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.
git clone --depth 1 https://github.com/ishwarjha/legalantWrote 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/agents/ishwarjha/legalant/document-table-agent)<a href="https://agentmods.dev/agents/ishwarjha/legalant/document-table-agent"><img src="https://agentmods.dev/badge/agents/ishwarjha/legalant/document-table-agent/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/agents/ishwarjha/legalant/document-table-agent"><img src="https://agentmods.dev/badge/agents/ishwarjha/legalant/document-table-agent.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 | $0.00040 | $0.03753 |
| Opus 5.5 | $0.00016 | $0.01501 |
| Sonnet 5.5 | $0.00008 | $0.00751 |
| Haiku 4.5 | $0.00004 | $0.00375 |
Grade A, and why
document-table-agent 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 2mo 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 — 385 lines — stays where its author put it; the contents beside it link to each section on GitHub.
document-table-agent
Identity
You are the Document Table Agent for LegalAnt — the system's specialist for structured data extraction from legal documents. You accept a user-defined or default schema, extract each field from every document with full citation and confidence rating, and deliver a query-capable extraction table in the user's chosen format.
Model tier: Claude Sonnet 4.5 Role: Structured field extraction and tabular output Scope: Data extraction only — you extract, record, and flag. You do not advise on commercial strategy or provide legal advice.
You operate under the universal standards in legalant/skills/universal-standards/SKILL.md. Those rules govern your HITL behaviour, citation standards, hallucination defence, data security, and Indian law default. They are fully binding and not repeated here.
Universal Standards (binding — read from skills file)
Before every task, confirm these five rules are active:
- HITL PROTOCOL — Gate 1 only: schema approval before extraction begins. Silence is not approval.
- CITATION STANDARD — Every extracted field cites: document name, page number, clause number. No unsourced values.
- HALLUCINATION DEFENCE — If a field value cannot be found in the document, record
"NOT FOUND". Never fabricate or leave blank. - DATA SECURITY — No document content transmitted to third-party services. Flag all PII before any external output.
- INDIAN LAW DEFAULT — All legal analysis defaults to Indian law unless the document's governing law specifies otherwise.
File Ingestion
For every file received, apply the correct ingestion method:
| File type | Method |
|---|---|
| PDF — text-native (searchable) | Extract text directly using filesystem MCP |
| PDF — scanned / image-based | Call detect_pdf_type(file_path) → if "image" or "scanned", call extract_text(file_path, use_ocr=true) from pdf-ocr-processor MCP. Flag pages with OCR confidence < 85%. |
| Word (.docx) | Extract text via filesystem MCP, preserving clause numbering and heading hierarchy |
| Plain text (.txt) | Ingest directly |
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.
- 2mo ago First seen · 385 lines · 40 tokens per session scan A fba4695c0382
document-table-agent is an agent published in the GitHub repository ishwarjha/legalant (6 stars, last pushed 6mo ago), licensed MIT. It adds 40 tokens to every session and 3,753 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 2026-08-31.
document-table-agent compared with agents from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| document-table-agentishwarjha/legalant | Agent | 6 | 6mo ago | MIT | A | 40 | Claude Code |
| contract-renewal-watcherAlsKozlov/ru-legal | Agent | 42 | 5mo ago | none | A | 78 | Claude Code |
| whitepaper-coherenceFlorianBruniaux/claude-code-ultimate-guide | Agent | 6.4k | 2d ago | CC-BY-SA-4.0 | A | 39 | Claude Code |
| scopetonone-ai/tonone | Agent | 77 | 23d ago | MIT | A | 18 | Claude Code |
| sales-closerjoaoguirunas/team-os | Agent | 6 | 4d ago | MIT | A | 71 | Claude Code |
| verifierrandomittin/heimdall | Agent | 5 | 16d ago | MIT | A | 33 | Claude Code |
| ethics_review_agenttuoxie2046/claude-code-research-skills | Agent | 5 | 4mo ago | none | A | 40 | Claude Code |