verifier

verifier is an agent for Claude Code from pedrohcgs/claude-code-my-workflow. It costs 31 tokens per session (882 once invoked), scanned A, original, MIT.

An end-to-end checker for academic course materials that compiles, renders, or runs each changed file and checks the resulting output.

In plain words
What is it for?
Use it to verify LaTeX slides, Quarto documents, R scripts, and SVG diagrams, including their generated PDFs, HTML, plots, and data files.
Why use it?
It catches build failures, rendering problems, warnings, missing references, and empty or missing generated files before delivery.

Agent for Claude Code

Written for Claude Code: effort in frontmatter. Also seen: model in frontmatter.

Needs its repository: it reads a path above its own folder, which exists only inside the repository. The line is TEXINPUTS=../Preambles:$TEXINPUTS xelatex -interaction=nonstopmode FILENAME.tex 2>&1 | tail -20.

Good fit Use it to verify LaTeX slides, Quarto documents, R scripts, and SVG diagrams, including their generated PDFs, HTML, plots, and data files.

Compare 6 agents from other repositories ↓
About the project

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.

pedrohcgs/claude-code-my-workflow · 1,668 stars · on GitHub · psantanna.com

Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo
git clone --depth 1 https://github.com/pedrohcgs/claude-code-my-workflow
agentmods
npx agentmods add agents/pedrohcgs/claude-code-my-workflow/verifier

Made for: Claude Code.

Wrote 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.

agentmods badge for verifier

README.md
[![agentmods](https://agentmods.dev/badge/agents/pedrohcgs/claude-code-my-workflow/verifier/github.svg)](https://agentmods.dev/agents/pedrohcgs/claude-code-my-workflow/verifier)
Your own site
<a href="https://agentmods.dev/agents/pedrohcgs/claude-code-my-workflow/verifier"><img src="https://agentmods.dev/badge/agents/pedrohcgs/claude-code-my-workflow/verifier/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.

agentmods 80×15 button for verifier

Your own site · 80×15
<a href="https://agentmods.dev/agents/pedrohcgs/claude-code-my-workflow/verifier"><img src="https://agentmods.dev/badge/agents/pedrohcgs/claude-code-my-workflow/verifier.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 31 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 882 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00031 $0.00882
Opus 5.5 $0.00012 $0.00353
Sonnet 5.5 $0.00006 $0.00176
Haiku 4.5 $0.00003 $0.00088

Measured 27d ago against content hash 477059de673b, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

verifier 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 27d 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.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

  • verifier — 97% identical, 9 lines differ
.claude/agents/verifier.md · 96 lines

How it starts

The opening of the file, as written. The whole thing — 96 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a verification agent for academic course materials.

Your Task

For each modified file, verify that the appropriate output works correctly. Run actual compilation/rendering commands and report pass/fail results.

Verification Procedures

For .tex files (Beamer slides):

cd Slides
TEXINPUTS=../Preambles:$TEXINPUTS xelatex -interaction=nonstopmode FILENAME.tex 2>&1 | tail -20
  • Check exit code (0 = success)
  • Grep for Overfull \\hbox warnings — count them
  • Grep for undefined citations — these are errors
  • Verify PDF was generated: ls -la FILENAME.pdf

For .qmd files (Quarto slides):

./scripts/sync_to_docs.sh LectureN 2>&1 | tail -20
  • Check exit code
  • Verify HTML output exists in docs/slides/
  • Check for render warnings
  • Plotly verification: grep for htmlwidget count in rendered HTML
  • Environment parity: scan QMD for all ::: {.classname} and verify each class exists in the theme SCSS

For .R files (R scripts):

# Pipeline stages share one environment, and 02_clean.R through 05_figures.R
# stop() when run on their own: verify a change to any stage through the orchestrator.
Rscript scripts/R/00_run_all.R 2>&1 | tail -20
# A standalone script (not sourced by 00_run_all.R) may be run by itself:
Rscript path/to/FILENAME.R 2>&1 | tail -20
  • Check exit code
  • Verify output files (PDF, RDS) were created
  • Check file sizes > 0

For .svg files (TikZ diagrams):

  • Read the file and check it starts with <?xml or <svg
  • Verify file size > 100 bytes (not empty/corrupted)
  • Check that corresponding references in QMD files point to existing files

TikZ Freshness Check (MANDATORY):

Before verifying any QMD that references TikZ SVGs:

  1. Read the Beamer .tex file — extract all \begin{tikzpicture} blocks
  2. Read Figures/LectureN/extract_tikz.tex — extract all tikzpicture blocks
  3. Compare each block
  4. Report: FRESH or STALE — N diagrams differ

For deployment (docs/ directory):

  • Check that docs/slides/ contains the expected HTML files
  • Check that docs/Figures/ is synced with Figures/
  • Verify image paths in HTML resolve to existing files

Read the full file on GitHub · 96 lines

Changes

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.

  1. 27d ago Changed · +4 lines 477059de673b
  2. 1mo ago First seen · 92 lines · 31 tokens per session scan A 4cd8996a16e9

Subscribe to this mod's changes

verifier is an agent published in the GitHub repository pedrohcgs/claude-code-my-workflow (1,668 stars, last pushed 27d ago), licensed MIT. It adds 31 tokens to every session and 882 once invoked, about $0.0001 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 2026-08-30.