Commit Graph

15 Commits

Author SHA1 Message Date
0e70156e26 feat(projman): add plan-then-batch skill optimization
Separate cognitive work from mechanical API execution to reduce
skill-related token consumption by ~76-83% during sprint workflows.

Changes:
- Add batch-execution.md skill with 4-phase protocol
- Promote mcp-tools-reference and batch-execution to frontmatter
  for planner and orchestrator agents (auto-injected, zero re-read)
- Replace "Skills to Load" with phase-based "Skill Loading Protocol"
- Restructure planning-workflow.md Steps 8-10 for batch execution
- Update agent matrix in CLAUDE.md and docs/CONFIGURATION.md
- Add Phase-Based Skill Loading documentation section
- Clean up .gitignore (transient files, dev symlinks)

Token impact:
- 6-issue sprint planning: ~76% reduction
- 10-issue sprint planning: ~80% reduction
- 8-issue status updates: ~83% reduction

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
2026-02-03 19:57:10 -05:00
19ba80191f feat(agents): add permissionMode, disallowedTools, skills frontmatter to all 25 agents
- permissionMode: 1 bypassPermissions, 7 acceptEdits, 7 default, 10 plan
- disallowedTools: 12 agents blocked from Write/Edit/MultiEdit
- model: promote Planner + Code Reviewer to opus
- skills: auto-inject on Executor (7), Code Reviewer (4), Maintainer (2)
- docs: CLAUDE.md + CONFIGURATION.md updated with full agent matrix

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
2026-02-03 11:08:49 -05:00
c0d62f4957 feat(agents): add model selection and standardize frontmatter
Add per-agent model selection using Claude Code's now-supported `model`
frontmatter field, and standardize all agent frontmatter across the
marketplace.

Changes:
- Add `model` field to all 25 agents (18 sonnet, 7 haiku)
- Fix viz-platform/data-platform agents using `agent:` instead of `name:`
- Remove non-standard `triggers:` field from domain agents
- Add missing frontmatter to 13 agents
- Document model selection in CLAUDE.md and CONFIGURATION.md
- Fix undocumented commands in README.md

Model assignments based on reasoning depth, tool complexity, and latency:
- sonnet: Planner, Orchestrator, Executor, Coordinator, Security Reviewers
- haiku: Maintainability Auditor, Test Validator, Git Assistant, etc.

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
2026-02-02 20:37:58 -05:00
f7bcd48fc0 refactor(projman): create shared visual-output skill for DRY headers
- New skill: visual-output.md defines all header, progress, and verdict formats
- All 4 agent files now reference the skill instead of inline templates
- Phase Registry table maps agents to their emoji and phase name
- Single source of truth for visual branding changes

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
2026-02-02 13:57:56 -05:00
bea46d7689 feat(projman): add sprint lifecycle state machine via milestone metadata
- New skill: sprint-lifecycle.md defines states, transitions, and check protocol
- All sprint commands now check and set lifecycle state
- States tracked in milestone description metadata (Sprint/Planning, Sprint/Executing, Sprint/Reviewing)
- Out-of-order calls produce warnings with guidance
- --force override available for all lifecycle checks
- Added Sprint/* labels to label taxonomy documentation

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
2026-02-02 13:48:13 -05:00
4614726350 feat(projman): add domain consultation step to planner agent
Integrate domain-consultation skill into the planner agent workflow:
- Add skills/domain-consultation.md to Skills to Load section
- Add new responsibility "7. Domain Consultation" between Task Sizing and Issue Creation
- Renumber subsequent sections (Issue Creation -> 8, Request Approval -> 9)
- Add critical reminder #8 to always check domain signals

The domain consultation step analyzes planned issues for domain-specific
signals (viz-platform, data-platform) and appends appropriate acceptance
criteria before issue creation.

Closes #361

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
2026-02-01 18:15:15 -05:00
2e65b60725 refactor(projman): extract skills and consolidate commands
Major refactoring of projman plugin architecture:

Skills Extraction (17 new files):
- Extracted reusable knowledge from commands and agents into skills/
- branch-security, dependency-management, git-workflow, input-detection
- issue-conventions, lessons-learned, mcp-tools-reference, planning-workflow
- progress-tracking, repo-validation, review-checklist, runaway-detection
- setup-workflows, sprint-approval, task-sizing, test-standards, wiki-conventions

Command Consolidation (17 → 12 commands):
- /setup: consolidates initial-setup, project-init, project-sync (--full/--quick/--sync)
- /debug: consolidates debug-report, debug-review (report/review modes)
- /test: consolidates test-check, test-gen (run/gen modes)
- /sprint-status: absorbs sprint-diagram via --diagram flag

Architecture Cleanup:
- Remove plugin-level mcp-servers/ symlinks (6 plugins)
- Remove plugin README.md files (12 files, ~2000 lines)
- Update all documentation to reflect new command structure
- Fix documentation drift in CONFIGURATION.md, COMMANDS-CHEATSHEET.md

Commands are now thin dispatchers (~20-50 lines) that reference skills.
Agents reference skills for domain knowledge instead of inline content.

