Skip to content

Clarify pattern boundaries - #42

Open
devill wants to merge 4 commits into
mainfrom
clarify-pattern-boundaries
Open

Clarify pattern boundaries#42
devill wants to merge 4 commits into
mainfrom
clarify-pattern-boundaries

Conversation

@devill

@devill devill commented Jul 29, 2026

Copy link
Copy Markdown
Collaborator

Hooks, Contextual Prompts, Habit Hooks and User Reminders read as near-duplicates. One boundary line in each says how they differ.

Also here: a link to the Habit Hooks open-source implementation, and Workflows added to Orchestrator's tool list.

devill and others added 3 commits July 29, 2026 16:48
… and User Reminders

Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
@devill
devill marked this pull request as ready for review July 29, 2026 14:49
@devill
devill marked this pull request as draft July 29, 2026 14:56
@devill
devill marked this pull request as ready for review July 29, 2026 15:03
@devill
devill requested a review from lexler July 29, 2026 19:46

This is what we've always done for humans: good error messages guide you to the solution. It works equally well for AI agents.

This needs no agent integration — the guidance lives in the output of scripts you own. When the trigger comes from a tool you can't modify (a linter, a test runner), see Habit Hooks, which delivers the same just-in-time guidance through agent lifecycle Hooks.

Copy link
Copy Markdown

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

"the guidance comes from the output"?
The sentence starting "When the trigger comes..." doesn't need the comma after the closing parens. Is it saying "when the trigger comes from a tool you can't modify (...) consider Habit Hooks [pattern]..."

Comment thread documents/patterns/habit-hooks.md Outdated

This approach reduces context bloat while improving compliance by providing precise, relevant guidance exactly when violations occur, rather than front-loading massive instructions that AI forgets or misapplies.

Habit Hooks is Contextual Prompts applied to tools you can't modify: a deterministic detector provides the trigger, Hooks provide the delivery, and the prompt provides actionable coaching.

Copy link
Copy Markdown

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

"Habit Hooks are Contextual Prompts..."

Comment thread documents/patterns/hooks.md Outdated
- Provide just-in-time guidance when specific conditions are detected
- Inject reminders before the agent forgets your preferences

Hooks are the delivery mechanism — what you deliver through them is a separate choice. User Reminders (see Reminders) re-inject your most important rules; Habit Hooks pairs hooks with quality detectors to coach specific fixes. When the guidance belongs in a script you own, you may not need hooks at all — see Contextual Prompts.

Copy link
Copy Markdown

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

"Habit Hooks pair..." (shouldn't be plural)
"... coach specific fixes..." feels as if it's missing a "that result in ..." conclusion to the sentence.

@andrewharmellaw andrewharmellaw left a comment

Copy link
Copy Markdown

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Made a few suggestions - feel free to ignore any you disagree with.

Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_012EjEPvjHK2SVy9jjzwMSRm
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants