feat(knowledge): adversarial review protocol, design smells, object calisthenics, testability patterns#40
Merged
Merged
Conversation
…ct calisthenics, testability patterns Closes gaps identified in competitive analysis against code-craft plugin. **New knowledge files (4)** - `knowledge/adversarial-review-protocol.md` — structured challenger loop with per-agent question sets; agents append confidence level to summary - `knowledge/design-smells.md` — 14-row smell→pattern mapping table, finding format template, naming offender catalog - `knowledge/object-calisthenics.md` — Jeff Bay's 9 rules with language-agnostic pseudocode and pragmatic exceptions table - `knowledge/testability-patterns.md` — 4 patterns, "I Can't Test This Class" decision flow, anti-patterns table, references **Agent wiring (8 agents)** - structure-review: loads design-smells + object-calisthenics; Self-Challenge - complexity-review: loads object-calisthenics; Self-Challenge - test-review: loads testability-patterns; testability blocker detection; Self-Challenge - arch-review, domain-review, security-review: Self-Challenge sections - naming-review: loads naming offender catalog from design-smells - domain-review: Skills section wired to ubiquitous-language; `Skill` added to tools - spec-compliance-review: missing ## Skip section added (audit fix) **Skill wiring** - legacy-code: reference to testability-patterns added to Integration section **File-anchored plan tracking** - commands/plan.md: `## Build Progress` section added to plan template - commands/build.md: step completion now written to plan file on disk via Edit tool **New skill: ubiquitous-language** - `skills/ubiquitous-language/SKILL.md` — 6-phase grep-based glossary extraction; 4-gate filter; append-mostly per-concept files; optional interview phase; language-agnostic - `skills/ubiquitous-language/scripts/collect-domain-signals.sh` — signal collection script for JS/TS, C#, Java, Python, Go **Registry updates** - agent-registry.md: 4 new knowledge files registered; mermaid-diagramming and ubiquitous-language added to skills table Co-Authored-By: Claude Sonnet 4.6 (1M context) <noreply@anthropic.com>
- knowledge/agent-registry.md: add missing Name column to Knowledge Files table header (was rendering as malformed markdown) - CLAUDE.md: update knowledge files count 6→11 and skills count 33→34; add Ubiquitous Language to skills quick-reference list - agents/complexity-review.md: clarify self-challenge borrows structure-review questions (no complexity-specific section exists) - knowledge/adversarial-review-protocol.md: add ### complexity-review challenge questions section so complexity-review has its own set - skills/ubiquitous-language/SKILL.md: fix script path to use .claude/skills/ (installed path, not source-tree path) - collect-domain-signals.sh: add -- end-of-options separator to grep invocation to prevent option-injection via ROOT path Co-Authored-By: Claude Sonnet 4.6 (1M context) <noreply@anthropic.com>
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
code-craftplugin: adversarial-review-protocol, design-smells (14-row smell→pattern table + naming offender catalog), object-calisthenics (9 rules), and testability-patterns (decision flow + anti-patterns)## Knowledge Filesand## Self-Challengesections; adds## Build Progressto plan template + disk-write step to/buildfor session-reset durabilityubiquitous-languageskill (6-phase grep-based glossary extraction with 4-gate filter, append-mostly per-concept files, optional interview phase) and registers mermaid-diagramming + ubiquitous-language in agent-registryQuality Gate
Test Plan
/code-reviewon a project — review agents should loadknowledge/adversarial-review-protocol.mdand append confidence level to their summaries/planon a task — output plan should include## Build Progresssection with checkboxes/buildon an approved plan — verify it edits the plan file checkboxes on disk/ubiquitous-language src/on a project with domain entities — verify.plans/domain/is populated with per-concept files and_index.mdagent-registry.mdKnowledge Files table renders correctly (11 entries, 4-column header)🤖 Generated with Claude Code