npm - @dotdotgod/claude-code - Versions diffs - 0.2.27 → 0.3.0 - Mend

@dotdotgod/claude-code 0.2.27 → 0.3.0

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.

Files changed (13) hide show

package/README.md CHANGED Viewed

@@ -4,11 +4,19 @@
 Claude Code adapter for dotdotgod's docs-first project-memory workflow.
-Use this package when you want Claude Code to initialize shared project docs, load bounded repository context, plan from durable docs before implementation, and review changed files with graph-impact evidence before handoff.
+Use this package when you want Claude Code to work from a shared project brain: maintained agent rules and docs, durable plans, focused context loading, and changed-file evidence before handoff.
+## What Changes
+- **Claude starts from shared project knowledge.** `AGENTS.md` and the documentation map remain reusable across agents while Claude-specific commands provide a native entry point.
+- **Plans become durable project artifacts.** `/dd:plan` records task intent under `docs/plan/` so it survives compaction, handoff, and new sessions.
+- **Project evidence arrives when needed.** `/dd:load` and the local MCP runtime provide bounded documentation, command output, files, and fetched text.
+- **Changed files retain their review context.** Packaged hooks track successful edits and require matching graph impact before broad verification or handoff commands.
+- **The workflow stays inspectable.** A denied operation names the required MCP action, and Claude retries the original operation after the check succeeds.
 ## Start Here
-This package is a Claude Code plugin: a plugin manifest plus `/dd:*` commands and skills. Installing it from npm alone does not register the commands — Claude Code loads it through plugin registration or a local plugin directory.
+This package is a Claude Code plugin containing a manifest, `/dd:*` commands, skills, MCP integration, and hooks. Claude Code registers these resources when it loads the package through plugin registration or a local plugin directory.
 Register the dotdotgod plugin marketplace inside Claude Code, then install the plugin:
@@ -70,7 +78,7 @@ The plugin starts a local stdio MCP server. It exposes `execute`, `batch_execute
 Dotdotgod execution tools share a 10 MiB stdout/stderr capture ceiling per command. Crossing that ceiling terminates the child process and reports `captureLimitExceeded`; direct stdout and stderr excerpts are each capped at 1 MiB. Their child environments preserve compatibility-oriented inheritance after filtering runtime injection variables; this reports filtered names without values but does not isolate ordinary inherited credentials. Large output is indexed before retrieval in the ignored project-local `.dotdotgod/context/context.sqlite` FTS5 store, and searches return bounded excerpts. The store uses WAL, a bounded busy timeout, and transactional source replacement, expiry, and purge. Structural Markdown/JSON chunks, bounded typo-tolerant trigram candidates, reciprocal-rank fusion, and title/path/proximity signals improve retrieval while provenance and `instructionAuthority: "none"` identify retrieved text as non-authoritative data.
-The MCP `index` tool accepts project-contained files or bounded directories with deterministic traversal, configurable resource limits, explicit extension/path exclusions, and symlinks skipped by default; it does not apply `.gitignore` semantics automatically. These capture and retrieval rules apply only when Claude calls the dotdotgod MCP tools. The plugin does not transparently intercept or rewrite Claude Code's built-in Bash tool. URL indexing performs application-level HTTP(S), DNS/address, connected-peer, redirect, and byte-limit validation. Accepted HTML is normalized as bounded untrusted text without browser rendering, JavaScript, subresource loading, or link following by default. The server bundles no browser renderer, so browser opt-in fails unless a host injects that capability. These controls are not a network sandbox or complete prompt-injection prevention. See the [`@dotdotgod/context` npm package](https://www.npmjs.com/package/@dotdotgod/context), its [GitHub README](https://github.com/dotdotgod/dotdotgod-kit/tree/main/packages/context), and the [maintained execution contract](https://github.com/dotdotgod/dotdotgod-kit/blob/main/docs/spec/CONTEXT_EXECUTION.md) for the complete runtime behavior.
+The MCP `index` tool accepts project-contained files or bounded directories with deterministic traversal, configurable resource limits, explicit extension/path exclusions, and symlinks skipped by default. These capture and retrieval rules apply when Claude calls the dotdotgod MCP tools; Claude Code's built-in Bash tool keeps its native behavior. URL indexing performs application-level HTTP(S), DNS/address, connected-peer, redirect, and byte-limit validation. Accepted HTML is normalized as bounded untrusted text without browser rendering, JavaScript, subresource loading, or link following by default. The server bundles no browser renderer, so browser opt-in fails unless a host injects that capability. These controls are not a network sandbox or complete prompt-injection prevention. See the [`@dotdotgod/context` npm package](https://www.npmjs.com/package/@dotdotgod/context), its [GitHub README](https://github.com/dotdotgod/dotdotgod-kit/tree/main/packages/context), and the [maintained execution contract](https://github.com/dotdotgod/dotdotgod-kit/blob/main/docs/spec/CONTEXT_EXECUTION.md) for the complete runtime behavior.
 Bundled hooks mark project load as required at session start, record successful source/config edits, and deny broad verification or handoff commands until matching graph impact succeeds. Denial asks Claude to call the required MCP tool and retry; hooks do not silently change one tool type into another. See [`hooks/README.md`](https://github.com/dotdotgod/dotdotgod-kit/blob/main/packages/claude-code/hooks/README.md) for lifecycle and trust boundaries.
@@ -85,6 +93,6 @@ pnpm --filter @dotdotgod/claude-code run pack:dry-run
 See the [root README](https://github.com/dotdotgod/dotdotgod-kit#readme), [Context curation](https://github.com/dotdotgod/dotdotgod-kit/blob/main/docs/concept/CONTEXT_CURATION.md), [Context mechanics](https://github.com/dotdotgod/dotdotgod-kit/blob/main/docs/concept/CONTEXT_MECHANICS.md), [Memory area config](https://github.com/dotdotgod/dotdotgod-kit/blob/main/docs/spec/MEMORY_AREA_CONFIG.md), and [Traceability config](https://github.com/dotdotgod/dotdotgod-kit/blob/main/docs/spec/TRACEABILITY_CONFIG.md).
-## Compared with Graphify-Style Memory
+## Workflow Model
-This adapter is guidance-oriented. It asks Claude Code to prefer a depth-bounded documentation map with optional focused local query, avoid broad archive scans, and follow README indexes before reading raw files. The strength is structured retrieval from maintained project docs, not a giant graph report.
+The adapter connects Claude Code's commands, skills, MCP tools, and hooks to the same maintained project memory used by other agents. README indexes route focused reads, durable plans preserve intent, and graph impact supplies related evidence for review.

