bmad-module-skill-forge 0.8.1 → 0.8.3

package/docs/how-it-works.md

@@ -40,7 +40,7 @@ Each workflow directory contains these files, and each has a specific job:
 |---------------------------|---------------------------------------------------------------------------------------------------------------------|---------------------------------------------------|
 | `forger.agent.yaml`       | Expert persona — identity, principles, critical actions, menu of triggers                                           | First — always in context                         |
 | `skf-knowledge-index.csv` | Knowledge fragment index — id, name, tags, tier, file path                                                          | Read by steps to decide which fragments to load   |
-| `knowledge/*.md`          | 12 reusable fragments + overview.md index — cross-cutting principles and patterns (e.g., `zero-hallucination.md`, `confidence-tiers.md`, `ccc-bridge.md`) | Selectively read into context when a step directs |
+| `knowledge/*.md`          | 13 reusable fragments + overview.md index — cross-cutting principles and patterns (e.g., `zero-hallucination.md`, `confidence-tiers.md`, `ccc-bridge.md`) | Selectively read into context when a step directs |
 
 ```mermaid
 flowchart LR
@@ -421,7 +421,7 @@ src/
 │   └── README.md
 ├── knowledge/
 │   ├── skf-knowledge-index.csv
-│   └── *.md (12 knowledge fragments + overview.md index)
+│   └── *.md (13 knowledge fragments + overview.md index)
 └── workflows/
     ├── setup-forge/
     ├── analyze-source/

package/docs/workflows.md

@@ -133,7 +133,7 @@ SKF has 12 workflows. You trigger them by typing commands to [Ferris](../agents/
 
 **Command:** `@Ferris TS`
 
-**Purpose:** Cognitive completeness verification. Quality gate before export.
+**Purpose:** Cognitive completeness verification. Naive and contextual modes. Quality gate before export.
 
 **When to Use:** After creating or updating a skill, before exporting.
 

package/package.json

@@ -1,7 +1,7 @@
 {
   "$schema": "https://json.schemastore.org/package.json",
   "name": "bmad-module-skill-forge",
-  "version": "0.8.1",
+  "version": "0.8.3",
   "description": "BMAD module — Turn code and docs into instructions AI agents can actually follow. Progressive capability tiers (Quick/Forge/Forge+/Deep).",
   "keywords": [
     "bmad",

package/src/knowledge/ccc-bridge.md

@@ -102,7 +102,7 @@ For remote repository sources (GitHub URLs), CCC cannot operate during step-02b
 
 1. **step-02b:** Detects remote source, sets `{ccc_discovery: []}`, displays deferred message
 2. **step-03:** After ephemeral clone succeeds, detects the deferred scenario (`tools.ccc == true AND {ccc_discovery} is empty AND ephemeral_clone_active == true AND tier is Forge+/Deep`)
-3. **step-03:** Runs `cd {temp_path} && ccc init` + `ccc index` on the ephemeral clone (extended timeout or background mode, verified via `ccc status`)
+3. **step-03:** Runs `cd {temp_path} && ccc init` on the ephemeral clone, then applies brief `exclude_patterns` (if present) to `{temp_path}/.cocoindex_code/settings.yml` before running `ccc index` (extended timeout or background mode, verified via `ccc status`). This prevents CCC from indexing files the brief explicitly excludes, keeping search results focused on in-scope source code and reducing indexing time for large repositories.
 4. **step-03:** Executes CCC search and populates `{ccc_discovery}` before AST extraction begins
 
 The ephemeral clone index is not registered in `ccc_index_registry` — the clone is deleted after extraction and the CCC daemon's own GC handles orphaned indexes.
@@ -131,6 +131,7 @@ To prevent excessive daemon calls, workflow steps cap ccc queries:
 - Passing ccc results directly to the extraction inventory — they are candidates, not extractions
 - Listing ccc as "unavailable" in reports for Quick/Forge tiers — ccc is a Forge+ capability, not something Quick/Forge tiers are missing
 - Indexing without configuring SKF exclusions — framework and output directories pollute search results
+- Indexing an ephemeral clone without applying brief `exclude_patterns` — excluded files pollute CCC search results and waste indexing time on large repositories
 - Skipping CCC discovery for remote sources without deferring to step-03 — remote repos deserve the same pre-ranking as local sources
 
 ## Related Fragments

package/src/workflows/create-skill/data/extraction-patterns-tracing.md

@@ -82,7 +82,7 @@ Scripts and assets are file-level artifacts, not code exports. They follow the *
 - Exclude generated files (`dist/`, `build/`, `.webpack/` output)
 - Exclude vendored/third-party files
 - Flag files >500 lines for user confirmation (may be too large for skill package)
-- If `scripts_intent: "none"` or `assets_intent: "none"` in brief, skip that category
+- If `scripts_intent` is absent from the brief, treat as `"detect"` (auto-detection is the default). If `scripts_intent` is explicitly `"none"`, skip scripts detection. Same rule applies to `assets_intent`.