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
2026-01-30 15:02:16 -05:00
11d77ebe84 revert: remove unsupported defaultModel and model fields
Claude Code rejects `defaultModel` in plugin.json and `model` in agent
frontmatter with "Unrecognized key" validation error.

Removed:
- defaultModel from 6 plugin.json files
- model from 7 agent frontmatter files
- docs/MODEL-RECOMMENDATIONS.md (deleted)
- Model config sections from CONFIGURATION.md and CLAUDE.md
- Model validation from validate-marketplace.sh

This reverts Sprint 7 (v5.4.0) multi-model feature that was never
supported by Claude Code's plugin schema.

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
2026-01-30 12:09:38 -05:00
5aff53972e feat: add model:opus to critical reasoning agents
- projman/planner.md - architecture decisions
- projman/code-reviewer.md - quality review
- pr-review/security-reviewer.md - security analysis
- code-sentinel/security-reviewer.md - security scanning
- data-platform/data-analysis.md - complex data insights

Fixes #303

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
2026-01-28 21:51:20 -05:00
3561025dfc feat(projman): add visual output requirements to agents and commands
Add Visual Output sections to all projman files:
- 4 agent files with phase-specific headers (PLANNING, EXECUTION, CLOSING)
- 16 command files with appropriate headers

Headers use double-line box characters for projman branding:
- Planning phase: TARGET PLANNING
- Execution phase: LIGHTNING EXECUTION (+ progress block for orchestrator)
- Closing phase: FLAG CLOSING
- Setup commands: GEAR SETUP

Closes #273, #274

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
2026-01-28 17:10:49 -05:00
26310d05f0 feat(projman): add sprint approval requirement before execution (#233)
Sprint-plan approval workflow:
- Request explicit approval after creating issues
- Present scope summary (branches, files, dependencies)
- User must type "approve sprint N" to authorize
- Record approval in milestone description with timestamp

Sprint-start verification:
- Check milestone for "## Sprint Approval" section
- If missing, STOP and direct to /sprint-plan
- Extract approved scope (branches, files)
- Enforce scope during execution

Orchestrator scope enforcement:
- Verify approval before any execution
- Check each operation against approved scope
- Operations outside scope require re-approval

This separates planning (review) from execution (action),
preventing agents from executing without explicit user consent.

Closes #233

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
2026-01-28 10:51:10 -05:00
0abf510ec0 feat(projman): add strict task sizing rules to prevent runaway agents (#238)
Add mandatory task scoping rules:
- XS: 1 file, 0-2 checklist items, ~30 tool calls
- S: 1 file, 2-4 checklist items, ~50 tool calls
- M: 2-3 files, 4-6 checklist items, ~80 tool calls
- L/XL: MUST be broken down into smaller tasks

Sprint 3 showed agents running 400+ tool calls on single tasks,
causing 1+ hour waits with no visibility. This enforces:
- Maximum task scope (M = 2-3 files, 80 tool calls)
- Mandatory breakdown for L/XL tasks
- Clear scoping checklist for planners
- Good/bad examples showing proper breakdown

Planner must refuse to create L/XL tasks without breakdown.

Closes #238

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
2026-01-28 10:44:52 -05:00
842ce3f6bc feat(projman): add wiki-based planning workflow to sprint-plan
Phase 1 implementation for Change V04.1.0:
- Add flexible input source detection (file, wiki, conversation)
- Add wiki proposal and implementation page creation
- Add wiki reference to created issues
- Add cleanup step to delete local files after migration
- Update planner agent with wiki workflow responsibilities

Closes #161

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
2026-01-26 10:01:13 -05:00
74b28170fa feat: major improvements to projman plugin v1.0.0
- Remove Wiki.js MCP server entirely
- Add wiki, milestone, and dependency tools to Gitea MCP server
- Add parallel execution support based on dependency graph
- Add mandatory pre-planning validations (org check, labels, docs/changes)
- Add CLI blocking rules to all agents (API-only)
- Add standardized task naming: [Sprint XX] <type>: <description>
- Add branch naming convention: feat/, fix/, debug/ prefixes
- Add MR body template without subtasks
- Add auto-close issues via commit keywords
- Create claude-config-maintainer plugin for CLAUDE.md optimization
- Update all sprint commands with new tools and workflows
- Update documentation to remove Wiki.js references

New MCP tools:
- Wiki: list_wiki_pages, get_wiki_page, create_wiki_page, create_lesson, search_lessons
- Milestones: list_milestones, get_milestone, create_milestone, update_milestone
- Dependencies: list_issue_dependencies, create_issue_dependency, get_execution_order
- Validation: validate_repo_org, get_branch_protection, create_label

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
2026-01-19 17:12:35 -05:00
e9e425933b refactor: consolidate plugins into plugins/ directory
- Created plugins/ directory to centralize all plugins
- Moved projman and project-hygiene into plugins/
- Updated .mcp.json paths from ../mcp-servers/ to ../../mcp-servers/
- Updated CLAUDE.md governance section with new directory structure
- Updated README.md with new repository structure diagram
- Fixed all path references in documentation

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
2025-12-11 23:26:38 -05:00