feat(systemplane): refactor migration skill for lib-commons v5 API
docs(plugin): update skill counts and keywords for new deck skill
chore(plans): remove obsolete caching and dev-cycle plan documents
Migrate authoritative sources, standards, skills, and platform mirrors from lib-commons v2/v4 to v5.0.2. ~215 line-level replacements across 26 files.
- Authority chain aligned: README, backend-engineer-golang, standards-coverage-table, and dev-team/docs/standards/golang/* now declare v5 as current.
- Code examples and import paths updated from lib-commons/v2/... and lib-commons/v4/... to lib-commons/v5/....
- Header notices added to preserve historical bodies of dev-systemplane-migration (v5 systemplane rewrite flagged), .archive/migrate-v4 (completed v2/v3 to v4 migration), and docs/plans/2026-04-14-caching-cqrs-standards (archived plan).
- OpenCode Version Gate: removed false claim that cassert, cruntime, csafe, cbackoff, and coutbox were introduced in v5 (they are v4); callout now lists v2/v3/v4 as legacy below the v5 standard.
X-Lerian-Ref: 0x1
Generated-by: Claude
AI-Model: claude-opus-4-7
docs: align all documentation with the new 10-reviewer workflow
docs(lib-commons): update skill to reflect major v5.0.2 release
chore(hooks): tune context reminder hook to reduce token consumption
Cross-reference audit after v1.56.0 found stale references to the removed Gate 0.5 dispatch. Critical: validate-gate-progression.sh was reading .delivery_verification.status from TASK level (no longer populated), firing false errors on every real cycle. Now reads subtask-level .gate_progress.implementation.delivery_verified. dev-cycle/SKILL.md self-description (frontmatter, overview, cannot-skip block) updated from "11 gates (0→0.5→1→...→9)" to the three-cadence model. using-dev-team marks ring:dev-delivery-verification DEPRECATED. dev-refactor-frontend artifact description swaps "1:1 mapped" for clustering.
Public docs (CLAUDE.md, README.md, WORKFLOWS.md) updated to describe subtask/task/cycle cadence instead of old per-unit linear flow. file-size-enforcement.md dispatch point corrected from Gate 0.5 to Gate 0 exit criteria (ring:dev-implementation Step 7).
Stripped meta-narration markers ("since R4", "formerly Gate 0.5", "since Prancy Bentley speedup", "absorbed from former...") from skill bodies. Skills describe current behavior; edit history lives in CHANGELOG and git log, not in agent context.
X-Lerian-Ref: 0x1
Align cycle-management and systemplane-migration with the dev-* prefix pattern used by 30/31 other dev-team skills. Updates frontmatter, internal self-references, README cross-references, and state path (docs/ring-systemplane-migration/ -> docs/dev-systemplane-migration/).
X-Lerian-Ref: 0x1
feat(pm-team): add skill for Lerian Map platform integration
feat(installer): add support for pi-coding-agent to expand ecosystem
refactor(installer): remove Cursor and Cline support to simplify maintenance
docs: update skill counts to 93 and document new skills
refactor(skill): simplify name of lerian-map-management skill
style(skill): improve conciseness of dev-multi-tenant description
Full sweep of README.md, ARCHITECTURE.md, MANUAL.md, and CLAUDE.md
to match actual skill/agent/command counts. Previously documented as
83-84 skills / 37 agents / 32 commands; actual codebase has 89 skills
/ 38 agents / 33 commands. Added missing entries for helm-engineer
agent, migrate-v4 command, and 6 undocumented skills across default
and dev-team plugins.
Generated-by: Claude
AI-Model: claude-opus-4-6
Large pull requests suffer from context pollution, where automated
reviewers must process many unrelated files. This dilutes focus, leading
to shallower analysis and degraded review quality.
This commit introduces Review Slicing to solve this problem by improving
review depth for large, multi-themed changes.
A new orchestrator agent, `ring:review-slicer`, is introduced. It uses a
deterministic heuristic (based on file count and directory span) to
decide whether to slice a PR. For large PRs (e.g., 15+ files), it
classifies changed files into thematic slices. For small PRs, the
standard review process is used, adding no overhead.
The core review skill and command now dispatch all seven reviewers in
parallel for each slice, providing them with a focused, scoped diff.
A new consolidation step then merges and deduplicates findings from all
slices into a single report, identifying "cross-cutting concerns" that
appear across multiple slices and may signal architectural issues.
Introduces a new parallel reviewer, `ring:dead-code-reviewer`, to
systematically identify orphaned code resulting from changes. This
enhances codebase hygiene by detecting unused helpers, types, and
tests, thereby reducing technical debt and improving maintainability.
The parallel code review system is expanded from 6 to 7 concurrent
reviewers. All related workflows, skills, commands, and documentation
have been updated to integrate this new capability.
- Add the `ring:dead-code-reviewer` agent, which analyzes code across
three concentric rings (target, direct dependents, ripple effect) to
find unreachable code.
- Update the `/ring:codereview` command and `ring:requesting-code-review`
skill to dispatch all 7 reviewers in a single parallel step.
