@draht/coding-agent 2026.3.4 → 2026.3.5

package/dist/prompts/agents/build.md

@@ -1,6 +1,10 @@
+---
+description: "Execution agent that implements plans precisely"
+---
+
 # Draht Build Agent
 
-You are an execution agent for the Get Shit Done methodology. Your job is to implement plans precisely.
+You are an execution agent. Your job is to implement plans precisely.
 
 ## Core Rules
 1. Read the plan FIRST — it is your instruction set

package/dist/prompts/agents/plan.md

@@ -1,6 +1,10 @@
+---
+description: "Planning agent that creates atomic, executable plans"
+---
+
 # Draht Plan Agent
 
-You are a planning agent for the Get Shit Done methodology. Your job is to create atomic, executable plans.
+You are a planning agent. Your job is to create atomic, executable plans.
 
 ## Core Rules
 1. Plans are prompts — they tell the executor EXACTLY what to build

package/dist/prompts/agents/verify.md

@@ -1,6 +1,10 @@
+---
+description: "Verification agent that tests work against acceptance criteria"
+---
+
 # Draht Verify Agent
 
-You are a verification agent for the Get Shit Done methodology. Your job is to test completed work against acceptance criteria.
+You are a verification agent. Your job is to test completed work against acceptance criteria.
 
 ## Core Rules
 1. Test from the USER's perspective, not the developer's

package/dist/prompts/commands/atomic-commit.md

@@ -4,19 +4,13 @@ description: "Analyze changes and create atomic commits"
 
 # Git Atomic Commit Analysis
 
-First, check the current status:
+First, gather the current state:
 
-*! git status*
+1. Run `git status` to see what changed
+2. Run `git diff` to see unstaged changes
+3. Run `git diff --cached` to see staged changes
 
-Now get the full diff of all changes:
-
-*! git diff*
-
-And staged changes:
-
-*! git diff --cached*
-
-Based on the changes shown above, analyze and group them into logical, ATOMIC commits. Each commit should:
+Based on the changes, analyze and group them into logical, ATOMIC commits. Each commit should:
 
 1. Contain ONE logical change only
 2. Be self-contained and complete
@@ -27,13 +21,11 @@ For each group of changes you identify:
 - Generate a clear, descriptive commit message following conventional commits format
 - Explain WHY these changes belong in one commit
 
-Then provide the exact `git add` and `git commit` commands to execute for each atomic commit in the order they should be applied.
+Then execute the `git add` and `git commit` commands for each atomic commit in the order they should be applied.
 
 Format each commit message as:
+```
 type(scope): brief description
-- Detailed explanation of what changed
-- Why the change was necessary
-
+```
 
 Common types: feat, fix, refactor, docs, test, chore, style, perf
-

package/dist/prompts/commands/discuss-phase.md

@@ -1,3 +1,7 @@
+---
+description: "Capture implementation decisions before planning a phase"
+---
+
 # /discuss-phase
 
 Capture implementation decisions before planning a phase.
@@ -7,13 +11,15 @@ Capture implementation decisions before planning a phase.
 /discuss-phase [N]
 ```
 
+Phase: $1
+
 ## Steps
-1. Run `draht-tools phase-info N` to load phase context
+1. Run `draht-tools phase-info $1` to load phase context
 2. Identify gray areas based on what's being built
 3. Present 1-2 questions at a time about preferences
 4. If `.planning/DOMAIN.md` exists, load it and validate discovered terms against the glossary. Add any new domain terms found during discussion.
-5. Record decisions with `draht-tools save-context N`
-6. Commit: `draht-tools commit-docs "capture phase N context"`
+5. Record decisions with `draht-tools save-context $1`
+6. Commit: `draht-tools commit-docs "capture phase $1 context"`
 
 ## Gray Area Categories
 - **Visual features** → Layout, density, interactions, empty states

package/dist/prompts/commands/execute-phase.md

@@ -1,3 +1,7 @@
+---
+description: "Execute all plans in a phase with atomic commits"
+---
+
 # /execute-phase
 
 Execute all plans in a phase with atomic commits.
@@ -7,37 +11,40 @@ Execute all plans in a phase with atomic commits.
 /execute-phase [N] [--gaps-only]
 ```
 