package/commands/dd/init.md CHANGED Viewed

@@ -34,7 +34,7 @@ Create a non-destructive dotdotgod baseline with canonical agent instructions, t
 ## Workflow
 1. Preserve existing files and unrelated user work.
-2. Run `dotdotgod init <project-root> --template <name>` when available; otherwise run `sh "${CLAUDE_PLUGIN_ROOT}/skills/project-initializer/scripts/init_project.sh" <project-root> --template <name>`. Existing files must be skipped, not replaced.
+2. Run `dotdotgod init <project-root> [--documentation-root PATH] --template <name>` when available; otherwise run `sh "${CLAUDE_PLUGIN_ROOT}/skills/project-initializer/scripts/init_project.sh" <project-root> --template <name>`. Existing files must be skipped, not replaced.
 3. The POSIX fallback supports bundled templates only. If a custom template was selected and the CLI is unavailable, stop and explain that custom templates require the CLI; do not silently substitute another template.
 4. Validate the initialized project with `dotdotgod validate <project-root>` when available.
 5. Report created and skipped files, the selected template, validation failures, and unresolved instruction conflicts.

package/hooks/README.md CHANGED Viewed

@@ -25,7 +25,7 @@ Claude Code currently does not document dedicated plan-mode transition hooks suc
 Hook handlers may be `command`, `http`, `mcp_tool`, `prompt`, or `agent`, with event-specific support limits. `SessionStart` and `Setup` support only `command` and `mcp_tool`. For project or plugin scripts, prefer command exec form with `args` so `${CLAUDE_PROJECT_DIR}`, `${CLAUDE_PLUGIN_ROOT}`, and `${CLAUDE_PLUGIN_DATA}` paths are passed without shell quoting. Hooks should not write directly to `/dev/tty`; use JSON `systemMessage` for user-visible messages or Claude Code's `terminalSequence` field for terminal notifications.
-Claude Code plugins can package hook config at `hooks/hooks.json` or through the plugin manifest. Dotdotgod intentionally does not ship a default hook config today: `/dd:impact` and the `impact-review` skill provide the Pi-like changed-file review path without adding automatic local command execution. If a future release adds packaged hooks, they should be advisory, fast, and clearly documented as opt-in or safe defaults.
+Claude Code plugins can package hook config at `hooks/hooks.json` or through the plugin manifest. Dotdotgod ships `hooks/hooks.json` with bounded load-required and impact-pending routing. The hooks run local commands with user permissions, so users should review the packaged resources through Claude Code's plugin trust flow. `/dd:impact` and the `impact-review` skill remain explicit ways to request the same changed-file review workflow.
 ## SDLC Guardrail Framing

