What is model-ledger CLAUDE.md?

A set of Claude Code instructions for the model-ledger project, covering its architecture, development commands, tests, formatting, type checks, and version-specific design notes. Model-ledger is an open-source inventory and governance framework for models.

Use it when working on model-ledger to run its test suite, linting, formatter, and type checker, and to navigate its connectors, storage backends, SDK, and agent tools.

It gives the coding agent project-specific guidance so it can understand the codebase and use the documented checks when changing it.

How block/model-ledger configures Claude Code

About the project

model-ledger is an open-source inventory and governance system that maps an organization’s deployed models, rules, pipelines, and dependencies in an immutable graph with change history. Organizations use it to track model deployments, assess dependencies, and query their inventory through AI agents.

block/model-ledger · 17 stars · on GitHub · block.github.io

Reuse

Borrowing it

Nothing to install: this file belongs to block/model-ledger. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/block/model-ledger/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/block/model-ledger

Made for: Claude Code.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/block/model-ledger/claude-md/github.svg)](https://agentmods.dev/instructions/block/model-ledger/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/block/model-ledger/claude-md"><img src="https://agentmods.dev/badge/instructions/block/model-ledger/claude-md/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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/block/model-ledger/claude-md"><img src="https://agentmods.dev/badge/instructions/block/model-ledger/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 1,331 This file is loaded in full into every session.

When invoked 1,331 The same file — it is already loaded in full.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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	$0.01331	$0.01331
Opus 5.5	$0.00532	$0.00532
Sonnet 5.5	$0.00266	$0.00266
Haiku 4.5	$0.00133	$0.00133

Measured 2mo ago against content hash 70a7feb84d3d, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

model-ledger CLAUDE.md 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.

CLAUDE.md · 104 lines

How it starts

The opening of the file, as written. The whole thing — 104 lines — stays where its author put it; the contents beside it link to each section on GitHub.

model-ledger

Open-source model inventory and governance framework. Apache-2.0.

Build & Test

.venv/bin/python -m pytest tests/ -v
.venv/bin/python -m pytest tests/test_file.py::test_name -v  # single test
.venv/bin/python -m ruff check src/ tests/
.venv/bin/python -m ruff format src/ tests/
.venv/bin/python -m mypy src/

Architecture

v0.7.2+ (current — agent protocol + connectors + change tracking)

src/model_ledger/connectors/sql.py — sql_connector() factory
src/model_ledger/connectors/rest.py — rest_connector() factory
src/model_ledger/connectors/github.py — github_connector() factory
src/model_ledger/connectors/prefect.py — prefect_connector() factory (Prefect Cloud API)
src/model_ledger/backends/sqlite_ledger.py — SQLiteLedgerBackend (persistent, zero-dep)
src/model_ledger/backends/snowflake.py — SnowflakeLedgerBackend (production)
src/model_ledger/backends/http.py — HttpLedgerBackend (MCP → REST API pass-through)
src/model_ledger/backends/json_files.py — JsonFileLedgerBackend (git-friendly)
src/model_ledger/sdk/ledger.py — Ledger SDK with last_seen, change_detected/change_occurred
src/model_ledger/tools/ — 8 agent tool functions (record, query, investigate, trace, changelog, discover, tag, list_tags)
src/model_ledger/mcp/server.py — MCP server (FastMCP, 8 tools + 3 resources)
src/model_ledger/rest/app.py — REST API (FastAPI, create_app() factory)

v0.4.x (DataNode graph)

src/model_ledger/core/ledger_models.py — ModelRef, Snapshot, Tag
src/model_ledger/sdk/ledger.py — Ledger SDK (register, record, tag, add, connect, trace, upstream, downstream)
src/model_ledger/graph/models.py — DataNode, DataPort (with schema discriminators)
src/model_ledger/graph/protocol.py — SourceConnector protocol
src/model_ledger/backends/ledger_protocol.py — LedgerBackend protocol
src/model_ledger/backends/ledger_memory.py — InMemory backend
src/model_ledger/adapters/sql.py — SQL parsing (extract_tables, write_tables, model_name_filters)
src/model_ledger/adapters/tables.py — Table-based pipeline discovery
src/model_ledger/adapters/cron.py — Cron expression translation

Read the full file on GitHub · 104 lines

Changes

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 · 104 lines · 1,331 tokens per session scan A 70a7feb84d3d

Subscribe to this mod's changes

model-ledger CLAUDE.md is an instructions file published in the GitHub repository block/model-ledger (17 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 1,331 tokens to every session, about $0.0053 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 2026-08-30.

MLOps ai-governance compliance mcp model-governance model-inventory

model-ledger CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
model-ledger CLAUDE.mdblock/model-ledger	Instructions file	17	1mo ago	Apache-2.0	A	1,331	Claude Code
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	yesterday	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	274k	2d ago	MIT	A	4,313	Codex, OpenCode

model-ledger: Instructions file for Claude Code