+Phase: $1
+Arguments: $ARGUMENTS
+
 ## Steps
-1. Run `draht-tools discover-plans N` to find and order plans
+1. Run `draht-tools discover-plans $1` to find and order plans
 2. For each plan in dependency order:
-   a. Load plan: `draht-tools read-plan N P`
+   a. Load plan: `draht-tools read-plan $1 P`
    b. Execute each task in strict TDD cycle:
 
       **🔴 RED — Write failing tests first**
       - Write the test cases from `<test>`
       - Run tests — confirm they FAIL (if they pass, the test is wrong)
-      - Commit failing tests: `draht-tools commit-task N P T "red: test description"`
+      - Commit failing tests: `draht-tools commit-task $1 P T "red: test description"`
 
       **🟢 GREEN — Minimal implementation**
       - Write the minimum code from `<action>` to make tests pass
       - Use domain language from `<context>` and `<domain>` for all names
       - Run tests — confirm they PASS
-      - Commit: `draht-tools commit-task N P T "green: task name"`
+      - Commit: `draht-tools commit-task $1 P T "green: task name"`
 
       **🔵 REFACTOR — Clean up with safety net**
       - Apply improvements from `<refactor>` (if any)
       - Run tests after each change — must stay green
       - Verify domain language compliance (names match DOMAIN.md)
-      - Commit: `draht-tools commit-task N P T "refactor: description"`
+      - Commit: `draht-tools commit-task $1 P T "refactor: description"`
 
       **✅ VERIFY**
       - Run the `<verify>` step
       - Confirm `<done>` criteria met
 
-   c. Write summary: `draht-tools write-summary N P`
-3. Phase verification: `draht-tools verify-phase N`
+   c. Write summary: `draht-tools write-summary $1 P`
+3. Phase verification: `draht-tools verify-phase $1`
 4. Update state: `draht-tools update-state`
-5. Final commit: `draht-tools commit-docs "complete phase N execution"`
+5. Final commit: `draht-tools commit-docs "complete phase $1 execution"`
 
 ## TDD Rules
 - Never write implementation before a failing test exists

package/dist/prompts/commands/fix.md

@@ -1,3 +1,7 @@
+---
+description: "Diagnose and fix a bug with TDD discipline"
+---
+
 # /fix
 
 Diagnose and fix a specific bug or failing task with TDD discipline.
@@ -7,6 +11,8 @@ Diagnose and fix a specific bug or failing task with TDD discipline.
 /fix [description of what's broken]
 ```
 
+Issue: $ARGUMENTS
+
 ## Steps
 1. **Diagnose**: Read the relevant code and error output to identify the root cause
    - If a test is failing, run it first to see the actual error

package/dist/prompts/commands/init-project.md

@@ -1,13 +1,19 @@
+---
+description: "Initialize planning for an existing project"
+---
+
 # /init-project
 
-Initialize GSD planning framework for an existing project: codebase mapping → questioning → domain model → requirements → roadmap.
+Initialize planning framework for an existing project: codebase mapping → questioning → domain model → requirements → roadmap.
 
 ## Usage
 ```
 /init-project [focus area or goal]
 ```
 
-Use this when you have an existing codebase and want to add GSD methodology.
+Focus: $ARGUMENTS
+
+Use this when you have an existing codebase and want to add structured planning.
 For greenfield projects, use `/new-project` instead.
 
 ## Steps
@@ -37,7 +43,7 @@ For greenfield projects, use `/new-project` instead.
 10. Run `draht-tools create-requirements` with v1/v2/out-of-scope (map requirements to bounded contexts)
 11. Run `draht-tools create-roadmap` with phases
 12. Run `draht-tools init-state`
-13. Git commit via `draht-tools commit-docs "initialize GSD planning"`
+13. Git commit via `draht-tools commit-docs "initialize project planning"`
 
 ## Rules
 - Ask 1-2 questions at a time, never dump 10 at once

package/dist/prompts/commands/map-codebase.md

@@ -1,3 +1,7 @@
+---
+description: "Analyze existing codebase before planning"
+---
+
 # /map-codebase
 
 Analyze existing codebase before planning.
@@ -7,8 +11,10 @@ Analyze existing codebase before planning.
 /map-codebase [directory]
 ```
 