package/package.json CHANGED Viewed

@@ -1,6 +1,6 @@
 {
   "name": "@dotdotgod/claude-code",
-  "version": "0.2.27",
+  "version": "0.3.0",
   "description": "Claude Code adapter for dotdotgod project memory workflows.",
   "type": "module",
   "license": "Elastic-2.0",
@@ -21,7 +21,7 @@
     "traceability"
   ],
   "dependencies": {
-    "@dotdotgod/context": "0.2.27"
+    "@dotdotgod/context": "0.3.0"
   },
   "files": [
     ".claude-plugin",

package/skills/project-initializer/SKILL.md CHANGED Viewed

@@ -30,7 +30,7 @@ Create a non-destructive dotdotgod baseline with canonical agent instructions, t
 ## Workflow
 1. Preserve existing files and unrelated user work.
-2. Run `dotdotgod init <project-root> --template <name>` when available; otherwise run `sh "${CLAUDE_PLUGIN_ROOT}/skills/project-initializer/scripts/init_project.sh" <project-root> --template <name>`. Existing files must be skipped, not replaced.
+2. Run `dotdotgod init <project-root> [--documentation-root PATH] --template <name>` when available; otherwise run `sh "${CLAUDE_PLUGIN_ROOT}/skills/project-initializer/scripts/init_project.sh" <project-root> --template <name>`. Existing files must be skipped, not replaced.
 3. The POSIX fallback supports bundled templates only. If a custom template was selected and the CLI is unavailable, stop and explain that custom templates require the CLI; do not silently substitute another template.
 4. Validate the initialized project with `dotdotgod validate <project-root>` when available.
 5. Report created and skipped files, the selected template, validation failures, and unresolved instruction conflicts.