 
 ### Provenance and Hashing
 

package/src/workflows/create-skill/steps-c/step-03-extract.md

@@ -84,16 +84,24 @@ If ALL of these conditions are true:
 
 Then run CCC indexing and discovery on the ephemeral clone:
 
-1. **Index the clone:** Run `cd {temp_path} && ccc init` then `ccc index` with an extended timeout or in background mode — `ccc init` takes no positional arguments and initializes the index for the current working directory. Indexing can take several minutes on large codebases (1000+ files). Use `ccc status` to verify completion — check that `Chunks` and `Files` counts are non-zero. If init fails or indexing fails, set `{ccc_discovery: []}` and continue — this is not an error.
+1. **Initialize index:** Run `cd {temp_path} && ccc init` — `ccc init` takes no positional arguments and initializes the index for the current working directory. If init fails, set `{ccc_discovery: []}` and continue — this is not an error.
 
-2. **Construct semantic query:** Build from brief data: `"{brief.name} {brief.scope}"`. Truncate to 80 characters — keep the full skill name and trim `brief.scope` from the end. If `brief.scope` is very short (< 10 chars), append terms from `brief.description` to fill the remaining space.
+2. **Apply brief exclusions:** If `brief.exclude_patterns` is present and non-empty, apply them to `{temp_path}/.cocoindex_code/settings.yml` before indexing:
+   1. Read `{temp_path}/.cocoindex_code/settings.yml` (created by `ccc init`)
+   2. For each pattern in `brief.exclude_patterns`: if the pattern is NOT already present in the `exclude_patterns` array, append it
+   3. Write the updated `settings.yml` back
+   This prevents CCC from indexing excluded files, keeping search results focused on in-scope source code. If `brief.exclude_patterns` is absent or empty, skip this step.
 
-3. **Execute search:** Run `ccc_bridge.search(query, temp_path, top_k=20)`:
+3. **Index the clone:** Run `cd {temp_path} && ccc index` with an extended timeout or in background mode. Indexing can take several minutes on large codebases (1000+ files). Use `ccc status` to verify completion — check that `Chunks` and `Files` counts are non-zero. If indexing fails, set `{ccc_discovery: []}` and continue — this is not an error.
+
+4. **Construct semantic query:** Build from brief data: `"{brief.name} {brief.scope}"`. Truncate to 80 characters — keep the full skill name and trim `brief.scope` from the end. If `brief.scope` is very short (< 10 chars), append terms from `brief.description` to fill the remaining space.
+
+5. **Execute search:** Run `ccc_bridge.search(query, temp_path, top_k=20)`:
    - **Tool resolution:** Use `/ccc` skill search (Claude Code), ccc MCP server (Cursor), or `cd {temp_path} && ccc search --limit 20 "{query}"` (CLI). Note: `ccc search` operates on the index in the current working directory. See [knowledge/tool-resolution.md](../../../knowledge/tool-resolution.md).
 
-4. **Store results:** If search succeeds, store as `{ccc_discovery: [{file, score, snippet}]}`. Display: "**CCC semantic discovery (post-clone): {N} relevant regions identified across {M} unique files.**"
+6. **Store results:** If search succeeds, store as `{ccc_discovery: [{file, score, snippet}]}`. Display: "**CCC semantic discovery (post-clone): {N} relevant regions identified across {M} unique files.**"
 
-5. **On failure:** Set `{ccc_discovery: []}`. Display: "CCC post-clone discovery unavailable — proceeding with standard extraction." Do NOT halt.
+7. **On failure:** Set `{ccc_discovery: []}`. Display: "CCC post-clone discovery unavailable — proceeding with standard extraction." Do NOT halt.
 
 **CCC Discovery Integration (Forge+ and Deep with ccc only):**
 
@@ -184,7 +192,9 @@ Use the entry point as the authoritative source for `metadata.json`'s `exports[]
 
 ### 4c. Detect and Inventory Scripts/Assets
 
-**If `scripts_intent: "none"` AND `assets_intent: "none"` in brief:** Skip this section.
+**Default resolution:** If `scripts_intent` is absent from the brief, treat as `"detect"` (auto-detection). If `assets_intent` is absent, treat as `"detect"`. Only an explicit `"none"` value disables detection.
+
+**If `scripts_intent` is `"none"` AND `assets_intent` is `"none"`:** Skip this section entirely. **If only one is `"none"`:** Skip that category only, proceed with the other.
 
 After export extraction, scan the source for scripts and assets using the detection patterns in `{extractionPatternsTracingData}`: