valent-pipeline 0.2.6 → 0.2.8

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "valent-pipeline",
-  "version": "0.2.6",
+  "version": "0.2.8",
   "description": "v3 multi-agent AI pipeline for software development lifecycle",
   "type": "module",
   "bin": {

package/pipeline/prompts/embed.md

@@ -30,7 +30,7 @@ Verify `{story_output_dir}/embed-instructions.md` exists. If missing, send `[BLO
 **If `{knowledge_mode}` is `sqlite` (recommended):**
 
 ```bash
-npx valent-pipeline db embed {story_output_dir}/embed-instructions.md \
+node .valent-pipeline/bin/cli.js db embed {story_output_dir}/embed-instructions.md \
   --curated-path {curated_files_path}
 ```
 

package/pipeline/prompts/knowledge.md

@@ -38,7 +38,7 @@ Read all files in `{curated_files_path}`. Build in-memory index of file names, s
 **If `{knowledge_mode}` is `sqlite`:**
 Verify the database is accessible by running:
 ```bash
-npx valent-pipeline db query-stories
+node .valent-pipeline/bin/cli.js db query-stories
 ```
 If it returns results or "No stories in database", the DB is accessible. If the command fails, operate in curated-only mode.
 
@@ -53,12 +53,12 @@ For each incoming query:
 1. Search correction directives for relevant entries
 2. Search curated knowledge files for matching sections
 3. If database connected (SQLite mode): query using the CLI tool and read stdout for results:
-   - Fetch a specific artifact: `npx valent-pipeline db query-artifact --story KANBAN-001 --type reqs-brief`
-   - Fetch directives for an agent: `npx valent-pipeline db query-directives --agent BEND`
-   - Full-text search: `npx valent-pipeline db search --query "acceptance criteria"`
-   - List artifacts for a story: `npx valent-pipeline db query-list --story KANBAN-001`
-   - List all stories: `npx valent-pipeline db query-stories`
-   - Cross-story bug search: `npx valent-pipeline db query-bugs-since --since 2026-03-01`
+   - Fetch a specific artifact: `node .valent-pipeline/bin/cli.js db query-artifact --story KANBAN-001 --type reqs-brief`
+   - Fetch directives for an agent: `node .valent-pipeline/bin/cli.js db query-directives --agent BEND`
+   - Full-text search: `node .valent-pipeline/bin/cli.js db search --query "acceptance criteria"`
+   - List artifacts for a story: `node .valent-pipeline/bin/cli.js db query-list --story KANBAN-001`
+   - List all stories: `node .valent-pipeline/bin/cli.js db query-stories`
+   - Cross-story bug search: `node .valent-pipeline/bin/cli.js db query-bugs-since --since 2026-03-01`
    If ChromaDB mode: use collection query (ChromaDB)
 4. Compose response: targeted, SHORT (aim ~200 tokens, max 500)
 5. Include source reference: `Source: curated/{file}#section` or `Source: sqlite:artifacts/{story_id}/{type}` or `Source: correction-directives#{directive-id}`

package/pipeline/prompts/lead.md

@@ -389,9 +389,11 @@ From the manifest `reads_from` / `writes_to`, build the execution order for this
 
 ### Step 5: Spawn Teammates
 
-For each agent in the roster, spawn a teammate with:
+**Do NOT read agent prompt files or step files yourself.** Use the spawn template — substitute variables and pass it to the Agent tool. Each teammate reads its own prompt and steps after spawning. This keeps your context lean.
+
+For each agent in the roster, spawn a teammate with the filled spawn template containing:
 - Role assignment from manifest
-- Prompt template from manifest `prompt_template`
+- Prompt path from manifest `prompt_template` (the teammate reads it, not you)
 - Shared context references: story_id, story_output_dir, tech stack values, correction directives
 - Task assignment with dependency information
 
@@ -493,7 +495,7 @@ This runs PMCP in parallel with QA-B's test execution, removing it from the crit
 When `{knowledge_mode}` is `sqlite` and you receive a `[HANDOFF]` from an agent that produces an output file, index the artifact into the SQLite database so downstream agents can query it via Knowledge:
 
 ```bash
-npx valent-pipeline db index-handoff --file {story_output_dir}/{artifact_file} \
+node .valent-pipeline/bin/cli.js db index-handoff --file {story_output_dir}/{artifact_file} \
   --story-id {story_id} \
   --agent {agent_name} \
   --artifact-type {type}
@@ -588,7 +590,7 @@ Tear down all per-story teammates. Send `shutdown_request` to each individually.
 If `{knowledge_mode}` is `sqlite`, record story actuals to the calibration table for future estimation accuracy:
 