package/skills/project-initializer/scripts/init_project.sh CHANGED Viewed

@@ -6,7 +6,7 @@ TEMPLATES_DIR="$SCRIPT_DIR/../templates"
 usage() {
   cat <<'EOF'
-Usage: init_project.sh <project-root> [--project-name NAME] [--template NAME] [--dotdot-setting] [--dry-run]
+Usage: init_project.sh <project-root> [--project-name NAME] [--template NAME] [--documentation-root PATH] [--dotdot-setting] [--dry-run]
 Initializes:
   AGENTS.md, CLAUDE.md, CODEX.md
@@ -26,6 +26,7 @@ PROJECT_NAME=""
 DRY_RUN=0
 DOTDOT_SETTING=0
 TEMPLATE_NAME="software"
+DOCUMENTATION_ROOT="docs"
 while [ "$#" -gt 0 ]; do
   case "$1" in
@@ -45,6 +46,11 @@ while [ "$#" -gt 0 ]; do
       TEMPLATE_NAME=$2
       shift 2
       ;;
+    --documentation-root)
+      [ "$#" -ge 2 ] || { echo "error: --documentation-root requires a value" >&2; exit 2; }
+      DOCUMENTATION_ROOT=$2
+      shift 2
+      ;;
     --dotdot-setting)
       DOTDOT_SETTING=1
       shift
@@ -84,6 +90,14 @@ case "$PROJECT_ROOT" in
   *) PROJECT_ROOT="$(pwd)/$PROJECT_ROOT" ;;
 esac
+case "$DOCUMENTATION_ROOT" in
+  ''|/*|*\\*|*'..'*|*'*'*|*'?'*|*'['*|*']'*|*'{'*|*'}'*|.dotdotgod*|dotdotgod.config.json*)
+    echo "error: invalid documentation root: $DOCUMENTATION_ROOT" >&2
+    exit 2
+    ;;
+esac
+DOCUMENTATION_ROOT=$(printf '%s' "$DOCUMENTATION_ROOT" | sed 's#^\./##; s#//*#/#g; s#/$##')
 if [ -z "$PROJECT_NAME" ]; then
   PROJECT_NAME=$(basename "$PROJECT_ROOT")
 fi
@@ -184,7 +198,7 @@ fi
 DOTDOT_AGENT_RULE=""
 if [ "$DOTDOT_SETTING" -eq 1 ]; then
   DOTDOT_AGENT_RULE='
-- Follow the project documentation structure in `docs/arch/DOCS_STRUCTURE.md` and code conventions in `docs/arch/CODE_CONVENTIONS.md`.'
+- Follow the project documentation structure in `$DOCUMENTATION_ROOT/arch/DOCS_STRUCTURE.md` and code conventions in `$DOCUMENTATION_ROOT/arch/CODE_CONVENTIONS.md`.'
 fi
 ARCH_README_EXTRA=""
@@ -239,17 +253,17 @@ TODO
 ## Documentation Map
-- \`docs/spec/\`: product behavior, API contracts, user-facing requirements.
-- \`docs/test/\`: test strategy, regression cases, manual verification notes.
-- \`docs/arch/\`: architecture decisions, code conventions, module boundaries, data flow, infrastructure/runtime dependencies, integration boundaries, and migration design.
-- \`docs/\`: all directories use kebab-case; all markdown file names use UPPER_SNAKE_CASE, including \`README.md\`.
-- \`docs/\`: prefer keeping individual markdown files under 200 lines and under 10,000 characters; split larger docs into focused UPPER_SNAKE_CASE files and keep \`README.md\` as the index/overview.
-- \`docs/\`: when adding, renaming, splitting, moving, or archiving docs, update the nearest relevant \`README.md\` index/table of contents in the same change.
-- \`docs/\`: each docs subdirectory \`README.md\` acts as the local table of contents; list important files, task directories, status, and a one-line purpose for each entry.
-- \`docs/\`: start small with a single focused markdown file; when one domain grows into multiple docs, promote it to \`docs/<area>/<domain>/README.md\` plus related UPPER_SNAKE_CASE files in that directory.
-- \`docs/arch/\`: code conventions may start as \`CODE_CONVENTIONS.md\`; when they grow across multiple topics, use \`docs/arch/conventions/README.md\` as the index with supporting UPPER_SNAKE_CASE files.
-- \`docs/plan/\`: local active implementation plans. Create one kebab-case directory per task (\`docs/plan/<task-slug>/\`), keep the task overview/index in that directory's \`README.md\`, and add supporting UPPER_SNAKE_CASE plan files alongside it. Ignored by git by default.
-- \`docs/archive/\`: local completed plans, temporary reports, historical notes, payload captures. Move completed plan task directories to \`docs/archive/plan/<task-slug>/\`; put temporary reports and investigations under \`docs/archive/report/<report-slug>/\`. Ignored by git by default.
+- \`$DOCUMENTATION_ROOT/spec/\`: product behavior, API contracts, user-facing requirements.
+- \`$DOCUMENTATION_ROOT/test/\`: test strategy, regression cases, manual verification notes.
+- \`$DOCUMENTATION_ROOT/arch/\`: architecture decisions, code conventions, module boundaries, data flow, infrastructure/runtime dependencies, integration boundaries, and migration design.
+- \`$DOCUMENTATION_ROOT/\`: all directories use kebab-case; all markdown file names use UPPER_SNAKE_CASE, including \`README.md\`.
+- \`$DOCUMENTATION_ROOT/\`: prefer keeping individual markdown files under 200 lines and under 10,000 characters; split larger docs into focused UPPER_SNAKE_CASE files and keep \`README.md\` as the index/overview.
+- \`$DOCUMENTATION_ROOT/\`: when adding, renaming, splitting, moving, or archiving docs, update the nearest relevant \`README.md\` index/table of contents in the same change.
+- \`$DOCUMENTATION_ROOT/\`: each docs subdirectory \`README.md\` acts as the local table of contents; list important files, task directories, status, and a one-line purpose for each entry.
+- \`$DOCUMENTATION_ROOT/\`: start small with a single focused markdown file; when one domain grows into multiple docs, promote it to \`$DOCUMENTATION_ROOT/<area>/<domain>/README.md\` plus related UPPER_SNAKE_CASE files in that directory.
+- \`$DOCUMENTATION_ROOT/arch/\`: code conventions may start as \`CODE_CONVENTIONS.md\`; when they grow across multiple topics, use \`$DOCUMENTATION_ROOT/arch/conventions/README.md\` as the index with supporting UPPER_SNAKE_CASE files.
