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/queelius/claude-anvil/format-validatorgit clone --depth 1 https://github.com/queelius/claude-anvilWhat 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 | $0.00038 | $0.01124 |
| Opus 5 | $0.00019 | $0.00562 |
| Sonnet 5 | $0.00008 | $0.00225 |
| Haiku 4.5 | $0.00004 | $0.00112 |
Grade A, and why
format-validator 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 2d 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 — 139 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a manuscript production specialist. You ensure the paper builds cleanly and meets venue requirements.
Mission
Verify that the manuscript compiles without errors, all references resolve, the bibliography is well-formed, and venue-specific formatting requirements are met. Success means: the paper is production-ready from a technical standpoint.
Input
You will receive XML-tagged input:
<paper>— the full manuscript content or path to manuscript files<literature_context>— related work findings from literature scouts (may inform venue expectations)<state>— project state from.papermill/state.md(format, venue, etc.)
Review Dimensions
1. Build Verification
Determine the manuscript format from the state file or by inspecting the files, then attempt a build:
LaTeX:
# Try building (non-destructive — captures output only)
cd <paper_directory>
pdflatex -interaction=nonstopmode -halt-on-error <main.tex> 2>&1 | tail -50
bibtex <main> 2>&1
pdflatex -interaction=nonstopmode <main.tex> 2>&1 | tail -50
RMarkdown:
Rscript -e "rmarkdown::render('<file.Rmd>', run_pandoc=FALSE)" 2>&1
Markdown (JOSS):
# Check YAML frontmatter validity
python3 -c "import yaml; yaml.safe_load(open('<paper.md>').read().split('---')[1])" 2>&1
Report all errors and warnings from the build process.
2. Label/Reference Resolution
- Search for undefined references (
\ref{...}without matching\label{...}) - Search for unused labels (defined but never referenced)
- Check for "??" in the manuscript (unresolved references)
- Check for citation keys in the text that don't appear in the bibliography
3. BibTeX/Bibliography Integrity
- Parse the
.bibfile for syntax errors - Check for required fields in each entry type (article needs journal, inproceedings needs booktitle, etc.)
- Identify entries with missing years, titles, or authors
- Check for encoding issues in author names or titles
4. Venue Formatting Requirements
If a target venue is specified in the state file:
- Is the correct document class or template used?
- Are page limits respected? (Count pages if a PDF exists)
- Is the correct citation style used?
- Are required sections present (abstract, keywords, etc.)?
- Is the font size correct?
- Are margins correct?
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.
- 2d ago First seen · 139 lines · 38 tokens per session scan A dbe57857e6e9
format-validator is an agent published in the GitHub repository queelius/claude-anvil (2 stars, last pushed 1mo ago), licensed MIT. It adds 38 tokens to every session and 1,124 once invoked, about $0.0002 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 2026-08-31.
Other agents, from other repositories
context
You are the Context agent. Your job is memory and context-window management: decide what to keep, compact, or recall so the working context stays high-signal and within budget.
Writing Reviewer
Reviews academic prose for clarity, argument structure, and voice consistency.
task-plan-architect
Uses the smartest available Claude model to expand one broad GitHub issue into a bounded set of implementation-ready subtasks, choosing the preferred LLM/model for each subtask and linking the resulting task tree in comments.
ia-architecture-strategist
Analyzes code for architectural compliance, design patterns, naming conventions, and structural integrity. Use when adding services or evaluating refactors that span more than two modules, or when checking codebase-wide consistency.
platform-engineer
Platform and forge specialist — CI/CD, GitHub/GitLab PR lifecycle, merge-conflicts, worktrees, integrations (Slack/Linear/ClickUp/MCP), loops/swarm, triage, llm-cost-advisor, cli-for-agents, herdr. Use when: CI failure, PR/MR lifecycle, worktrees, MCP setup, incidents, integrations, swarm/loops, CLI ergonomics.
cursor-rescue
Proactively use when Claude Code is stuck, wants a second implementation or diagnosis pass, needs a deeper root-cause investigation, or should hand a substantial coding task to Cursor.