+Directory: $1
+
 ## Steps
-1. Run `draht-tools map-codebase [dir]`
+1. Run `draht-tools map-codebase $1`
 2. Tool generates: STACK.md, ARCHITECTURE.md, CONVENTIONS.md, CONCERNS.md
 3. Review output, supplement with your own analysis if needed
 4. Identify implicit bounded contexts from directory structure:

package/dist/prompts/commands/new-project.md

@@ -1,12 +1,18 @@
+---
+description: "Initialize a new project with structured planning"
+---
+
 # /new-project
 
-Initialize a new GSD project: questioning → research → requirements → roadmap.
+Initialize a new project: questioning → research → requirements → roadmap.
 
 ## Usage
 ```
 /new-project [description]
 ```
 
+Description: $ARGUMENTS
+
 ## Steps
 1. Run `draht-tools init` to check preconditions
 2. If existing code detected, run `draht-tools map-codebase` first
@@ -29,7 +35,7 @@ Initialize a new GSD project: questioning → research → requirements → road
 9. Run `draht-tools create-requirements` with v1/v2/out-of-scope (map requirements to bounded contexts)
 10. Run `draht-tools create-roadmap` with phases
 11. Run `draht-tools init-state`
-12. Git commit via `draht-tools commit-docs "initialize GSD project"`
+12. Git commit via `draht-tools commit-docs "initialize project planning"`
 
 ## Rules
 - Ask 1-2 questions at a time, never dump 10 at once

package/dist/prompts/commands/next-milestone.md

@@ -1,3 +1,7 @@
+---
+description: "Plan the next milestone after current one completes"
+---
+
 # /next-milestone
 
 Plan the next milestone after the current one is complete.

package/dist/prompts/commands/pause-work.md

@@ -1,3 +1,7 @@
+---
+description: "Create a handoff document for session continuity"
+---
+
 # /pause-work
 
 Create a handoff document for session continuity.

package/dist/prompts/commands/plan-phase.md

@@ -1,3 +1,7 @@
+---
+description: "Create atomic execution plans for a roadmap phase"
+---
+
 # /plan-phase
 
 Create atomic execution plans for a roadmap phase.
@@ -7,18 +11,20 @@ Create atomic execution plans for a roadmap phase.
 /plan-phase [N]
 ```
 
+Phase: $1
+
 ## Steps
-1. Run `draht-tools load-phase-context N` to gather all context
-2. Optional: `draht-tools research-phase N` for domain research
+1. Run `draht-tools load-phase-context $1` to gather all context
+2. Optional: `draht-tools research-phase $1` for domain research
 3. Goal-backward planning:
    a. State the goal (outcome, not activity)
    b. Derive observable truths (3-7 from user perspective)
    c. From each observable truth, derive the test scenarios that would prove it (specific inputs → expected outputs or state changes)
    d. Map to required artifacts (files, endpoints, schemas)
    e. Break into atomic tasks (2-5 per plan)
-4. Write plans: `draht-tools create-plan N P`
-5. Validate: `draht-tools validate-plans N`
-6. Commit: `draht-tools commit-docs "create phase N plans"`
+4. Write plans: `draht-tools create-plan $1 P`
+5. Validate: `draht-tools validate-plans $1`
+6. Commit: `draht-tools commit-docs "create phase $1 plans"`
 
 ## Plan Format
 Plans use XML task format:

package/dist/prompts/commands/progress.md

@@ -1,3 +1,7 @@
+---
+description: "Show current project status"
+---
+
 # /progress
 
 Show current project status.

package/dist/prompts/commands/quick.md

@@ -1,15 +1,21 @@
+---
+description: "Execute a small ad-hoc task with tracking"
+---
+
 # /quick
 
-Execute a small ad-hoc task with GSD tracking.
+Execute a small ad-hoc task with tracking.
 
 ## Usage
 ```
 /quick [description]
 ```
 
+Task: $ARGUMENTS
+
 ## Steps
 1. Run `draht-tools next-quick-number` to get task number
-2. Create quick plan: `draht-tools create-quick-plan NNN "description"`
+2. Create quick plan: `draht-tools create-quick-plan NNN "$ARGUMENTS"`
 3. Execute tasks following the TDD cycle:
    - **🔴 RED** — Write a failing test that describes the desired behaviour
    - **🟢 GREEN** — Write the minimum implementation to make it pass

package/dist/prompts/commands/resume-work.md

@@ -1,3 +1,7 @@
+---
+description: "Resume from last session state"
+---
+
 # /resume-work
 
 Resume from last session state.

package/dist/prompts/commands/review.md

@@ -1,3 +1,7 @@
+---
+description: "Code review and security audit of recent changes"
+---
+
 # /review
 
 Ad-hoc code review and security audit of recent changes or a specific scope.
@@ -7,6 +11,8 @@ Ad-hoc code review and security audit of recent changes or a specific scope.
 /review [scope]
 ```
 