+- \`$DOCUMENTATION_ROOT/plan/\`: local active implementation plans. Create one kebab-case directory per task (\`$DOCUMENTATION_ROOT/plan/<task-slug>/\`), keep the task overview/index in that directory's \`README.md\`, and add supporting UPPER_SNAKE_CASE plan files alongside it. Ignored by git by default.
+- \`$DOCUMENTATION_ROOT/archive/\`: local completed plans, temporary reports, historical notes, payload captures. Move completed plan task directories to \`$DOCUMENTATION_ROOT/archive/plan/<task-slug>/\`; put temporary reports and investigations under \`$DOCUMENTATION_ROOT/archive/report/<report-slug>/\`. Ignored by git by default.
 ## Agent-Specific Entrypoints
@@ -266,21 +280,21 @@ write_file "$PROJECT_ROOT/CODEX.md" "# CODEX.md
 See [AGENTS.md](./AGENTS.md)."
-write_file "$PROJECT_ROOT/docs/README.md" "# Docs
+write_file "$PROJECT_ROOT/$DOCUMENTATION_ROOT/README.md" "# Docs
 This directory keeps project knowledge close to the code.
 ## Naming
-- All directories under \`docs/\` use kebab-case.
-- All markdown file names under \`docs/\` use UPPER_SNAKE_CASE, including \`README.md\`.
+- All directories under \`$DOCUMENTATION_ROOT/\` use kebab-case.
+- All markdown file names under \`$DOCUMENTATION_ROOT/\` use UPPER_SNAKE_CASE, including \`README.md\`.
 - Prefer keeping individual markdown files under 200 lines and under 10,000 characters; split larger docs into focused UPPER_SNAKE_CASE files and keep \`README.md\` as the index/overview.
 ## Indexing
 - When adding, renaming, splitting, moving, or archiving docs, update the nearest relevant \`README.md\` index/table of contents in the same change.
 - Each docs subdirectory \`README.md\` acts as the local table of contents; list important files, task directories, status, and a one-line purpose for each entry.
-- Start small with a single focused markdown file; when one domain grows into multiple docs, promote it to \`docs/<area>/<domain>/README.md\` plus related UPPER_SNAKE_CASE files in that directory.
+- Start small with a single focused markdown file; when one domain grows into multiple docs, promote it to \`$DOCUMENTATION_ROOT/<area>/<domain>/README.md\` plus related UPPER_SNAKE_CASE files in that directory.
 ## Map
@@ -290,37 +304,37 @@ This directory keeps project knowledge close to the code.
 - \`plan/\`: local active implementation plans. Create one kebab-case directory per task (\`plan/<task-slug>/\`), keep the task overview/index in that directory's \`README.md\`, and add supporting UPPER_SNAKE_CASE plan files alongside it. Ignored by git by default.
 - \`archive/\`: local completed plans, temporary reports, historical notes, payload captures. Move completed plan task directories to \`archive/plan/<task-slug>/\`; put temporary reports and investigations under \`archive/report/<report-slug>/\`. Ignored by git by default."
-write_file "$PROJECT_ROOT/docs/spec/README.md" "# Specs
+write_file "$PROJECT_ROOT/$DOCUMENTATION_ROOT/spec/README.md" "# Specs
 Use this area for behavior specs, API contracts, and product requirements.
 For projects using the dotdotgod CLI, behavior specs may be required by \`dotdotgod validate\` to include fenced \`json dotdotgod\` traceability blocks as the final section. The CLI owns the schema and prints property-level repair guidance when validation fails."
-write_file "$PROJECT_ROOT/docs/test/README.md" "# Tests
+write_file "$PROJECT_ROOT/$DOCUMENTATION_ROOT/test/README.md" "# Tests
 Use this area for test strategy, coverage notes, regression cases, and manual verification records."
-write_file "$PROJECT_ROOT/docs/arch/README.md" "# Architecture
+write_file "$PROJECT_ROOT/$DOCUMENTATION_ROOT/arch/README.md" "# Architecture
 Use this area for architecture decisions, code conventions, module boundaries, data flow notes, infrastructure/runtime dependencies, integration boundaries, and migration design.$ARCH_README_EXTRA"
 if [ "$DOTDOT_SETTING" -eq 1 ]; then
-  write_file "$PROJECT_ROOT/docs/arch/DOCS_STRUCTURE.md" "# Docs Structure
+  write_file "$PROJECT_ROOT/$DOCUMENTATION_ROOT/arch/DOCS_STRUCTURE.md" "# Docs Structure
 Long-term documentation structure for this project.
 ## Top-Level Areas
-- \`docs/spec/\`: product behavior, API contracts, user-facing requirements, and feature contracts.
-- \`docs/test/\`: test strategy, coverage notes, regression cases, and manual verification records.
-- \`docs/arch/\`: architecture decisions, code conventions, module boundaries, data flow, infrastructure/runtime dependencies, integration boundaries, and migration design.
-- \`docs/plan/\`: local active implementation plans.
-- \`docs/archive/\`: local completed plans, historical notes, payload captures, and investigation notes.
+- \`$DOCUMENTATION_ROOT/spec/\`: product behavior, API contracts, user-facing requirements, and feature contracts.
+- \`$DOCUMENTATION_ROOT/test/\`: test strategy, coverage notes, regression cases, and manual verification records.
+- \`$DOCUMENTATION_ROOT/arch/\`: architecture decisions, code conventions, module boundaries, data flow, infrastructure/runtime dependencies, integration boundaries, and migration design.
+- \`$DOCUMENTATION_ROOT/plan/\`: local active implementation plans.
+- \`$DOCUMENTATION_ROOT/archive/\`: local completed plans, historical notes, payload captures, and investigation notes.