- Adjust project documentation, including architecture diagrams, manuals,
and agent guides, to reflect the 7-reviewer workflow.
feat(default): add session-handoff skill to enable seamless context resume
refactor(arch): move complex orchestration from commands into skills
feat(pm-team): add orchestrator skills for pre-dev planning workflows
feat(dev-team): add skill to manage development cycle state (status/cancel)
feat(default): add skill to formalize git commit generation process
refactor(default): prune granular skills to focus core library on workflows
fix(pmo-team): align pmo-retrospective skill name with ring convention
docs: update all documentation to reflect major skill refactoring
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.
The codereview pre-analysis pipeline is refactored to use 'mithril',
an external tool installed via 'go install'. The previous system of
pre-built, in-repo binaries with its custom build workflow and
checksum verification is removed. This change simplifies maintenance
and improves security by leveraging the Go ecosystem's checksum DB.
The visual-explainer skill is refactored to use the '@pierre/diffs'
library for rendering code diffs, replacing the hand-rolled CSS
panels. This provides a more professional and feature-rich
visualization with word-level diffs and Shiki syntax highlighting.
Finally, obsolete audit and handoff documents are removed, and a help
message in the install script is updated to be accurate.
The previous 10-gate workflow lacked specific validation for multi-
tenant environments. To improve software reliability and ensure data
isolation between tenants, a dedicated multi-tenancy gate is necessary.
This change introduces a new "multi-tenant" gate into the `dev-cycle`
workflow, immediately following the implementation gate. This expands the
process from 10 to 11 gates. All related documentation has been
updated to reflect this new, more robust development cycle.
Reflects the addition of two new skills to the `ring-dev-team` plugin.
The total number of skills is increased from 81 to 83.
The `dev-cycle` workflow is now an 11-gate process, updated from the
previous 10-gate structure. All references in ARCHITECTURE.md,
CLAUDE.md, MANUAL.md, and README.md have been updated to maintain
documentation accuracy and consistency with the new features.
- Map skills to ~/.cursor/skills, agents to agents/, commands to commands/
- Emit YAML frontmatter (name, description) for skills and agents; plain markdown for commands
- Add PyYAML to requirements for frontmatter parse/emit
- Update transformers and tests for Cursor format
Co-authored-by: Cursor <cursoragent@cursor.com>
Code reviews that focus only on changed files can miss how those
changes break other parts of the codebase. Callers, contract
consumers, and dependent modules can be inadvertently affected, leading to
bugs that are difficult to detect in a localized review.
This commit introduces a new agent, `ring:consequences-reviewer`, to
systematically trace these "ripple effects." Its purpose is to analyze
the downstream impact of code changes by walking caller chains and
verifying consumer contracts.
The core parallel code review workflow, orchestrated by the
`/ring:codereview` command, now dispatches six agents in parallel
instead of five. All related documentation, skills, and agent prompts
have been updated to reflect this more robust 6-reviewer process.
Adds documentation for the new `visual-explainer` skill and its
corresponding `/ring:md-to-html` command to the `ring-default` plugin.
This change updates component counts (skills, commands) across all
documentation files including README, ARCHITECTURE, and MANUAL.
The purpose is to ensure all documentation is accurate and consistent
with the current codebase, making the new feature discoverable.
To provide a specialized process for frontend development, this commit
introduces a dedicated frontend development cycle, agent, and commands.
This new workflow is distinct from the backend-focused dev-cycle and
enforces critical quality gates specific to the frontend, such as
accessibility, visual regression, and performance testing.
The `dev-team` plugin is expanded with the following:
- A new `qa-analyst-frontend` agent for specialized UI/UX testing.
- New commands: `/ring:dev-cycle-frontend` and
`/ring:dev-refactor-frontend`.
- Six new skills to support the frontend workflow gates.
Additionally, component counts and descriptions are updated across all
documentation (README, MANUAL, ARCHITECTURE) to reflect these additions
and other minor changes, such as the expanded scope of the
`production-readiness-audit` skill.
The parallel code review process expands from 3 to 5 reviewers to
enhance code quality. This introduces `ring:test-reviewer` and
`ring:nil-safety-reviewer` to provide deeper analysis of test coverage
and null safety patterns, improving overall reliability.
The `dev-cycle` workflow is upgraded from a 6-gate to a 10-gate process,
incorporating a sophisticated suite of automated testing gates:
- Unit Testing (Gate 3)
- Fuzz Testing (Gate 4)
- Property-based Testing (Gate 5)
- Integration Testing (Gate 6)
- Chaos Testing (Gate 7)
This change establishes a much higher standard for testing and ensures
features are more resilient and production-ready.
Finally, new agents and commands are added to the PMO and Product plugins
to support delivery tracking, design validation, and reporting, further
extending the system's capabilities across the development lifecycle.
All documentation is updated to reflect these enhancements.
Apply unified ring: namespace to agent/skill identifiers across README, executing-plans, writing-plans, and pre-dev-feature command to comply with the Ring component naming convention.
