fix(instructions): optimize Phase 1 DT token budgets and close #564/#565 gaps

[chaosdinosaur]

Pull Request

Description

Optimize all 6 Phase 1 Design Thinking instruction files for token budget compliance and fix two gaps blocking closure of issues #564 and #565.

Token Optimization (Issues #573-#578):

• Compressed 3 ambient tier files from ~5,000 combined tokens to ~1,911 tokens (62% reduction)
• Compressed 2 method tier files (Methods 02-03) with deep-file deferrals
• Added Quality Rules sections to all 3 method files (redistributed from ambient dt-quality-constraints)
• All 6 files now within their specified token budget upper bounds

Content Gap Fills (Issues #573, #574):

• Added Graduation Awareness section to dt-coaching-identity (readiness signals, advisory mode, partial graduation, re-engagement)
• Added Quality Enforcement Approach with Think/Speak/Empower integration to dt-quality-constraints
• Added Too Nice Prototype tension to dt-quality-constraints

Issue #565 Gap Fixes:

• Added hint_calibration block to dt-coaching-state schema (level 1-4, pattern_notes)
• Enriched dt-start-project prompt with stakeholders and industry optional inputs

Standards Compliance:

• Added Human-AI Collaboration deep-file reference to dt-method-03-synthesis

File	Before	After	Budget	Status
dt-coaching-identity	~1,275 tokens	~662 tokens	600-800	Pass
dt-quality-constraints	~1,394 tokens	~538 tokens	800-1,000	Pass
dt-method-sequencing	~2,331 tokens	~711 tokens	600-800	Pass
dt-method-01-scope	~1,713 tokens	~1,755 tokens	1,500-2,000	Pass
dt-method-02-research	~3,050 tokens	~1,108 tokens	1,500-2,000	Pass
dt-method-03-synthesis	~2,782 tokens	~1,401 tokens	1,500-2,000	Pass

Related Issue(s)

Closes #564
Closes #565
Relates to #573, #574, #575, #576, #577, #578

Type of Change

Select all that apply:

Code & Documentation:

• Bug fix (non-breaking change fixing an issue)
• New feature (non-breaking change adding functionality)
• Breaking change (fix or feature causing existing functionality to change)
• Documentation update

AI Artifacts:

• Reviewed contribution with prompt-builder agent and addressed all feedback
• Copilot instructions (.github/instructions/*.instructions.md)
• Copilot prompt (.github/prompts/*.prompt.md)
• Copilot agent (.github/agents/*.agent.md)
• Copilot skill (.github/skills/*/SKILL.md)

Sample Prompts (for AI Artifact Contributions)

User Request:
/dt-start-project projectName="Factory Floor Maintenance" context="Customer wants AI for manufacturing" stakeholders="Floor managers, maintenance technicians, IT" industry="Manufacturing"

Execution Flow:

1. dt-start-project prompt triggers dt-coach agent
2. Ambient instructions load (coaching-identity, quality-constraints, method-sequencing)
3. Method-01-scope instructions load via applyTo pattern matching
4. Coaching state initialized with hint_calibration at level 1
5. Coach begins Method 1 scope conversations with industry-informed vocabulary

Output Artifacts:

• .copilot-tracking/dt/factory-floor-maintenance/coaching-state.md with hint_calibration block
• Stakeholder mapping begins with pre-populated stakeholder groups

Success Indicators:

• Coach identity consistent across methods (Think/Speak/Empower, Graduation Awareness active)
• Quality constraints enforce fidelity without rule citations
• Method transitions follow compact sequencing table
• hint_calibration level adjusts based on team responsiveness

Testing

• npm run lint:md: 0 errors across 176 files
• Word count verification via PowerShell Measure-Object -Word on all 6 instruction files
• Token estimate verification: words x 1.3 within budget upper bounds for all files
• Task-reviewer validation with 4 parallel subagents (RPI Phase 1, Phase 2, feat(agents): DT coach agent and entry prompts #565 gaps, implementation quality)
• Review log: .copilot-tracking/reviews/2026-02-18/dt-phase1-token-optimization-plan-review.md

Checklist

Required Checks

• Documentation is updated (if applicable)
• Files follow existing naming conventions
• Changes are backwards compatible (if applicable)
• Tests added for new functionality (if applicable)

AI Artifact Contributions

• Used /prompt-analyze to review contribution
• Addressed all feedback from prompt-builder review
• Verified contribution follows common standards and type-specific requirements

Required Automated Checks

• Markdown linting: npm run lint:md
• Spell checking: npm run spell-check
• Frontmatter validation: npm run lint:frontmatter
• Skill structure validation: npm run validate:skills
• Link validation: npm run lint:md-links
• PowerShell analysis: npm run lint:ps

Security Considerations

• This PR does not contain any sensitive or NDA information
• Any new dependencies have been reviewed for security issues
• Security-related scripts follow the principle of least privilege

Additional Notes

Breaking Change: Method-Specific Quality Frameworks section removed from dt-quality-constraints. Methods 1-3 quality rules redistributed to their respective method files. Methods 4-9 quality rules tracked as deferred work (WI-01) for when those method files are created.

Deferred Content: Detailed coaching hat triggers, interview techniques, subagent dispatch protocol, and Human-AI Collaboration patterns deferred to Phase 3 deep files (dt-method-02-deep.instructions.md, dt-method-03-deep.instructions.md). References in method files point to these planned destinations.

[WilliamBerryiii]

One issue with the maturity field still being there ... not sure if that's the issues I filed or we still have latent instructions hanging around.

[codecov-commenter]

Codecov Report

✅ All modified and coverable lines are covered by tests.
✅ Project coverage is 85.43%. Comparing base (0079a4f) to head (bdff0c7).
⚠️ Report is 4 commits behind head on main.

Additional details and impacted files

@@           Coverage Diff           @@
##             main     #675   +/-   ##
=======================================
  Coverage   85.43%   85.43%           
=======================================
  Files          23       23           
  Lines        4674     4674           
=======================================
  Hits         3993     3993           
  Misses        681      681           

Flag	Coverage Δ
pester	85.43% <ø> (ø)

Flags with carried forward coverage won't be shown. Click here to find out more.

🚀 New features to boost your workflow:

• ❄️ Test Analytics: Detect flaky tests, report on failures, and find test suite problems.