 ## Naming
-- Directories under \`docs/\` use kebab-case.
-- Markdown files under \`docs/\` use UPPER_SNAKE_CASE.
+- Directories under \`$DOCUMENTATION_ROOT/\` use kebab-case.
+- Markdown files under \`$DOCUMENTATION_ROOT/\` use UPPER_SNAKE_CASE.
 - \`README.md\` is the only mixed-case markdown filename exception and is required for index/overview files.
 ## File Size Guideline
@@ -335,13 +349,13 @@ When adding, renaming, splitting, moving, or archiving docs, update the nearest
 ## Domain Directory Promotion
-Start small with one focused markdown file. When one domain grows into multiple docs, promote it to \`docs/<area>/<domain>/README.md\` and place related UPPER_SNAKE_CASE markdown files in that directory.
+Start small with one focused markdown file. When one domain grows into multiple docs, promote it to \`$DOCUMENTATION_ROOT/<area>/<domain>/README.md\` and place related UPPER_SNAKE_CASE markdown files in that directory.
 ## Spec Writing Contract
 Behavior specs describe the current product contract: supported commands, API shapes, user-visible behavior, defaults, constraints, and validation outcomes.
-Specs should not describe how behavior changed over time. Rewrite historical-change wording into direct current-state rules. Historical context, migration rationale, future extension ideas, and completed-plan notes belong in \`docs/arch/\`, \`docs/test/\`, \`docs/archive/\`, or active \`docs/plan/\` files rather than behavior specs. If compatibility behavior is still user-visible, keep it in the spec but phrase it as a current supported or unsupported rule.
+Specs should not describe how behavior changed over time. Rewrite historical-change wording into direct current-state rules. Historical context, migration rationale, future extension ideas, and completed-plan notes belong in \`$DOCUMENTATION_ROOT/arch/\`, \`$DOCUMENTATION_ROOT/test/\`, \`$DOCUMENTATION_ROOT/archive/\`, or active \`$DOCUMENTATION_ROOT/plan/\` files rather than behavior specs. If compatibility behavior is still user-visible, keep it in the spec but phrase it as a current supported or unsupported rule.
 Config/action terms such as \`remove\`, \`exclude\`, \`fallback\`, and \`replacement semantics\` are allowed when they name current behavior precisely.
@@ -351,12 +365,12 @@ Behavior specs may include fenced \`json dotdotgod\` traceability blocks as the
 ## Plan and Archive Directories
-Active task plans use \`docs/plan/<task-slug>/README.md\`. Completed or superseded plan task directories move to \`docs/archive/plan/<task-slug>/\`. Temporary investigations, reports, payload captures, and historical notes move to \`docs/archive/report/<report-slug>/\`.
+Active task plans use \`$DOCUMENTATION_ROOT/plan/<task-slug>/README.md\`. Completed or superseded plan task directories move to \`$DOCUMENTATION_ROOT/archive/plan/<task-slug>/\`. Temporary investigations, reports, payload captures, and historical notes move to \`$DOCUMENTATION_ROOT/archive/report/<report-slug>/\`.
-\`docs/plan\` and \`docs/archive\` are ignored by git by default.
+\`$DOCUMENTATION_ROOT/plan\` and \`$DOCUMENTATION_ROOT/archive\` are ignored by git by default.
 "
-  write_file "$PROJECT_ROOT/docs/arch/CODE_CONVENTIONS.md" "# Code Conventions
+  write_file "$PROJECT_ROOT/$DOCUMENTATION_ROOT/arch/CODE_CONVENTIONS.md" "# Code Conventions
 Dotdot code conventions for keeping implementation simple and maintainable.
@@ -389,25 +403,25 @@ Dotdot code conventions for keeping implementation simple and maintainable.
 "
 fi
-write_file "$PROJECT_ROOT/docs/plan/README.md" "# Plans
+write_file "$PROJECT_ROOT/$DOCUMENTATION_ROOT/plan/README.md" "# Plans
 Use this area for active implementation plans.
 ## Naming
-- Task directories use kebab-case: \`docs/plan/<task-slug>/\`.
+- Task directories use kebab-case: \`$DOCUMENTATION_ROOT/plan/<task-slug>/\`.
 - Markdown file names use UPPER_SNAKE_CASE: \`README.md\`, \`RESEARCH_NOTES.md\`, \`VERIFICATION.md\`.
 ## Structure
-- Create one directory per task: \`docs/plan/<task-slug>/\`.
-- Put the task overview, index, scope, status, and main plan in \`docs/plan/<task-slug>/README.md\`.
+- Create one directory per task: \`$DOCUMENTATION_ROOT/plan/<task-slug>/\`.
+- Put the task overview, index, scope, status, and main plan in \`$DOCUMENTATION_ROOT/plan/<task-slug>/README.md\`.
 - Add supporting research, checklists, payload captures, or verification notes as additional UPPER_SNAKE_CASE markdown files in the same task directory.
-- Move completed or superseded task directories to \`docs/archive/plan/<task-slug>/\`.
+- Move completed or superseded task directories to \`$DOCUMENTATION_ROOT/archive/plan/<task-slug>/\`.
 This directory is local-only and ignored by git by default."
-write_file "$PROJECT_ROOT/docs/archive/README.md" "# Archive
+write_file "$PROJECT_ROOT/$DOCUMENTATION_ROOT/archive/README.md" "# Archive
 Use this area for local completed plans, temporary reports, historical notes, payload captures, and investigation notes.
@@ -419,8 +433,8 @@ Use this area for local completed plans, temporary reports, historical notes, pa
 ## Structure
-- Move completed plan task directories from \`docs/plan/<task-slug>/\` to \`docs/archive/plan/<task-slug>/\`.
-- Put temporary investigations, reports, payload captures, and historical notes under \`docs/archive/report/<report-slug>/\`.