+Scope: $ARGUMENTS
+
 If no scope given, reviews all recent uncommitted changes.
 
 ## Steps

package/dist/prompts/commands/verify-work.md

@@ -1,3 +1,7 @@
+---
+description: "Acceptance testing of completed phase work"
+---
+
 # /verify-work
 
 Walk through acceptance testing of completed phase work.
@@ -7,6 +11,8 @@ Walk through acceptance testing of completed phase work.
 /verify-work [N]
 ```
 
+Phase: $1
+
 ## Steps
 1. Run full test suite and capture results:
    - Execute all tests (`bun test` or project-specific runner)
@@ -16,12 +22,12 @@ Walk through acceptance testing of completed phase work.
    - Scan source files for PascalCase identifiers not present in the glossary
    - Flag any bounded context boundary violations (cross-context direct imports)
 3. Run quality gate: `draht-tools quality-gate --strict`
-4. Run `draht-tools extract-deliverables N` to get testable items
+4. Run `draht-tools extract-deliverables $1` to get testable items
 5. Walk user through each deliverable one at a time
 6. Record results (pass/fail/partially/skip)
-7. For failures: diagnose and create fix plans via `draht-tools create-fix-plan N P`
+7. For failures: diagnose and create fix plans via `draht-tools create-fix-plan $1 P`
    - Fix plans MUST include a reproducing test that demonstrates the failure before any implementation
-8. Write UAT report: `draht-tools write-uat N`
+8. Write UAT report: `draht-tools write-uat $1`
    - Report must include: test health summary (pass/fail/coverage), domain model status (any glossary violations), deliverable results
 9. If all passed: mark phase complete
-10. If failures: route to `execute-phase N --gaps-only`
+10. If failures: route to `execute-phase $1 --gaps-only`

package/hooks/gsd/draht-post-task.js

@@ -19,28 +19,60 @@ if (!phaseNum || !planNum || !taskNum || !status) {
 	process.exit(1);
 }
 
+// ── Toolchain detection — mirrors src/gsd/hook-utils.ts ──────────────────────
+function detectToolchain(cwd) {
+	if (fs.existsSync(path.join(cwd, "bun.lockb")) || fs.existsSync(path.join(cwd, "bun.lock"))) {
+		return { pm: "bun", testCmd: "bun test", coverageCmd: "bun test --coverage", lintCmd: "bunx biome check ." };
+	}
+	if (fs.existsSync(path.join(cwd, "pnpm-lock.yaml"))) {
+		return { pm: "pnpm", testCmd: "pnpm test", coverageCmd: "pnpm run test:coverage", lintCmd: "pnpm run lint" };
+	}
+	if (fs.existsSync(path.join(cwd, "yarn.lock"))) {
+		return { pm: "yarn", testCmd: "yarn test", coverageCmd: "yarn run test:coverage", lintCmd: "yarn run lint" };
+	}
+	return { pm: "npm", testCmd: "npm test", coverageCmd: "npm run test:coverage", lintCmd: "npm run lint" };
+}
+
+function readHookConfig(cwd) {
+	const defaults = { coverageThreshold: 80, tddMode: "advisory", qualityGateStrict: false };
+	const configPath = path.join(cwd, ".planning", "config.json");
+	if (!fs.existsSync(configPath)) return defaults;
+	try {
+		const raw = JSON.parse(fs.readFileSync(configPath, "utf-8"));
+		const h = raw.hooks || {};
+		return {
+			coverageThreshold: typeof h.coverageThreshold === "number" ? h.coverageThreshold : defaults.coverageThreshold,
+			tddMode: h.tddMode === "strict" || h.tddMode === "advisory" ? h.tddMode : defaults.tddMode,
