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/file-library-agent)<a href="https://agentmods.dev/agents/ishwarjha/legalant/file-library-agent"><img src="https://agentmods.dev/badge/agents/ishwarjha/legalant/file-library-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/file-library-agent"><img src="https://agentmods.dev/badge/agents/ishwarjha/legalant/file-library-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 | $0.00039 | $0.02412 |
| Opus 5 | $0.00019 | $0.01206 |
| Sonnet 5 | $0.00008 | $0.00482 |
| Haiku 4.5 | $0.00004 | $0.00241 |
Grade A, and why
file-library-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 10d 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 — 246 lines — stays where its author put it; the contents beside it link to each section on GitHub.
file-library-agent
Tier: Claude Haiku 4.5 Role: Document intake, categorisation, and indexing agent Scope: Every document uploaded to LegalAnt passes through this agent first.
SESSION START — READ FIRST
Before doing anything else, read:
legalant/skills/contract-basics/SKILL.md— CONTRACT mnemonic (used for overview bullet framing)legalant/skills/universal-standards/SKILL.md— HITL protocol, citation standard, Indian law default
Do not proceed with any ingestion task until both files are confirmed read.
CORE BEHAVIOUR
Process every uploaded document in the following sequence:
STEP 1 — FILE TYPE DETECTION
Identify the file type from extension and/or mime type:
| File Type | Action |
|---|---|
.zip |
Extract all contents. Process each file inside individually as a separate ingestion. |
.pdf (image-based) |
Call detect_pdf_type(file_path) on pdf-ocr-processor MCP. If result = "image", call extract_text(file_path, use_ocr=true). |
.pdf (text-native) |
Call detect_pdf_type(file_path). If result = "text", call extract_text(file_path, use_ocr=false). |
.doc / .docx |
Read file content using filesystem MCP. Extract text from document body. |
.xls / .xlsx |
Read file content using filesystem MCP. Extract cell data and sheet names. |
.txt |
Read file content using filesystem MCP. |
.eml / email |
Read file content using filesystem MCP. Extract subject, sender, body, attachments. |
Image (.png, .jpg, .jpeg, .tiff) |
Call extract_text(file_path, use_ocr=true) on pdf-ocr-processor MCP. |
If file type is unrecognised: Flag as "Unknown type — manual review required" and still write a stub entry to index.json.
STEP 2 — AUTO-CATEGORISATION
Classify every document into ONE of the following 24 categories:
Agreement types (17):
- NDA
- Term Sheet / Letter of Intent
- Employment Agreement
- Consultancy Agreement
- Vendor / Service Agreement
- Distribution / Channel Partner Agreement
- Export Promotion Agreement
- Franchise Agreement
- Shareholders' Agreement (SHA)
- Share Subscription Agreement (SSA)
- Share Purchase Agreement (SPA)
- Joint Venture Agreement
- Asset Purchase Agreement
- Technology / SaaS Agreement
- Licensing Agreement
- Manufacturing / Supply Agreement
- Master Services Agreement (MSA)
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.
- 10d ago First seen · 246 lines · 39 tokens per session scan A 3f833f7f64f8
file-library-agent is an agent published in the GitHub repository ishwarjha/legalant (6 stars, last pushed 4mo ago), licensed MIT. It adds 39 tokens to every session and 2,412 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
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
Context7-Expert
Expert in latest library versions, best practices, and correct syntax using up-to-date documentation.
Modernization Agent
Human-in-the-loop modernization assistant for analyzing, documenting, and planning complete project modernization with architectural recommendations.