+- Move completed plan task directories from \`$DOCUMENTATION_ROOT/plan/<task-slug>/\` to \`$DOCUMENTATION_ROOT/archive/plan/<task-slug>/\`.
+- Put temporary investigations, reports, payload captures, and historical notes under \`$DOCUMENTATION_ROOT/archive/report/<report-slug>/\`.
 - Preserve each archive directory's \`README.md\` overview/index and supporting UPPER_SNAKE_CASE markdown files.
 - Additional archive categories can be added later as focused kebab-case subdirectories when needed.
@@ -431,69 +445,69 @@ case "$TEMPLATE_NAME" in
   software)
     ;;
   research)
-    write_file "$PROJECT_ROOT/docs/research/README.md" "# Research
+    write_file "$PROJECT_ROOT/$DOCUMENTATION_ROOT/research/README.md" "# Research
 Use this area for research notes, sources, and findings."
-    write_file "$PROJECT_ROOT/docs/record/README.md" "# Research Records
+    write_file "$PROJECT_ROOT/$DOCUMENTATION_ROOT/record/README.md" "# Research Records
 Use this area for dated measurements, experiments, and execution records."
-    write_file "$PROJECT_ROOT/docs/report/README.md" "# Reports
+    write_file "$PROJECT_ROOT/$DOCUMENTATION_ROOT/report/README.md" "# Reports
 Use this area for research diagnoses, analyses, results, and performance reports."
     ensure_directory "$PROJECT_ROOT/outputs"
     ;;
   case-and-evidence)
-    write_file "$PROJECT_ROOT/docs/case/README.md" "# Case Records
+    write_file "$PROJECT_ROOT/$DOCUMENTATION_ROOT/case/README.md" "# Case Records
 Use this area for canonical case facts, questions, and decisions."
-    write_file "$PROJECT_ROOT/docs/evidence/README.md" "# Evidence
+    write_file "$PROJECT_ROOT/$DOCUMENTATION_ROOT/evidence/README.md" "# Evidence
 Use this area for factual, legal, and other supporting evidence."
-    write_file "$PROJECT_ROOT/docs/outputs/README.md" "# Case Outputs
+    write_file "$PROJECT_ROOT/$DOCUMENTATION_ROOT/outputs/README.md" "# Case Outputs
 Use this area for maintained case outputs."
     ;;
   publication)
-    write_file "$PROJECT_ROOT/docs/outline/README.md" "# Publication Outline
+    write_file "$PROJECT_ROOT/$DOCUMENTATION_ROOT/outline/README.md" "# Publication Outline
 Use this area for publication structure and outlines."
-    write_file "$PROJECT_ROOT/docs/chapters/README.md" "# Chapter Plans
+    write_file "$PROJECT_ROOT/$DOCUMENTATION_ROOT/chapters/README.md" "# Chapter Plans
 Use this area for chapter plans and direction."
-    write_file "$PROJECT_ROOT/docs/claims/README.md" "# Claims
+    write_file "$PROJECT_ROOT/$DOCUMENTATION_ROOT/claims/README.md" "# Claims
 Use this area for maintained claims and their support."
-    write_file "$PROJECT_ROOT/docs/research/README.md" "# Research Sources
+    write_file "$PROJECT_ROOT/$DOCUMENTATION_ROOT/research/README.md" "# Research Sources
 Use this area for research sources and supporting notes."
     ensure_directory "$PROJECT_ROOT/book"
     ;;
   portfolio)
-    write_file "$PROJECT_ROOT/docs/strategy/README.md" "# Portfolio Strategy
+    write_file "$PROJECT_ROOT/$DOCUMENTATION_ROOT/strategy/README.md" "# Portfolio Strategy
 Use this area for portfolio strategy and risk rules."
-    write_file "$PROJECT_ROOT/docs/positions/README.md" "# Position Theses
+    write_file "$PROJECT_ROOT/$DOCUMENTATION_ROOT/positions/README.md" "# Position Theses
 Use this area for position theses and investment conclusions."
-    write_file "$PROJECT_ROOT/docs/journal/README.md" "# Decision Journal
+    write_file "$PROJECT_ROOT/$DOCUMENTATION_ROOT/journal/README.md" "# Decision Journal
 Use this area for dated investment decisions and reviews."
-    write_file "$PROJECT_ROOT/docs/report/README.md" "# Market Research
+    write_file "$PROJECT_ROOT/$DOCUMENTATION_ROOT/report/README.md" "# Market Research
 Use this area for maintained market research and analysis."
     ensure_directory "$PROJECT_ROOT/data"
     ;;
   policy)
-    write_file "$PROJECT_ROOT/docs/policy/README.md" "# Policy Documents
+    write_file "$PROJECT_ROOT/$DOCUMENTATION_ROOT/policy/README.md" "# Policy Documents
 Use this area for integrated policy proposals and outputs."
-    write_file "$PROJECT_ROOT/docs/sections/README.md" "# Policy Sections
+    write_file "$PROJECT_ROOT/$DOCUMENTATION_ROOT/sections/README.md" "# Policy Sections
 Use this area for source policy sections."
-    write_file "$PROJECT_ROOT/docs/evidence/README.md" "# Policy Evidence
+    write_file "$PROJECT_ROOT/$DOCUMENTATION_ROOT/evidence/README.md" "# Policy Evidence
 Use this area for evidence supporting policy proposals."
-    write_file "$PROJECT_ROOT/docs/outputs/README.md" "# Submission Outputs
+    write_file "$PROJECT_ROOT/$DOCUMENTATION_ROOT/outputs/README.md" "# Submission Outputs
 Use this area for maintained policy submission outputs."
     ;;
@@ -503,9 +517,9 @@ fi
 if [ -e "$CONFIG_PATH" ]; then
   print_result "skipped" "$CONFIG_PATH"
 else
-  write_file "$CONFIG_PATH" "$(cat "$CONFIG_TEMPLATE")"
+  write_file "$CONFIG_PATH" "$(sed 's#"root": "docs"#"root": "'$DOCUMENTATION_ROOT'"#; s#"docs/#"'$DOCUMENTATION_ROOT'/#g' "$CONFIG_TEMPLATE")"
 fi
-ensure_gitignore_entry "docs/plan"
-ensure_gitignore_entry "docs/archive"
+ensure_gitignore_entry "$DOCUMENTATION_ROOT/plan"
+ensure_gitignore_entry "$DOCUMENTATION_ROOT/archive"
 ensure_gitignore_entry ".dotdotgod"

