feat(hooks): add schema validator and enhance skill generation
refactor(*): align all components with the new frontmatter schema
refactor(commands): replace arguments object with simple argument-hint
refactor(agents): remove invalid version field from agent frontmatter
test(hooks): add unit tests for frontmatter validation and generation
Removes the hard-coded `model: "opus"` requirement from all agent
definitions, skill examples, and command documentation. The orchestrator
is now responsible for model selection, making the agent framework more
flexible and model-agnostic.
Key changes include:
- Removing the `model` parameter from all agent frontmatter and Task
tool examples.
- Deleting the "Model Requirement" hard gate and self-verification
sections from all agent prompts. This simplifies the prompts and
removes model-specific enforcement logic.
- Updating core documentation (ARCHITECTURE, MANUAL, README) to reflect
that model selection is an orchestrator concern.
- Removing redundant `changelog` and `last_updated` fields from agent
frontmatter, as this information is tracked by source control.
This architectural shift allows the orchestrator to dynamically choose
the best model for a given task based on complexity, cost, or speed,
without being constrained by the agent's definition. It simplifies
agent maintenance and prepares the system for easier integration of
future AI models.
Transform all user-facing Ring component references from colon-based
notation (ring:) to a standardized hyphen-based format (ring-).
This change affects skill names, agent names, and slash commands in all
documentation, guides, and examples. The goal is to create a consistent
and user-friendly namespace that is easier to read and type.
For example:
- Skill/Agent references like `ring:code-reviewer` become `ring-code-reviewer`
- Slash commands like `/ring:codereview` become `/ring-codereview`
The colon-based format (`ring:`) is intentionally preserved in YAML
frontmatter (`name: ring:skill-name`) for internal metadata, separating
the user-facing display name from the internal tooling identifier.
All 8 dev-team agents now MUST output a Precedence Decisions table showing:
- Which source was used for each decision (Ring vs PROJECT_RULES)
- Explicit conflict resolution when PROJECT_RULES overrides Ring
- Clear audit trail for standards compliance
X-Lerian-Ref: 0x1
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
This commit restructures the plugin ecosystem to improve maintainability,
simplify component invocation, and focus on high-value domains.
Key changes:
- **Unified Namespace:** All component invocations are standardized to the
`ring:{component}` format, replacing the verbose `ring-{plugin}:...`
prefix. This simplifies usage and abstracts the internal plugin
structure.
- **Archive Legacy Plugins:** The `finance-team`, `ops-team`, `pmm-team`,
and `pmo-team` plugins are moved to a new `.archive` directory.
These plugins contained complex, outdated patterns and are now
preserved for historical reference only.
- **Introduce FinOps Plugin:** A new, highly-focused `finops-team` plugin
is added to handle Brazilian financial regulatory compliance (BACEN,
RFB), consolidating critical functionality into a more focused package.
- **Update Documentation:** Core documentation (`ARCHITECTURE.md`,`README.md`,
`CLAUDE.md`, `MANUAL.md`) and the plugin marketplace are updated to
reflect the new structure and unified namespace.
This change introduces a namespacing convention for all built-in agents,
commands, and skills to prevent potential naming collisions with
user-defined entities.
All default entity names in the frontmatter are now prefixed with
'ring:'. For example, 'name: code-reviewer' becomes
'name: ring:code-reviewer'.
This creates a clear distinction between core framework components and
custom ones, improving the system's overall robustness and
extensibility.
- 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
