Add required 'Standards Verification' as FIRST output section to:
- qa-analyst (v1.3.2)
- devops-engineer (v1.3.3)
- sre (v1.4.2)
- frontend-engineer (v3.2.6)
- frontend-designer (v1.2.3)
Agents MUST output table showing PROJECT_RULES.md and Ring Standards status
before any implementation/validation work.
X-Lerian-Ref: 0x1
- Fix FOUR-FILE UPDATE RULE references in all 5 standards files
- Replace 'any LAYER' with 'any layer' in sre.md diagrams
- Concise rewording in dev-cycle and dev-refactor skills
- Add Anti-Duplication Check to template-tdd-prompts.md
- Fix sentence capitalization in standards-coverage-table.md
- Standardize section header casing in agent files
- Replace 'fix' with 'resolve' in sre.md for formal tone
Generated-by: Claude
AI-Model: claude-sonnet-4-20250514
Agents now reference standards-coverage-table.md instead of duplicating section lists inline. This prevents drift between agents and the canonical coverage table.
Also strengthens CodeRabbit execution rules in requesting-code-review skill - MANDATORY if installed, optional to install.
X-Lerian-Ref: 0x1
- Add standards-boundary-enforcement.md shared pattern
- Update all 8 dev-team agents with Standards Boundary Enforcement section
- Strengthen ORCHESTRATOR principle with explicit tool prohibition table
- Add recovery process for ORCHESTRATOR violations
- Add anti-rationalization rules for standards boundary
Agents must now:
1. WebFetch standards file first
2. Check ONLY requirements explicitly listed in standards
3. Verify before flagging - if not in WebFetch result, do NOT flag
4. Never directly edit source code (dispatch specialists instead)
Generated-by: Claude
AI-Model: claude-sonnet-4-20250514
AI agents can generate plausible but flawed code ("AI slop") that
includes hallucinated dependencies, scope creep, and context-unaware
implementations. This is a primary source of bugs and security risks.
To address this, introduce a system-wide framework for detecting and
preventing AI slop, centered around a new shared skill document:
`ai-slop-detection.md`.
This framework is integrated across the agent ecosystem:
- Specialist agents (engineers, DevOps) now perform a mandatory
pre-submission self-check to catch their own slop before review.
- Reviewer agents (code, security, business) use new mandatory
checklists to enforce quality gates against slop from other agents.
- Validation agents (QA, SRE) must verify command outputs to prevent
reporting hallucinated metrics or test results.
This provides a defense-in-depth strategy against common AI failure
modes, improving code quality and mitigating supply-chain attack
vectors like "slopsquatting."
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 all agent references to use the ring-{plugin}:{agent-name} format instead of bare agent names. This ensures consistent naming across all plugins and prevents ambiguity in multi-plugin environments.
X-Lerian-Ref: 0x1
Comprehensive update of all agent, skill, and command references throughout
the repository to use fully qualified names:
- Agent refs: `agent-name` → `ring-{plugin}:agent-name`
- Skill refs: `skill-name` → `ring-{plugin}:skill-name`
- Command refs: `/command` → `/ring-{plugin}:command`
Files updated include:
- All agent files in */agents/
- All skill files in */skills/
- All command files in */commands/
- Documentation files (README, CLAUDE.md, ARCHITECTURE.md, WORKFLOWS.md)
- Shared patterns and standards files
This ensures consistency between documentation and implementation,
enabling unambiguous component resolution in multi-plugin environments.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
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>
docs(standards): mandate explicit model parameter for specialized agents
feat(reviewers): add guidance for skipping reviews on trivial changes
refactor(docs): simplify shared pattern files for better reusability
fix(security): add SSRF to blocker criteria and OWASP version check
fix(docs): align heading levels and table formats for consistency
- Remove all CI/CD references from skills and agents
- Make DDD patterns MANDATORY for all services (Go, TypeScript, BFF)
- Update standards and agent files with mandatory language
Generated-by: Claude
AI-Model: claude-opus-4-5-20251101
Rename files to group related content alphabetically:
- agent-anti-rationalization.md -> anti-rationalization-agents.md
- skills-anti-rationalization.md -> anti-rationalization-skills.md
Update all 14 files referencing these shared patterns.
Generated-by: Claude
AI-Model: claude-opus-4-5-20251101
- Create standards-coverage-table.md with mandatory table format, status legend, anti-rationalization rules, and agent→standards section index
- Update all dev-team agents to reference shared pattern instead of duplicating instructions
- Add explicit TDD RED/GREEN sub-phases (0.1, 0.2) to dev-cycle Gate 0
- Enhance dev-implementation with detailed TDD phase tracking and state persistence
- Add Standards-Agent Synchronization rule (#5) to CLAUDE.md critical rules
Generated-by: Claude
AI-Model: claude-opus-4-5-20251101
Create shared-patterns directory with reusable content:
- pressure-resistance.md: Universal pressure scenarios for all gates
- anti-rationalization.md: Universal anti-rationalizations for skills
- agent-anti-rationalization.md: Agent-specific anti-rationalizations
- execution-report.md: Standard execution report format
Update 6 skills and 8 agents to reference shared patterns instead of
duplicating content. Add Shared Patterns Rule to CLAUDE.md enforcing
extraction of duplicated content to canonical locations.