X-Lerian-Ref: 0x1
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.
Expands the FinOps plugin to include cost management, which is a core
pillar of the discipline. This provides users with a new capability to
plan and optimize infrastructure spending.
This change introduces the `infrastructure-cost-estimator` agent and
its corresponding `infrastructure-cost-estimation` skill. All project
documentation is updated to reflect the new agent, skill, and the
incremented total counts.
The existing ring-pm-team focuses on single-feature planning. This
leaves a gap in portfolio-level coordination, governance, and
executive reporting.
This commit adds the 'ring-pmo-team' plugin to provide macro-level
strategic oversight for managing a portfolio of multiple projects. It
complements the feature-focused teams, completing the value chain from
portfolio strategy to code execution.
Key additions include:
- 5 specialist agents for portfolio, resource, risk, governance, and
executive reporting functions.
- 8 skills with frameworks for planning, allocation, and analysis.
- 3 slash commands to initiate common PMO workflows.
- A 'shared-patterns' library to enforce consistency across skills.
The plugin is registered in the marketplace, and all documentation and
installation scripts are updated to reflect this new addition and the
corresponding increase in total agents, skills, and commands.
feat(codereview): add call graph analyzers for Go, TS, and Python
feat(codereview): add JSON output and markdown impact summary report
docs(codereview): add handoff documents for phase 2 and 3
test(codereview): add unit and integration tests for call graph feature
refactor(*): standardize all agent and skill names with `ring:` prefix
docs(*): update all documentation to use new `ring:` prefix for names
docs(commands): add 'ring:' prefix to all command invocations
build(deps): remove requirements.txt in favor of dependency-map.md
chore(docs): remove obsolete handoff for namespace refactoring
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 major refactoring archives 5 non-core plugins to simplify the
project's focus and reduce maintenance overhead. The goal is to
concentrate on the primary software delivery value chain: Product
Planning -> Development -> Documentation.
The following plugins have been moved to the `.archive/` directory:
- ring-finance-team
- ring-finops-team
- ring-ops-team
- ring-pmm-team
- ring-pmo-team
This change reduces the number of active plugins from 9 to 4.
Key changes include:
- Updating `.claude-plugin/marketplace.json` to remove archived plugins.
- Updating all top-level documentation (README, ARCHITECTURE, MANUAL) to
reflect the new, focused set of 4 plugins.
- Deleting obsolete development plans and handoffs associated with the
archived plugins.
- Removing cross-plugin references from the remaining active plugins.
- Updating the installer script to remove mentions of archived plugins.
By archiving this code instead of deleting it, we preserve the work
for future reference while cleaning up the active codebase.
Proactive requirements gathering through structured user interview. Instead of the AI making assumptions, it systematically interviews the user to uncover ambiguities, preferences, and constraints BEFORE implementation begins.
X-Lerian-Ref: 0x1
- Delete duplicate dev-review skill from dev-team
- Update all references to use requesting-code-review
- Clarify skill modes: WITH INPUTS (any caller) vs STANDALONE (auto-detect)
- requesting-code-review now serves as the canonical Gate 4 skill
This commit updates all documentation to reflect a major expansion of the
Ring marketplace. The changes introduce new plugins, agents, and
commands, significantly increasing the system's capabilities.
Four new plugins are added, expanding the total from 5 to 9:
- `ring-finance-team`: For financial operations and analysis.
- `ring-ops-team`: For production and platform operations.
- `ring-pmo-team`: For portfolio management and governance.
- `ring-pmm-team`: For product marketing and go-to-market.
Existing plugins are also enhanced:
- `ring-dev-team`: Adds `frontend-engineer` and `prompt-quality-reviewer`
agents, increasing the agent count from 7 to 9.
- `ring-default`: Adds new commands like `explore-codebase` and `lint` to
improve codebase analysis and quality checks.
Finally, documentation standards are improved by enforcing fully
qualified names (e.g., `ring-default:agent`) in all examples to prevent
ambiguity and improve clarity in a multi-plugin environment.
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
The ring-cli tool and its associated search index are removed to
reduce project complexity and maintenance overhead.
The pre-built search index, Go CLI, Python extractor, and automated CI
workflow created a significant maintenance burden that outweighed the
benefits of a standalone search tool. This change simplifies the
codebase and the developer setup process.
Component discovery will now rely on in-session capabilities and
standard documentation.
This commit removes:
- The entire `tools/ring-cli` directory and its contents.
- The `rebuild-index.yml` GitHub Actions workflow.
- All references to `ring-cli` in documentation and shell hooks.
Implements multi-touchpoint discoverability strategy for ring-cli component search tool. Users now see CLI awareness at session start (hook injection), during onboarding (README), in quick reference (MANUAL), in AI context (CLAUDE.md), and when learning skills (using-ring).
Ensures users discover the CLI when they need it without overwhelming core workflows. CLI serves 'before Claude' and 'outside Claude' moments (pre-session planning, CI/CD, quick lookups).
Generated-by: Claude
AI-Model: claude-sonnet-4-5-20250929
