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 commands/lowtidebuild/contract-review/ingestgit clone --depth 1 https://github.com/lowtidebuild/contract-reviewWrote 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/commands/lowtidebuild/contract-review/ingest)<a href="https://agentmods.dev/commands/lowtidebuild/contract-review/ingest"><img src="https://agentmods.dev/badge/commands/lowtidebuild/contract-review/ingest.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 | $0.00000 | $0.00727 |
| Opus 5 | $0.00000 | $0.00364 |
| Sonnet 5 | $0.00000 | $0.00145 |
| Haiku 4.5 | $0.00000 | $0.00073 |
Grade A, and why
ingest 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 — 75 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Library Ingestion Pipeline
You are ingesting documents into the contract review library. The user has placed source files in contract-review/library/inbox/raw/.
$ARGUMENTS
Process
Step 1: Scan inbox
Scan contract-review/library/inbox/raw/ for files. Supported formats: DOCX, PDF, MD, TXT, HTML. If no files are found, inform the user and stop.
Check contract-review/library/inbox/sidecars/ for any matching sidecar metadata files (YAML).
Step 2: Fingerprint & duplicate check
For each file:
- Generate a SHA-256 content hash
- Assign a provisional
doc_id(lowercase, hyphenated) - Compare the hash against existing entries in
contract-review/library/indexes/documents.json - If exact duplicate found, skip and log
Step 3: Normalize
Convert each file to clean Markdown (clean.md) and plain text (plain.txt):
- DOCX: extract text preserving heading hierarchy, numbering, and table structure
- PDF: extract text (requires pdftotext/pymupdf/pypdf)
- MD/TXT/HTML: normalize formatting
If normalization fails, move the file to contract-review/library/quarantine/ with an error log.
Step 4: Classify
Using the normalized text and policy files (contract-review/library/policies/contract-families.yaml, clause-taxonomy.yaml):
- Determine:
doc_class(template/precedent/playbook/comment_bank),contract_family,subtype,paper_role,jurisdiction,governing_law,language - Apply sidecar values first if available, infer only missing fields
- Assign classification confidence (high/medium/low)
If confidence is low, route to contract-review/library/staging/ for human review.
Step 5: Structural parse
Identify heading hierarchy, section numbering, defined terms, cross-references, and exhibits/annexes. Output as structured JSON.
Step 6: Clause segmentation
Segment the document into clause-level units. Assign each clause a clause_type from clause-taxonomy.yaml. Mark unmapped clauses (do not guess). If unmapped ratio exceeds 30%, flag for human 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.
- 5d ago First seen · 75 lines · 0 tokens per session scan A c02e73add9c9
ingest is a command published in the GitHub repository lowtidebuild/contract-review (40 stars, last pushed 1mo ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 727 tokens. 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 commands, from other repositories
/a11y-report
Reporte de conformidad de accesibilidad para stakeholders y legal. Tres formatos: ejecutivo (resumen + score), técnico (detalles completos + código), legal (declaración VPAT/Section 508). Tracking de tendencias. Exportable.
sign
Sign a PDF — stamp a signature block (name + date, or a PNG signature) on a signed copy.
pipeline-minutar-pdf
Pipeline completo de sentença judicial a partir de PDF (conversão, linha-tempo, relatório, análise, fundamentação, merge).
baixar-inteligente
Pipeline inteligente - baixa processo especifico com selecao por LLM.
baixar-pje
Baixa processos do PJE (apenas PDF).
family-tree
戸籍謄本PDFから家族関係を分析し相続関係説明図（自己完結HTML）を生成.