Generated-by: Claude
AI-Model: claude-opus-4-5-20251101
Added mandatory section comparison process: agents must parse ALL sections from WebFetch result and compare each one with codebase-report.md. No section can be skipped - if not applicable, must report as N/A with reason.
Generated-by: Claude
AI-Model: claude-opus-4-5-20251101
Updated all 8 dev-team agents to require quoting from WebFetch results when reporting non-compliant findings. Agents must now include actual code/patterns from both codebase-report.md and the fetched standards file in their findings output.
Generated-by: Claude
AI-Model: claude-opus-4-5-20251101
Remove /health, /ready, /metrics endpoint requirements from SRE validation:
- Gate 2 now requires structured logging and tracing only
- Endpoints removed from skills, agents, and standards docs
- Reduces infrastructure coupling for simpler services
Add AUTO-TRIGGERED Standards Compliance to 8 agents:
- Detects MODE: ANALYSIS ONLY in dispatch prompt
- Auto-triggers WebFetch of Ring standards + comparison table
- HARD GATE enforcement when triggered
- Optional for direct implementation tasks
Generated-by: Claude
AI-Model: claude-opus-4-5-20251101
Fix multiple linting and convention issues:
- prompt-quality-reviewer: wrap bare URL in markdown link, add blank line before table
- devops-engineer: fix canonical URL path to include dev-team/ prefix, rename section to standard 'When Implementation is Not Needed'
- qa-analyst: use fully qualified skill name ring-dev-team:dev-refactor, fix coverage recalculation commands for Jest and pytest
- dev-review: replace raw GitHub URLs with repository-relative paths for internal references
All changes improve consistency with project conventions and fix incorrect command patterns.
Generated-by: Claude
AI-Model: claude-sonnet-4-5-20250929
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 schema reference to 7 implementation/specialist agents that produce Standards Compliance Reports:
- backend-engineer-golang
- backend-engineer-typescript
- devops-engineer
- frontend-bff-engineer-typescript
- frontend-engineer
- qa-analyst
- sre
Each now references docs/AGENT_DESIGN.md as the canonical source for output schema requirements per Content Duplication Prevention rule.
Note: prompt-quality-reviewer already documents its Standards Compliance Report section as 'Not Applicable' since it's an analyst agent.
Generated-by: Claude
AI-Model: claude-sonnet-4-5-20250929
Added reference to dev-team/docs/standards/devops.md as canonical source to prevent duplication per Content Duplication Prevention rule.
Generated-by: Claude
AI-Model: claude-sonnet-4-5-20250929
- Refactor all 7 dev-team agents to reference standards via WebFetch
- Remove duplicated Domain Standards sections from agents
- Update golang.md to lib-commons v3 with correct logging pattern:
- commons/zap for logger initialization (bootstrap/config only)
- commons/log for Logger interface (services, routes, consumers)
- Add Standards Compliance Output Format section to golang.md
- Add Standards Loading sections to qa-analyst and frontend-engineer agents
Agents now contain only: role definition, output schema, expertise
knowledge, blockers, and WebFetch references to standards files.
Generated-by: Claude
AI-Model: claude-opus-4-5-20251101
Removes the required_when field from agent output_schema definitions
as it was not implemented in any orchestrator validation layer. The
conditional requirement for Standards Compliance is already enforced
through prose instructions in each agent's documentation section
'Standards Compliance Report (MANDATORY when invoked from dev-refactor)'.
Updated description to clarify enforcement is via prose instructions.
Generated-by: Claude
AI-Model: claude-opus-4-5-20251101
Adds conditional Standards Compliance output section to all dev-team agents. When invoked from dev-refactor skill, agents compare codebase against Lerian/Ring standards (lib-commons for Go, lib-commons-js for TypeScript) and produce compliance reports.
Changes:
- Add Standards Compliance to output_schema with required_when conditional
- Add comparison categories and output format documentation per agent
- Update dev-refactor prompt templates to request compliance reports
- Categories adapted per domain (Go: lib-commons, TS: lib-commons-js, SRE: health/logging/tracing only)
Generated-by: Claude
AI-Model: claude-opus-4-5-20251101
- Add 'What If No PROJECT_RULES.md Exists?' HARD BLOCK section to all 7 agents
- Add 'What If Non-Compliant?' and 'Cannot Be Overridden' sections to devops, sre, qa agents
- Remove ~230 lines of internal duplications across all agents
- Consolidate Standards Loading references to single source of truth
- Merge redundant Blocker Format templates
- Unify Handling Ambiguous Requirements with cross-references
Generated-by: Claude
AI-Model: claude-opus-4-5-20251101
- Remove frontend-engineer.md agent (consolidated into frontend-bff-engineer-typescript)
- Fix dev-cycle state file inconsistency (cycle-state.json -> current-cycle.json)
- Update all cross-references in 19 files to point to frontend-bff-engineer-typescript
- Update agent count from 8 to 7 in documentation
Generated-by: Claude
AI-Model: claude-opus-4-5-20251101
