Workflows were calling init commands to get parsed JSON metadata, then
immediately reading the same files again with cat to pass raw content
to agents. This wastes context tokens.
Changes:
- Add --include flag to init execute-phase, plan-phase, and progress
- Support includes: state, config, roadmap, requirements, context,
research, verification, uat, project
- Update plan-phase.md to use --include (removes 6 cat calls)
- Update execute-phase.md to use --include (removes 2 cat calls)
- Update execute-plan.md to use --include (removes 2 cat calls)
- Update progress.md to use --include (removes 4 cat calls)
- Add 7 tests for --include functionality
Token savings: ~5,000-10,000 tokens per plan-phase execution,
~1,500-3,000 per other workflow executions.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
The installer was using JSON.parse() which fails on JSONC (JSON with
Comments) files. OpenCode supports JSONC via jsonc-parser, so users
may have comments or trailing commas in their config.
Previously, parse failures would reset config to {} and overwrite the
user's file, causing data loss.
Changes:
- Add parseJsonc() to handle comments, trailing commas, and BOM
- On parse failure, skip permission config entirely instead of
overwriting user's file
- Show helpful error message with reason
Fixes#474
Co-authored-by: Claude Opus 4.5 <noreply@anthropic.com>
Add three new commands that extract structured data from GSD files,
reducing context usage by returning only parsed fields instead of
raw file content:
- phase-plan-index: Plans grouped by wave with metadata (id, wave,
autonomous, objective, files_modified, task_count, has_summary)
- state-snapshot: Parsed STATE.md fields (current phase, decisions,
blockers, session info)
- summary-extract: Frontmatter extraction with optional --fields filter
Update workflows to use new commands:
- execute-phase: Use phase-plan-index instead of ls + grep loop
- plan-phase: Use state-snapshot for decisions
- research-phase: Use state-snapshot for decisions
- complete-milestone: Use summary-extract for one-liners
Co-authored-by: Claude Opus 4.5 <noreply@anthropic.com>
Reverts af7a057 "feat: add GSD Memory cross-project knowledge system"
The memory system needs more work before shipping:
- Workflow integration is incomplete (writes but doesn't query)
- UX requires too much manual intervention
- Setup friction exceeds value for most users
Preserved on branch `memory-wip` for continued development.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Implements MCP server for semantic search across GSD projects:
MCP Tools:
- gsd_memory_search: Search across all registered projects
- gsd_memory_decisions: Find decisions from SUMMARY/PROJECT.md
- gsd_memory_patterns: Find patterns from SUMMARY.md
- gsd_memory_pitfalls: Find pitfalls from RESEARCH.md
- gsd_memory_stack: Find tech stack entries
- gsd_memory_register: Register project with memory
- gsd_memory_index: Trigger indexing/update
- gsd_memory_status: Show system status
Architecture:
- QMD wrapper with grep fallback when QMD unavailable
- YAML frontmatter extractors for GSD document types
- Project registry at ~/.gsd/projects.json
- Auto-install via bin/install.js for Claude Code
Workflow integrations:
- new-project: Registers project with memory
- plan-phase: Indexes after planning
- execute-phase: Indexes after execution
- complete-milestone: Indexes milestone completion
- Researcher agents query memory before Context7
Tests: 117 passing (66 unit + 51 integration)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
set-profile and settings commands hard-errored when .planning/config.json
did not exist, blocking users from changing model profile before running
new-project. Create config.json with balanced defaults when missing.
Executor self-check after SUMMARY.md creation verifies key-files exist
on disk and commit hashes exist in git log. Orchestrator spot-checks
SUMMARY claims before trusting and proceeding to next wave. Segmented
execution (execute-plan.md) gets the same self-check inline.
Fixes#363
The update command was hardcoded to use --global flag, which would
convert a local installation to a global one during updates.
Changes:
- Detect install type by checking ./.claude/ first, then ~/.claude/
- Use --local flag when updating a local install
- Use --global flag when updating a global install
- Update cache cleanup path to match install location
- Clarify warning message paths to be relative to install location
Fixes#343
The agent was misinterpreting commit_docs=false as 'skip file write'
when it should only skip git commit operations.
Changes:
- Explicitly state Write tool is mandatory in Step 5
- Clarify commit_docs only affects git operations, not file writes
- Rename Step 6 to indicate it's optional
- Make the file-write-then-commit order explicit
When updating GSD, the installer renames statusline.js to gsd-statusline.js
but didn't update existing settings.json references. Users with the old
config would see their status line disappear.
Now cleanupOrphanedHooks() also checks for and updates any statusLine
config pointing to the old path.
Fixes#330
Co-authored-by: Claude Opus 4.5 <noreply@anthropic.com>
* prompt(001): map dependencies for new-project command
* fix(#326): enforce context fidelity in planning pipeline
Root cause: User decisions from CONTEXT.md were available but not
enforced throughout the RESEARCH → PLAN → VERIFY chain.
Changes:
- gsd-planner: Add <context_fidelity> section requiring agents to
parse and honor user decisions BEFORE creating tasks. Includes
self-check checklist and conflict handling guidance.
- gsd-phase-researcher: Add User Constraints as FIRST section in
downstream consumer table. Require researcher to copy CONTEXT.md
decisions verbatim to RESEARCH.md so planner sees them even if
it only skims.
- research.md template: Add <user_constraints> section that must
be populated first. Locked decisions, Claude's discretion, and
deferred ideas copied verbatim from CONTEXT.md.
The command file (commands/gsd/plan-phase.md) already passes
CONTEXT_CONTENT to all agents. These changes add the enforcement
layer in the agent instructions.
Fixes#326, #216, #206
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 4.5 <noreply@anthropic.com>
- Add Character Preservation section to GSD-STYLE.md
- Clarify 'no special chars' applies to FILENAME only in add-todo
- Use 'box-drawing' terminology for tree structure visualization
Co-authored-by: FlightCore Dev <dev@flightcore.pl>
CONTEXT.md from /gsd:discuss-phase now flows through entire pipeline:
- Loaded early in step 4, stored for all agent spawns
- Researcher: constrains research scope (locked decisions vs discretion)
- Planner: explicit guidance to honor locked decisions
- Checker: new Context Compliance dimension to verify plans respect user vision
- Revision: reminder to maintain context compliance during fixes
Adds Dimension 7 (Context Compliance) to gsd-plan-checker:
- Verifies locked decisions have implementing tasks
- Flags if tasks contradict locked decisions
- Flags if deferred ideas included in plans
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Add "Squash merge" as recommended option at complete-milestone
- Keep "Merge with history" (--no-ff) as alternative
- Document merge options in planning-config reference
Improves on #298 based on community feedback from @oojacoboo.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
