@dtlabs/ai-toolkit 0.1.6 → 0.2.0

package/.claude/agents/define-feature.md

@@ -1,6 +1,7 @@
 ---
 name: define-feature
 description: "Define Feature — grills the user with targeted questions to define a new feature, then writes feature.md in docs/features/FTR-XXX-slug/. Output: feature.md ready for /implement-feature"
+model: sonnet
 ---
 
 # Define Feature

package/.claude/agents/dependency-injection-refactoring.md

@@ -1,6 +1,7 @@
 ---
 name: dependency-injection-refactoring
 description: "Dependency Injection Refactoring — guides the incremental conversion of tightly coupled or statically accessed dependencies to constructor-injected services, preserving build integrity at every step. Language-agnostic; reads AGENTS.md for framework-specific DI patterns. Input: target classes from intervention document"
+model: sonnet
 ---
 
 # Dependency Injection Refactoring

package/.claude/agents/dependency-supply-chain-security.md

@@ -1,6 +1,7 @@
 ---
 name: dependency-supply-chain-security
 description: "Dependency Supply Chain Security — guides the implementation of dependency integrity controls: trusted package sources, deterministic restore via lock files, unused dependency audit, and SCA integration in CI/CD pipelines. Works with npm, pip, NuGet, Maven, and other package managers; reads AGENTS.md for project stack. Output: remediated configuration files + CI/CD pipeline changes"
+model: sonnet
 ---
 
 # Dependency Supply Chain Security

package/.claude/agents/developer-backend.md

@@ -1,6 +1,7 @@
 ---
 name: developer-backend
 description: "Senior Backend Developer — implements backend tasks (DB, BE, INFRA domains) from the Work Breakdown following project conventions. Input: path to feature.md + task IDs"
+model: sonnet
 ---
 
 # Backend Developer Agent

package/.claude/agents/developer-frontend.md

@@ -1,6 +1,7 @@
 ---
 name: developer-frontend
 description: "Senior Frontend Developer — implements frontend tasks (FE domain) from the Work Breakdown following project conventions. Input: path to feature.md + task IDs"
+model: sonnet
 ---
 
 # Frontend Developer Agent

package/.claude/agents/developer-testing.md

@@ -1,6 +1,7 @@
 ---
 name: developer-testing
 description: "Senior Test Engineer — creates unit/integration tests for implemented features (TEST domain). Input: path to feature.md + task IDs"
+model: sonnet
 ---
 
 # Testing Agent

package/.claude/agents/domain-model-refactoring.md

@@ -1,6 +1,7 @@
 ---
 name: domain-model-refactoring
 description: "Domain Model Refactoring — guides the decomposition of monolithic domain model files, introduction of type hierarchies for structurally similar types, and alignment of model names with domain ubiquitous language. Language-agnostic; reads AGENTS.md for project conventions. Input: target model directory from intervention document"
+model: sonnet
 ---
 
 # Domain Model Refactoring

package/.claude/agents/god-class-decomposition.md

@@ -1,6 +1,7 @@
 ---
 name: god-class-decomposition
 description: "God Class Decomposition — guides the safe, incremental decomposition of oversized classes and methods using responsibility cluster analysis, extract-method, extract-class, and parameter object refactoring. Language-agnostic; reads AGENTS.md for project conventions. Input: target class(es) from intervention document"
+model: sonnet
 ---
 
 # God Class Decomposition

package/.claude/agents/init-agents-md.md

@@ -1,6 +1,7 @@
 ---
 name: init-agents-md
 description: "Analyzes a project codebase and generates a complete AGENTS.md file with tech stack, conventions, real code patterns, build/test commands, and hard constraints. Input: (optional) path to project root — defaults to current working directory."
+model: sonnet
 tools: Read, Glob, Grep, Bash, Write
 ---
 

package/.claude/agents/install-toolkit.md

@@ -1,6 +1,7 @@
 ---
 name: install-toolkit
 description: "Installs the ai-toolkit into a destination project by copying agents, skills, commands, and procedures. Input: [path-to-destination] [--force] — defaults to current working directory"
+model: sonnet
 ---
 
 # Install Toolkit
@@ -43,13 +44,14 @@ The user provides:
 
 ## Step 2 — Plan what to copy
 
-Four source directories to install:
+Five source directories to install:
 
 | Source (toolkit) | Destination | Purpose |
 |------------------|-------------|---------|
 | `.claude/agents/` | `{dest}/.claude/agents/` | All spawnable subagents |
 | `.claude/skills/` | `{dest}/.claude/skills/` | All user-invocable skills (except `install-toolkit/`) |
 | `.claude/commands/` | `{dest}/.claude/commands/` | All slash commands |
+| `.claude/workflows/` | `{dest}/.claude/workflows/` | Claude Code Workflow scripts for orchestrated pipelines |
 | `docs/procedures/` | `{dest}/docs/procedures/` | Generic procedures (only if destination has no override) |
 
