A pattern for maintaining two separate GitHub identities on one machine (e.g. personal and work), with automatic switching based on which directory tree you are working in. No manual switching required after initial setup.
| The Adafruit 1.2" 4 digit 7-segment LED display with backpack (https://www.adafruit.com/product/1270) is connexted via the i2c bus interface. Adafruit has a quite good soldering & setup tutorial at https://learn.adafruit.com/adafruit-led-backpack/1-2-inch-7-segment-backpack, however they do a terrible job of describing in easy detail the necessary i2c writes to control the display from a language other than their provided libraries for Arduino or Python. So I've assembled a pretty comprehensive address and data to write in order to fully control the display. Please see attached images for some details. | |
| digit segment numbered.jpg - shows an image of the display, along with numbers/letters along with a bitmask to use to control each segment. | |
| seven segment bitmask chart.jpg - shows which bits control which segments for the digits | |
| dots segment bitmask chart.jpg - shows which bits control which segments for the dots | |
| Examples of writing are using the Linux i2c-tools. For example this write: | |
| i2cset 1 0x |
Audience: PAI users considering restructuring how steering rules and behavioral context reach the model.
Scope: How Claude Code loads context, where PAI's current architecture falls short, and how the @include directive in CLAUDE.md resolves the authority gap.
Out of scope: Defending the trust-chain files against prompt-injected writes. That threat is real and independent — covered in a separate document (pai-trust-chain-integrity-guard.md, in development). This guide is about authority routing (the model follows the rules it already has), not integrity (the rules don't get rewritten under the model).
Evidence base: Source-code-level analysis of the Claude Code TypeScript implementation. File/line citations (e.g., claudemd.ts:89) refer to Claude Code internals and are included so claims can be independently verified.
A practical guide to what dynamic workflows are, how a Claude Code agent uses them, and where they actually help. Written for teammates who already use Claude Code but haven't dug into this feature yet.
Status: research preview, Claude Code v2.1.154+. On Pro you turn it on in
/config("Dynamic workflows"). Available on all paid plans plus Anthropic API, Bedrock, Vertex AI, and Foundry.
How to read the source labels. This guide mixes three kinds of claims, and they're tagged inline so you can weigh them:
- [DOCS] - stated in Anthropic's official documentation. Take as authoritative.
- [OBSERVED] - discovered by having a Claude Code agent inspect its own tooling (the
Workflowtool's built-in description and the shippeddeep-researchworkflow). The official docs deliberately don't publish the scripting API, so these details came from the agent examining what it actually has access to. High confidence, but not officially documented - could