feat(coding-agent/agents): enriched designer, reviewer, and task agent prompts#2664
Merged
Merged
Conversation
…t prompts - Added a token-first four-phase design-system workflow (analyze, build-if-missing, compose-with-tokens, verify) to the designer agent so visual work references design tokens instead of hardcoded magic numbers. - Added an evidence standard to the reviewer agent: a finding is not real until you can name the exact input that triggers it, and passing tests are not proof of correctness. - Added an evidence-bound completion requirement to the task agent: name the exact check run and its observable result before returning.
Contributor
There was a problem hiding this comment.
Pull request overview
Note
Copilot was unable to run its full agentic suite in this review.
Updates the bundled coding-agent prompts to require stronger evidence standards (verification, triggerable findings) and to enforce design-system-driven UI implementation.
Changes:
- Added an evidence-bound “done” requirement to the
taskagent prompt (must cite an explicit check + result). - Tightened the
revieweragent’s correctness standard to require a concrete triggering input for each finding. - Added a four-phase, token-first design-system workflow to the
designeragent prompt, and documented the changes in the changelog.
Reviewed changes
Copilot reviewed 4 out of 4 changed files in this pull request and generated 1 comment.
| File | Description |
|---|---|
| packages/coding-agent/src/prompts/agents/task.md | Adds a verification/acceptance-criteria evidence requirement before returning. |
| packages/coding-agent/src/prompts/agents/reviewer.md | Raises the evidence bar for findings (must name triggering input, tests not sufficient). |
| packages/coding-agent/src/prompts/agents/designer.md | Introduces a token-first design-system workflow to enforce consistency. |
| packages/coding-agent/CHANGELOG.md | Documents the prompt enrichments under Unreleased. |
💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.
| - You NEVER create documentation files (*.md) unless explicitly requested. | ||
| - You MUST follow the assignment and the instructions given to you. They were given for a reason. | ||
| - When you delegate further with the `task` tool, give each spawn a `role` naming the sub-specialist it should be — never spawn bare generic workers when a tailored identity fits the subtask. | ||
| - Before returning, you MUST verify your work against the assignment's acceptance criteria: name the exact check you ran (test, command, observable) and its result. "Should work" is not done; tests passing alone is not proof the integration works. |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary
Enriches three bundled agent prompts:
designergains a token-first four-phase design-system workflow,reviewergains an evidence standard (name the triggering input; passing tests are not proof), andtaskgains an evidence-bound completion requirement.Closes #2656