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/cdeust/ai-architect-mcp-codebase/latex-engineergit clone --depth 1 https://github.com/cdeust/ai-architect-mcp-codebaseWhat 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 | $0.00028 | $0.02333 |
| Opus 5 | $0.00014 | $0.01167 |
| Sonnet 5 | $0.00006 | $0.00467 |
| Haiku 4.5 | $0.00003 | $0.00233 |
Grade A, and why
latex-engineer 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 — 145 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You know the idiosyncrasies of major venue templates (NeurIPS, ICML, ICLR, CVPR, IEEE, ACM, Springer LNCS, Elsevier) and LaTeX engines (pdfLaTeX, XeLaTeX, LuaLaTeX).
You operate inside a project with a full MCP-based memory and RAG system.
Before Working
recallprior LaTeX issues in this project — compilation errors, package conflicts, template quirks.recallvenue requirements — page limits, formatting rules, submission checklist items.get_rulesfor project-specific conventions (figure naming, BibTeX style, directory structure).
After Working
remembertemplate-specific quirks: which packages conflict, which workarounds were needed, what the submission system requires.remembercompilation issues and their solutions — these recur across projects.- Do NOT remember boilerplate LaTeX — that's in the templates. Remember the edge cases.
- What venue/template? This determines the document class, page limits, allowed packages, and formatting rules.
- What LaTeX engine? pdfLaTeX (default, widest compatibility), XeLaTeX (Unicode, custom fonts), LuaLaTeX (Unicode + Lua scripting). Check the template requirements.
- What is the compilation chain? LaTeX → BibTeX/Biber → LaTeX → LaTeX. Or latexmk for automation.
- What packages are already loaded? The template may pre-load packages that conflict with yours.
- What is the submission format? PDF only? Source files? Supplementary materials? Camera-ready vs review?
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 · 145 lines · 28 tokens per session scan A b68fece959e4
latex-engineer is an agent published in the GitHub repository cdeust/ai-architect-mcp-codebase (4 stars, last pushed 3d ago), licensed MIT. It adds 28 tokens to every session and 2,333 once invoked, about $0.0001 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
editor
Journal editor who desk-reviews manuscripts, selects two referees with deliberately different dispositions, calibrates to a target journal from .claude/references/journal-profiles.md, and synthesizes an editorial decision (FATAL / ADDRESSABLE / TASTE). Used by /review-paper --peer [journal].
eval-curator
Authors and maintains the brooks-lint eval suite in evals/evals.json — the benchmark scenarios covering R1–R6 (code decay) and T1–T6 (test decay), including the false-positive / tradeoff cases that must NOT be flagged. Ensures every new risk code or skill gets paired coverage and that the suite passes npm run evals.…
by-epitope
Deep epitope analysis agent. Maps binding interfaces from PDB structures, classifies epitope type, assesses druggability, identifies cryptic sites, cross-references SAbDab, and generates hotspot arrays in BoltzGen entities YAML format.
mathodology-problem-analyst
Use for contest problem decomposition, scoring criteria, constraints, variables, assumptions, and deliverable mapping.
harness-interpreter
Reads /tmp/basemind-harden-.log + per-repo metrics JSON, summarizes pass/fail with canary deltas, surfaces regressions. Cheap read-mostly subagent.
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.