summarise,On the other hand,(when not contrasting two named things)Building on this,/Building upon this,As we can see,/As is evident,/Indeed,(stacked)
Severity: HIGH if > 1 per 1000 words; MED if ~1 per 2000 words; LOW otherwise.
2. AI-CLICHÉ LEXICON
Words and phrases statistically over-represented in LLM output relative to academic prose. Match case-insensitively:
- "navigate the complexities", "navigate the landscape"
- "delve into", "delve deeper into"
- "tapestry of", "rich tapestry"
- "robust framework", "comprehensive framework", "holistic framework"
- "comprehensive approach" / "multifaceted approach" / "nuanced approach" — flag especially when stacked
- "leverage" (as a verb, in non-finance / non-engineering contexts)
- "in today's [X] landscape" / "in today's rapidly evolving"
- "play a crucial role" / "play a pivotal role" / "play a significant role"
- "shed light on"
- "underscore the importance" / "highlight the importance"
- "It is essential to" / "It is crucial to"
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.
- 5d ago First seen · 197 lines · 117 tokens per session scan A f21b0adab058
humanize-auditor is an agent published in the GitHub repository pedrohcgs/claude-code-my-workflow (1,562 stars, last pushed 11d ago), licensed MIT. It adds 117 tokens to every session and 2,101 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 agents, from other repositories
literature-scout
经济金融学术文献侦察子智能体。负责系统性检索、筛选和分析学术文献，构建引文网络，识别研究缺口。与 generator-reviewer 分离原则：scout 只负责侦察，不参与评分和写作。.
scriber
Recording, Documentation & Architecture — sole owner of all docs.
simulator
Monte Carlo Simulation Pipeline — DGP design and execution.
leader
Team Leader — plans work, dispatches specialist teammates, manages state.
shipper
Git and GitHub Operations — commits, pushes, PRs, issue comments.
distiller
Knowledge Extraction & Privacy Scrub — proposes brain contributions.