 ```bash
-npx valent-pipeline db record-calibration \
+node .valent-pipeline/bin/cli.js db record-calibration \
   --story-id {story_id} \
   --ac-count {ac_count_from_reqs_brief} \
   --surface {project_type} \

package/pipeline/steps/orchestration/adopt-lead-and-create-team.md

@@ -75,7 +75,15 @@ This file is appended to incrementally during monitoring as agents complete phas
 
 **IMPORTANT: Use the Agent tool to spawn teammates onto the team — NOT subagents.** Every pipeline agent must be a named teammate so it can send and receive inbox messages with other teammates. Use the `name` parameter on the Agent tool to set the teammate's addressable name (e.g., `name: "REQS"`).
 
-Read the spawn templates:
+**DO NOT read the agent's prompt files, step files, or templates yourself.** The spawn template tells the teammate to read its own prompt and steps. Your job is ONLY to:
+1. Read the spawn template (a short 15-line template)
+2. Substitute `{{variables}}` with resolved values from config and the task graph
+3. Pass the filled template as the Agent tool's `prompt` parameter
+4. The teammate reads its own prompt, step files, and inputs after it starts
+
+This keeps the main thread lightweight. If you read every agent's prompt and steps before spawning, you waste context window on content that only the teammate needs.
+
+Read the spawn templates (these are short variable templates, NOT the agent prompts):
 - `.valent-pipeline/spawn-templates/knowledge-spawn.template.md` -- for the Knowledge Agent
 - `.valent-pipeline/spawn-templates/agent-spawn.template.md` -- for all other agents
 

package/pipeline/steps/orchestration/sprint-groom.md

@@ -20,7 +20,7 @@ For each story in grooming candidates (up to `{groom_target}` from sprint-init):
 4. On UXA handoff → update status to `test-case-development` → QA-A writes `qa-test-spec.md`
 5. On QA-A handoff → index all artifacts to SQLite **working table**:
    ```bash
-   npx valent-pipeline db index-working \
+   node .valent-pipeline/bin/cli.js db index-working \
      --story-id {story_id} \
      --sprint-id {current_sprint_id}
    ```
@@ -46,7 +46,7 @@ After every `{sprint_max_groom_batch}` stories (default: 10), kill and respawn P
 After all stories groomed:
 
 ```bash
-npx valent-pipeline db flush-working \
+node .valent-pipeline/bin/cli.js db flush-working \
   --sprint-id {current_sprint_id}
 ```
 

package/pipeline/steps/orchestration/sprint-init.md

@@ -15,7 +15,7 @@ Sprint ID format:
 Query the calibration table for historical velocity data:
 
 ```bash
-npx valent-pipeline db query-velocity
+node .valent-pipeline/bin/cli.js db query-velocity
 ```
 
 **Velocity rules:**

package/pipeline/steps/orchestration/sprint-review.md

@@ -34,7 +34,7 @@ Update `sprint-{n}-status.yaml`:
 For each shipped story, ensure the calibration table has complete data:
 
 ```bash
-npx valent-pipeline db record-calibration \
+node .valent-pipeline/bin/cli.js db record-calibration \
   --story-id {story_id} \
   --story-points {fibonacci_estimate} \
   --estimated-points {fibonacci_estimate} \

package/pipeline/steps/readiness/sprint-review.md

@@ -9,7 +9,7 @@ These steps run AFTER the standalone review (Steps 1-8) passes. If the standalon
 Query the SQLite working table for specs from other stories groomed in this sprint batch:
 
 ```bash
-npx valent-pipeline db query-working \
+node .valent-pipeline/bin/cli.js db query-working \
   --sprint-id {current_sprint_id} \
   --exclude-story {story_id}
 ```

package/skills/valent-setup-backlog/SKILL.md

@@ -173,8 +173,8 @@ If the repo is empty or brand new (no source code yet), skip the subagents and c
 ### Step 7b: Initialize and Populate Knowledge Database
 
 After writing the curated knowledge files:
-1. Run `valent-pipeline db init` to create the SQLite database if it doesn't exist
-2. Run `npx valent-pipeline db rebuild` to index any existing story artifacts
+1. Run `node .valent-pipeline/bin/cli.js db init` to create the SQLite database if it doesn't exist
+2. Run `node .valent-pipeline/bin/cli.js db rebuild` to index any existing story artifacts
 3. The database is now ready for the Knowledge Agent to query during story execution
 
 ## Step 8: Report