- Add Table of Contents to devops.md, frontend.md, golang.md, sre.md, typescript.md
- Update CLAUDE.md with Four-File Update Rule and TOC maintenance guidelines
- Add checklist for adding/removing sections in standards files
- Improve dev-refactor skill to use Skill tool for dev-cycle handoff
- Add anti-rationalization patterns for gate execution shortcuts
- Add Execution Report sections to dev-cycle, dev-feedback-loop, dev-refactor
- Extract gap tracking rationalizations to shared-anti-rationalization.md
Generated-by: Claude
AI-Model: claude-opus-4-5-20251101
Simplify naming convention by removing fully qualified prefixes from all components. Names now use simple format (e.g., code-reviewer instead of ring-default:code-reviewer).
X-Lerian-Ref: 0x1
Update sequence and related fields in SKILL.md files across default, dev-team, finance-team, ops-team, pmo-team, and tw-team plugins to use ring-{plugin}:{component} naming format.
X-Lerian-Ref: 0x1
Update all agents, skills, and commands across 9 plugins to use fully qualified names in YAML frontmatter. This enables unambiguous component identification in multi-plugin environments.
Changes:
- 42 agents: name field updated to ring-{plugin}:{agent-name}
- 87 skills: name field updated to ring-{plugin}:{skill-name}
- 27 commands: name field updated (added frontmatter where missing)
- CLAUDE.md: Fixed contradictory examples in naming conventions
- ARCHITECTURE.md: Updated invocation examples throughout
X-Lerian-Ref: 0x1
- Rename execution-report.md to output-execution-report.md
- Rename anti-rationalization.md to shared-anti-rationalization.md
- Rename orchestrator-principle.md to shared-orchestrator-principle.md
- Rename pressure-resistance.md to shared-pressure-resistance.md
- Rename red-flags.md to shared-red-flags.md
- Rename tdd-prompt-templates.md to template-tdd-prompts.md
- Update all references across skills, agents, and documentation
Co-authored-by: factory-droid[bot] <138933559+factory-droid[bot]@users.noreply.github.com>
Converted all canonical references from relative paths to GitHub raw URLs for installation-agnostic access:
Changed pattern:
- Before: [CLAUDE.md](../../../CLAUDE.md)
- After: [CLAUDE.md](https://raw.githubusercontent.com/LerianStudio/ring/main/CLAUDE.md)
Files updated (18 total):
- All 10 dev-team skills
- All 8 dev-team agents with Standards Compliance Reports
Benefits:
- Works regardless of Ring installation location
- Consistent with WebFetch pattern already used in Standards Loading
- No broken links if directory structure changes
- Agent prompts can always access canonical sources
Generated-by: Claude
AI-Model: claude-sonnet-4-5-20250929
Added canonical references to 6 skills per Content Duplication Prevention rule:
- dev-devops: References CLAUDE.md and devops.md standards
- dev-feedback-loop: References CLAUDE.md for validation/gate requirements
- dev-implementation: References CLAUDE.md and test-driven-development skill
- dev-review: References CLAUDE.md and requesting-code-review skill
- dev-testing: References CLAUDE.md and test-driven-development skill
- using-dev-team: References CLAUDE.md and using-ring skill
All 10 dev-team skills now have canonical references pointing to single sources of truth.
Generated-by: Claude
AI-Model: claude-sonnet-4-5-20250929
This commit overhauls numerous skill files to prioritize information
density and improve readability for both humans and AI agents.
The main changes involve replacing verbose sections, such as Graphviz
diagrams and long descriptive paragraphs, with more structured and
compact formats like Markdown tables and simple text flows. This makes
the documents easier to parse and quicker to understand at a glance.
This refactoring aims to reduce the token count and cognitive load
required to process each skill, ensuring that the core patterns and
rules are immediately accessible.
Add agent output collection and prompt quality analysis to the dev-cycle:
- Store agent outputs in state (agent_outputs) at each gate for later analysis
- Add Step 3 to dev-feedback-loop for prompt quality analysis
- Create prompt-quality-reviewer agent to analyze outputs against agent definitions
- Calculate prompt quality scores based on MUST rules, output schema, and decision correctness
- Output feedback to docs/feedbacks/cycle-{date}/{agent}.md (one file per agent, accumulating tasks)
The feedback system enables continuous improvement of agent prompts by:
- Identifying rule violations with evidence
- Tracking patterns across multiple executions
- Generating specific, actionable prompt improvements
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Hardens dev-cycle, dev-review, dev-feedback-loop, and dev-sre skills by:
- Removing quantitative exceptions (<5 lines, <20 lines) from skip_when
- Adding NOT_skip_when sections with explicit rationalization rejections
- Expanding Common Rationalizations tables with new anti-patterns
- Adding Red Flags to catch self-exemption attempts
All gates now enforce absolute rules: AI doesn't negotiate, no exceptions.
Generated-by: Claude
AI-Model: claude-opus-4-5-20251101
- Add mandatory Standards Loading section to 5 agents (golang, typescript, devops, frontend, sre)
- Agents now WebFetch Ring standards from GitHub raw URLs
- Both PROJECT_RULES.md (local) and Ring standards (remote) are HARD GATES
- Fix using-dev-team agent count (9→7), remove non-existent agents
- Add Blocker Criteria section to dev-feedback-loop
- Standardize qa-analyst output_schema to Implementation archetype
Generated-by: Claude
AI-Model: claude-opus-4-5-20251101
Step 1 shows Gate 3 with 2 iterations (1 extra), so Step 2 calculation
should show 1 extra iteration = -10 penalty, resulting in score 90/100.
Generated-by: Claude
AI-Model: claude-opus-4-5-20251101
dev-feedback-loop: Replace unused skill references (root-cause-tracing,
codify-solution) with actual complementary skills (dev-cycle, dev-validation).
Add language identifier to formula code block.
dev-analysis: Fix agent dispatch format to use proper YAML structure with
explicit Task tool calls for parallel agent dispatch. Update AskUserQuestion
to match Claude Code's standard format with questions array and options.
Generated-by: Claude
AI-Model: claude-opus-4-5-20251101
Update root cause analysis example to use testing-related failures:
- Coverage gaps, missing edge case tests, fixture issues
- Root cause: TDD RED phase skipped
Update corrective actions and prevention measures to reference
correct gate numbers and skill names.
Generated-by: Claude
Update GATE BLOCKED example in dev-feedback-loop/SKILL.md to use
"Gate 4 (Review)" instead of "Gate 3 (Review)" to match the canonical
6-gate sequence: Gate 0 (Implementation), Gate 1 (DevOps), Gate 2 (SRE),
Gate 3 (Testing), Gate 4 (Review), Gate 5 (Validation).
Generated-by: Claude
Updated sequence and related fields in all dev-team skill YAML
frontmatter to use fully qualified names:
- ring-dev-team:skill-name for dev-team skills
- ring-default:skill-name for default plugin skills
Ensures consistent invocation names across the plugin ecosystem
per naming convention guidelines.
Generated-by: Claude
Co-Authored-By: Claude <noreply@anthropic.com>