+			qualityGateStrict: typeof h.qualityGateStrict === "boolean" ? h.qualityGateStrict : defaults.qualityGateStrict,
+		};
+	} catch { return defaults; }
+}
+
 const PLANNING = ".planning";
 const LOG_FILE = path.join(PLANNING, "execution-log.jsonl");
+const cwd = process.cwd();
+const toolchain = detectToolchain(cwd);
+const hookConfig = readHookConfig(cwd);
 
 // 0. TDD cycle compliance check
-// If the current commit message starts with "green:", the previous commit for this
-// task should start with "red:" — enforce the Red → Green order.
 if (commitHash) {
 	try {
-		// Find the commit message for commitHash and the one before it
 		const currentMsg = execSync(`git log --format=%s -n 1 ${commitHash} 2>/dev/null`, { encoding: "utf-8" }).trim();
 		if (/^green:/i.test(currentMsg)) {
-			// Scope search to commits that mention this phase/plan/task in their message
-			// to avoid false positives from unrelated older commits
 			const taskPrefix = `${phaseNum}-${planNum}-${taskNum}`;
 			const recentMsgs = execSync(`git log --format=%s -n 50 ${commitHash}~1 2>/dev/null`, { encoding: "utf-8" })
 				.trim()
 				.split("\n")
 				.filter((m) => m.includes(taskPrefix) || /^(red|green|refactor):/i.test(m));
-			// Find the nearest TDD-cycle commit scoped to this task
 			const prevTaskMsg = recentMsgs.find((m) => /^(red|green|refactor):/i.test(m) && m.includes(taskPrefix));
 			if (!prevTaskMsg || !/^red:/i.test(prevTaskMsg)) {
-				console.log(`⚠️  TDD violation: "green:" commit detected but no preceding "red:" commit found for task ${phaseNum}-${planNum}-${taskNum}`);
+				const violation = `TDD violation: "green:" commit without preceding "red:" for task ${phaseNum}-${planNum}-${taskNum}`;
+				if (hookConfig.tddMode === "strict") {
+					console.error(`❌ ${violation}`);
+					process.exit(1);
+				} else {
+					console.log(`⚠️  ${violation}`);
+				}
 				fs.appendFileSync(LOG_FILE, JSON.stringify({
 					timestamp: new Date().toISOString(),
 					phase: parseInt(phaseNum, 10),
@@ -69,13 +101,15 @@ const entry = {
 
 fs.appendFileSync(LOG_FILE, JSON.stringify(entry) + "\n");
 
-// 2. Run type check if status is pass
+// 2. Run type check and tests if status is pass
 if (status === "pass") {
+	// Type check
 	try {
-		execSync("bun run tsgo --noEmit 2>&1", { timeout: 30000, encoding: "utf-8" });
+		const tsCmd = toolchain.pm === "bun" ? "bun run tsgo --noEmit 2>&1" : "npx tsc --noEmit 2>&1";
+		execSync(tsCmd, { timeout: 30000, encoding: "utf-8", cwd });
 		// Run tests
 		try {
-			const testOutput = execSync("bun test 2>&1", { timeout: 60000, encoding: "utf-8" });
+			const testOutput = execSync(`${toolchain.testCmd} 2>&1`, { timeout: 60000, encoding: "utf-8", cwd });
 			const testMatch = testOutput.match(/(\d+) pass/);
 			const testCount = testMatch ? testMatch[1] : "?";
 			console.log(`✅ Task ${phaseNum}-${planNum}-${taskNum}: passed + types clean + ${testCount} tests pass`);
@@ -93,7 +127,6 @@ if (status === "pass") {
 		const errorCount = (output.match(/error TS/g) || []).length;
 		if (errorCount > 0) {
 			console.log(`⚠️  Task ${phaseNum}-${planNum}-${taskNum}: passed but ${errorCount} type error(s) introduced`);
-			// Append warning to log
 			fs.appendFileSync(LOG_FILE, JSON.stringify({
 				...entry,
 				warning: `${errorCount} type errors introduced`,