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 skills add docxology/template --skill formal_contractsgit clone --depth 1 https://github.com/docxology/templateWrote 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/docxology/template/formal_contracts)<a href="https://agentmods.dev/skills/docxology/template/formal_contracts"><img src="https://agentmods.dev/badge/skills/docxology/template/formal_contracts/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.
<a href="https://agentmods.dev/skills/docxology/template/formal_contracts"><img src="https://agentmods.dev/badge/skills/docxology/template/formal_contracts.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00044 | $0.00265 |
| Opus 5.5 | $0.00018 | $0.00106 |
| Sonnet 5.5 | $0.00009 | $0.00053 |
| Haiku 4.5 | $0.00004 | $0.00026 |
Grade A, and why
infrastructure-formal-contracts 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 1mo 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.
What it actually says
Formal Contracts
Commands
uv run pytest tests/infra_tests/formal_contracts -q
uv run python -c "from infrastructure.formal_contracts import read_blocks, compose, check_manuscript; ms = compose(list(read_blocks(open('manuscript.md').read()))); print(check_manuscript(ms).diagnostics)"
When to use
- Checking that manuscript claims carry evidence of a declared tier.
- Verifying formal statements resolve to registered definitions/theorems.
- Validating a manuscript block DAG: unique ids, acyclicity, no orphans.
API
compose, check_manuscript, compose_manuscripts, read_blocks,
Manuscript, Report, Diagnostic, FormalCode, block types
(Claim, Evidence, FormalStatement, Derivation, Figure, Table,
Dataset, Section).
Honesty
Preorder-enriched graph + monoidal composition; NOT a topos. See module docstrings.
What ships with it
7 files 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.
- 1mo ago First seen · 32 lines · 44 tokens per session scan A 19ff648bb366
infrastructure-formal-contracts is a skill published in the GitHub repository docxology/template (20 stars, last pushed yesterday), licensed Apache-2.0. It adds 44 tokens to every session and 265 once invoked, about $0.0002 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 2026-09-23.
Other skills, from other repositories
overleaf-latex-workflow
Working practices for LaTeX projects on Overleaf - finding the root file, compiling, reading the log, fixing errors, and keeping a shared paper buildable. Use when asked to write or revise a paper, fix a compile error, add figures, tables, sections or citations, or check that an Overleaf project still builds.
paper-figures
Extract figures from downloaded papers and include them in survey/review reports. Use when the report covers other groups' work and benefits from their architecture diagrams, experimental plots, or system schematics. Your brain prompt supplies the absolute path to the extract-figures script as {{EXTRACTFIGURES}} — use…
taxonomy-vto
A reference guide for diagnosing visual problems in LaTeX research papers. It defines categories such as wasted page space, misplaced figures, inconsistent formatting, overflow, alignment, and template-migration issues.
consistency-polisher
A LaTeX layout helper that makes tables, figures, and captions follow consistent formatting throughout a research paper. LaTeX is a system often used to typeset academic documents.
float-optimizer
A document-layout helper for LaTeX, the system commonly used to typeset research papers. It adjusts how figures and tables are placed near the text that refers to them.
space-util-fixer
A LaTeX layout helper for improving how content fills pages and columns. It addresses issues such as isolated lines, large blank areas, incorrect page counts, and uneven columns in two-column papers.