What is pipelinewise AGENTS.md?

A guide for contributors to PipelineWise, a Python framework that moves data between systems using Singer data pipelines.

Use it when changing PipelineWise code, Singer connectors, documentation, migrations, command-line behavior, or unit and end-to-end tests.

It explains the project’s architecture, scoped instructions, data-transfer modes, and which tests and documents apply to each area.

How transferwise/pipelinewise configures Codex and OpenCode

Reuse

Borrowing it

Nothing to install: this file belongs to transferwise/pipelinewise. 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/transferwise/pipelinewise/master/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/transferwise/pipelinewise

Made for: Codex, OpenCode.

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/transferwise/pipelinewise/agents-md/github.svg)](https://agentmods.dev/instructions/transferwise/pipelinewise/agents-md)

Your own site

<a href="https://agentmods.dev/instructions/transferwise/pipelinewise/agents-md"><img src="https://agentmods.dev/badge/instructions/transferwise/pipelinewise/agents-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/transferwise/pipelinewise/agents-md"><img src="https://agentmods.dev/badge/instructions/transferwise/pipelinewise/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 1,707 This file is loaded in full into every session.

When invoked 1,707 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	$0.01707	$0.01707
Opus 5.5	$0.00683	$0.00683
Sonnet 5.5	$0.00341	$0.00341
Haiku 4.5	$0.00171	$0.00171

Measured yesterday against content hash ec68498aec30, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

pipelinewise AGENTS.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 yesterday.

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.

AGENTS.md · 152 lines

How it starts

The opening of the file, as written. The whole thing — 152 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AI Coding Agent Instructions

Scope

PipelineWise is a Python 3.12 Singer ELT framework. Write for senior engineers with operational precision, edge cases, and rationale. Root rules apply repo-wide; scoped rules add to them, and explicit user instructions win. Read the guides relevant to the change:

pipelinewise/AGENTS.md: orchestration, FastSync, backend migrations, data-diff.
singer-connectors/AGENTS.md: vendored taps and targets.
tests/AGENTS.md: units and suite boundaries.
tests/end_to_end/AGENTS.md: databases, connector routes, E2E, dev-project/.
docs/AGENTS.md: documentation.

Every CLAUDE.md symlinks to its adjacent AGENTS.md; edit the latter and preserve the link.

Architecture

Singer JSON flows as tap | [transform-field] | [mbuffer] | target; YAML generates config, state, and catalog JSON.
pipelinewise/cli/__init__.py defines argparse and dispatches to PipelineWise. Canonical fast_sync and import_config retain deprecated aliases sync_tables and import.
FastSync optimizes native full/filtered bulk transfer; it is not a replication method. Singer handles INCREMENTAL/LOG_BASED and non-FastSync FULL_TABLE streams.
Treat UTC as the canonical convention for replication and data-diff timestamps and windows. Interpret source timezones correctly before normalizing; never rely on the host or container timezone for correctness.

Environment

Default to the dev-project Docker stack, whose Linux runtime best matches production. Use the host only to manage Docker or when the container cannot run a check; report that fallback and compatibility gap.
The repo mounts at /opt/pipelinewise in pipelinewise. PIPELINEWISE_HOME environments are on PATH under dev-project/.virtualenvs/.
make pipelinewise installs the editable root and test extras. Connector runtimes use .virtualenvs/<name>/; connector Makefiles may use venv/. Never mix host/container, root, runtime-connector, or connector-test interpreters; never use repository .venv/.

Read the full file on GitHub · 152 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.

yesterday Changed · +3 lines · +45 tokens per session ec68498aec30
4d ago Changed · +1 lines · +8 tokens per session 4591ff9f9ca1
1mo ago Changed · +4 tokens per session b14b2abd9e19
1mo ago Changed · +2 lines · +35 tokens per session 9af67058de40
1mo ago Changed · +2 lines · +38 tokens per session 2e829510080e
1mo ago Changed · +4 tokens per session a711ca5cd749
1mo ago Changed · +10 lines · +141 tokens per session 8f91b0f2b890
1mo ago Changed · +6 lines · +46 tokens per session aaa22b831019
1mo ago Changed · +1 lines · +20 tokens per session e63953597a81
1mo ago First seen · 127 lines · 1,366 tokens per session scan A 03c7b3aa2c50

Subscribe to this mod's changes

pipelinewise AGENTS.md is an instructions file published in the GitHub repository transferwise/pipelinewise (663 stars, last pushed yesterday), licensed Apache-2.0. It adds 1,707 tokens to every session, about $0.0068 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.

pipelinewise AGENTS.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
pipelinewise AGENTS.mdtransferwise/pipelinewise	Instructions file	663	yesterday	Apache-2.0	A	1,707	Codex, OpenCode
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

pipelinewise: Instructions file for Codex