v1.9.0 Pass 2A — poli-sci breadth in guide body + Cost-Conscious Composition#115
Merged
Merged
Conversation
… Composition Pass 2A lands two guide-only additions: weaves v1.8.0 political-science breadth into the user-facing guide body (previously discoverable only in the v1.8.0 CHANGELOG), and adds a Cost-Conscious Composition subsection documenting prompt-cache TTL behaviour, per-agent model routing, and /cost / /usage monitoring. No new skills, agents, rules, or hooks. Political-science breadth surfaced in guide body: - 5-Lens Framework table — added Political Science as third worked example column (ignorability, conjoint AMCEs, cjoint/survey defaults, manipulation-check fidelity). - Domain-reviewer ship-status callout — documents the two concrete customizations that ship (econ + poli-sci). - /review-paper --peer [journal] callout — explainer covering editor + 2-referee pipeline, journal-profiles starter set (econ + poli-sci), and the 6-paper-type methods-referee taxonomy. - §7 Customizing — "What ships preloaded vs. what you customize" callout. Points at v1.9-backlog.md as next-breadth roadmap. Cost-Conscious Composition subsection: - TTL guidance — 60min → 5min change and ENABLE_PROMPT_CACHING_1H opt-in. cache_miss_reason as the diagnostic. - 70/20/10 model-routing table mapping to template agents. - Effort-budgeting: reach for xhigh only when cheaper tier verified to fail. - /cost + /usage callout + Agent SDK credit-pool reference. Verification: - check-surface-sync.sh: 26/26 pass - check-skill-integrity: pass - quarto render: clean - quality_score: 100/100 🤖 Generated with [Claude Code](https://claude.com/claude-code)
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
1 participant
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
Pass 2A of v1.9.0 lands two guide-only additions with no new skills/agents/rules/hooks:
/review-paper --peer [journal]callout documents the 6-paper-type taxonomy with per-type sanity checks, and §7 Customizing gets a "what ships preloaded vs. what you customize" callout pointing at the v1.9-backlog roadmap.ENABLE_PROMPT_CACHING_1Hopt-in,cache_miss_reasondiagnostic), 70/20/10 model-routing table mapping to specific template agents, effort-budgeting rule,/costand/usagecallout, and Agent SDK credit-pool reference.Test plan
./scripts/check-surface-sync.sh— 26/26 assertions passcheck-skill-integrity— all checks passquarto render guide/workflow-guide.qmd— clean renderpython3 scripts/quality_score.py guide/workflow-guide.qmd— 100/100 [EXCELLENCE]docs/for GitHub Pages🤖 Generated with Claude Code