package/skills/project-initializer/templates/case-and-evidence.json CHANGED Viewed

@@ -1,4 +1,7 @@
 {
+  "documentation": {
+    "root": "docs"
+  },
   "memory": {
     "areas": [
       {

package/skills/project-initializer/templates/dotdotgod.config.json CHANGED Viewed

@@ -1,4 +1,7 @@
 {
+  "documentation": {
+    "root": "docs"
+  },
   "memory": {
     "areas": [
       {

package/skills/project-initializer/templates/policy.json CHANGED Viewed

@@ -1,4 +1,7 @@
 {
+  "documentation": {
+    "root": "docs"
+  },
   "memory": {
     "areas": [
       {

package/skills/project-initializer/templates/portfolio.json CHANGED Viewed

@@ -1,4 +1,7 @@
 {
+  "documentation": {
+    "root": "docs"
+  },
   "memory": {
     "areas": [
       {

package/skills/project-initializer/templates/publication.json CHANGED Viewed

@@ -1,4 +1,7 @@
 {
+  "documentation": {
+    "root": "docs"
+  },
   "memory": {
     "areas": [
       {

package/skills/project-initializer/templates/research.json CHANGED Viewed

@@ -1,4 +1,7 @@
 {
+  "documentation": {
+    "root": "docs"
+  },
   "memory": {
     "areas": [
       {

package/skills/project-initializer/templates/software.json CHANGED Viewed

@@ -1,4 +1,7 @@
 {
+  "documentation": {
+    "root": "docs"
+  },
   "memory": {
     "areas": [
       {