agentmods.dev

infermap CLAUDE.md

infermap CLAUDE.md is an instructions file for coding agents from benseverndev-oss/infermap. It costs 721 tokens per session, scanned A, original, MIT.

Project instructions for infermap, a Python project, including its environment, architecture, key files, tests, linting, and release details.

In plain words
What is it for?
Running infermap's tests and lint checks, understanding its scoring pipeline, and following its development and publishing workflow.
Why use it?
They tell an AI coding agent how this repository is structured and how changes must be checked before committing.

Instructions file

not rated 0 4mo ago A scan 721 tokens original MIT archived
View the source file benseverndev-oss/infermap
Install

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.

agentmods
npx agentmods add instructions/benseverndev-oss/infermap/claude-md
Clone the repo
git clone --depth 1 https://github.com/benseverndev-oss/infermap

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.

agentmods badge for infermap CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/benseverndev-oss/infermap/claude-md.svg)](https://agentmods.dev/instructions/benseverndev-oss/infermap/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/benseverndev-oss/infermap/claude-md"><img src="https://agentmods.dev/badge/instructions/benseverndev-oss/infermap/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 721 This file is loaded in full into every session.
When invoked 721 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
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.

ModelPer sessionOnce invoked
Fable 5 $0.00721 $0.00721
Opus 5 $0.00360 $0.00360
Sonnet 5 $0.00144 $0.00144
Haiku 4.5 $0.00072 $0.00072

Measured 4d ago against content hash 7196bf339133, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

infermap 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 4d 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 · 44 lines

How it starts

The opening of the file, as written. The whole thing — 44 lines — stays where its author put it; the contents beside it link to each section on GitHub.

infermap

Environment

  • Windows 11, bash shell (Git Bash) — use Unix paths in scripts
  • Python 3.12 at C:\Users\bsevern\AppData\Local\Programs\Python\Python312\python.exe
  • Project: D:\show_case\infermap
  • Two GitHub accounts: benzsevern (owner) and benzsevern-mjh (work)
  • Always gh auth switch --user benzsevern before push, switch back after
  • PyPI: infermap v0.1.0 published (trusted publishing configured)

Testing

  • pytest --tb=short from project root — 210 tests, ~2s
  • Optional deps (psycopg2, duckdb, pandas) must use pytest.importorskip() — CI only installs .[dev]
  • ruff check infermap/ tests/ must pass — CI lint job fails on any error
  • Run ruff check --fix before committing to auto-fix most issues
  • import polars hangs under heavy CPU load (parallel subagents) — kill stale python processes first

Architecture

  • Weighted scorer pipeline: ExactScorer → AliasScorer → PatternTypeScorer → ProfileScorer → FuzzyNameScorer
  • Score combination: weighted average, None = abstain, 0.0 = real negative, min 2 contributors
  • Optimal 1:1 assignment via scipy.optimize.linear_sum_assignment (Hungarian algorithm)
  • Providers: FileProvider, InMemoryProvider, SchemaFileProvider, DBProvider (SQLite/Postgres/DuckDB)
  • Config: infermap.yaml for scorer weights + alias extensions, schema definition files for target metadata
  • CLI: infermap map, apply, inspect, validate via Typer
  • Public API: infermap.map(), from_config(), extract_schema(), @infermap.scorer decorator

Key Files

  • infermap/engine.py — MapEngine orchestrator (scorer pipeline + assignment)
  • infermap/scorers/alias.py — ALIASES dict + _ALIAS_LOOKUP (extended by config)
  • infermap/scorers/pattern_type.py — SEMANTIC_TYPES regex registry + classify_field()
  • infermap/providers/db.py — SQLite/Postgres/DuckDB extraction (MySQL stubbed)
  • infermap/types.py — FieldInfo, SchemaInfo, ScorerResult, FieldMapping, MapResult
  • tests/conftest.py — FIXTURES_DIR (not FIXTURES), make_field(), make_schema()

Read the full file on GitHub · 44 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.

  1. 4d ago First seen · 44 lines · 721 tokens per session scan A 7196bf339133

Subscribe to this mod's changes

infermap CLAUDE.md is an instructions file published in the GitHub repository benseverndev-oss/infermap (0 stars, last pushed 4mo ago), licensed MIT. It adds 721 tokens to every session, about $0.0036 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.

clicolumn-mappingdata-engineeringdata-integrationdata-pipelinedata-quality
Related

Other instructions, from other repositories

goldenmatch AGENTS.md

AGENTS.md instructions for benseverndev-oss/goldenmatch, covering golden suite monorepo — agent guide, what this is, layout, build & test and landmines to know before you touch anything.

benseverndev-oss/goldenmatch · 1,505 tokens

goldenmatch CLAUDE.md

Claude Code instructions for benseverndev-oss/goldenmatch, covering golden suite monorepo, typescript: pnpm + turborepo (post-2026-05-02 fold), ci (.github/workflows/ci.yml), ci path filters (post-2026-05-06, pr #89) and merge queue: main serializes merges fifo (since 2026-06-15).

benseverndev-oss/goldenmatch · 5,169 tokens

sqrl CLAUDE.md

Claude Code instructions for DataSQRL/sqrl, covering claude.md, project overview, external dependencies, essential commands and build commands.

DataSQRL/sqrl · 3,429 tokens

dbt-doctor AGENTS.md

Instructions for northgraindata/dbt-doctor, covering dbt-doctor, stack, commands and conventions.

northgraindata/dbt-doctor · 254 tokens

datapulse-my AGENTS.md

AGENTS.md instructions for r3dz4r/datapulse-my, covering agents.md — r3dz4r/datapulse-my, what this repo is, hard rules, repo map and script taxonomy — which scripts regenerate vs hand-author.

r3dz4r/datapulse-my · 2,618 tokens

operator-etl AGENTS.md

AGENTS.md instructions for khaosans/operator-etl, covering agent instructions — operator etl, fast verify (do this first), load order (extended work), non-negotiables and multi-session work.

khaosans/operator-etl · 836 tokens