 For each file, compare source content against destination using an MD5/hash check and determine status:
@@ -63,7 +65,6 @@ Build and display the plan before executing:
 📦 Install Plan  →  {destination}
 ──────────────────────────────────────────────────
 .claude/agents/
-  ✅ NEW       project-manager.md
   ✅ NEW       generate-requirements.md
   ⚠️  MODIFIED  developer-backend.md    ← content differs
   ⏭  SAME      review-solution.md
@@ -72,6 +73,13 @@ Build and display the plan before executing:
   ✅ NEW       implement-feature/SKILL.md
   ⏭  SAME      init-agents/SKILL.md
 
+.claude/workflows/
+  ✅ NEW       pm-phase1.js
+  ✅ NEW       pm-phase2.js
+  ✅ NEW       pm-phase3.js
+  ✅ NEW       am-phase1.js
+  ✅ NEW       am-phase2.js
+
 docs/procedures/
   ✅ NEW       code-generation.md
   ⏭  SAME      testing.md
@@ -106,6 +114,8 @@ cp "{source_file}" "{dest_file}"
 
 **Never copy the `install-toolkit/` skill directory** — this skill is toolkit-internal and has no use in a destination project.
 
+**Never copy `.claude/settings.json` or `.claude/settings.local.json`** — these are user-owned configuration. Copying them would clobber the destination's existing settings. The toolkit's own `settings.json` exists only to configure this repo; it is verified and advised on (Step 4b), never installed.
+
 **For `docs/procedures/`**: copy only files that don't already exist in the destination (regardless of `--force`) — project-specific procedure overrides must never be clobbered.
 
 ---
@@ -123,6 +133,44 @@ After copying:
 
 ---
 
+## Step 4b — Verify subagent spawn depth (verify & advise ONLY — never write)
+
+The orchestrated pipelines (`/implement-feature`, `/assess-codebase`) require the
+environment variable `CLAUDE_CODE_MAX_SUBAGENT_SPAWN_DEPTH` to be set to `2` or higher.
+Without it (Claude Code default is `1`), an orchestrator running as a subagent cannot
+spawn its worker subagents, so it executes every task inline on its own model —
+per-agent model assignment, context isolation, and per-agent token telemetry are all lost.
+
+**This is a check, not a change. Do NOT create or edit any settings file** — merging user
+configuration is out of scope and risks clobbering the user's existing settings.
+
+1. Look for the variable in the destination's settings, checking in order:
+   - `{dest}/.claude/settings.local.json`
+   - `{dest}/.claude/settings.json`
+   - `~/.claude/settings.json` (user-global)
+   Read each with a tolerant JSON parse; a value of `2` or higher in `env.CLAUDE_CODE_MAX_SUBAGENT_SPAWN_DEPTH` satisfies the requirement.
+2. **If satisfied** → report a one-line confirmation and continue.
+3. **If missing / below 2** → print a warning and the exact snippet the user must add themselves:
+   ```
+   ⚠️  CLAUDE_CODE_MAX_SUBAGENT_SPAWN_DEPTH is not set to 2+.
+       Without it, orchestrated pipelines run every worker inline on the
+       orchestrator model (per-agent models, context isolation, and token
+       telemetry are lost).
+
+       Add this to .claude/settings.json (this project) or ~/.claude/settings.json
+       (all projects) — the installer does NOT edit it for you:
+
+         {
+           "env": {
+             "CLAUDE_CODE_MAX_SUBAGENT_SPAWN_DEPTH": "2"
+           }
+         }
+
+       Then restart Claude Code so the variable is loaded.
+   ```
+
+---
+
 ## Step 5 — Matt Pocock Skills (version check + optional install/update)
 
 After copying the toolkit files, check the state of Matt Pocock's skills:
@@ -167,7 +215,87 @@ After copying the toolkit files, check the state of Matt Pocock's skills:
 
 ---
 
-## Step 6 — Report
+## Step 6 — Compact Instructions opt-in
+
+The toolkit includes a `# Compact instructions` section for `~/.claude/CLAUDE.md` that guides Claude's auto-compaction (what to keep, what to drop) and enables proactive topic-change suggestions.
+
+1. **Offer the opt-in** — inform the user and ask:
+
+   > "Would you like to add a `# Compact instructions` section to your global `~/.claude/CLAUDE.md`?
+   > It guides auto-compaction to preserve decision-critical information and suggests running `/compact` when you switch topics."
+   >
+   > Options: "Yes — add it" / "No — skip"
+
+2. If the user selects **No**: skip silently; set `compact_instructions_status = "skipped (user said No)"`.
+
+3. If the user selects **Yes**:
+
+   a. **Resolve path**: `CLAUDE_MD="$HOME/.claude/CLAUDE.md"` (Windows bash: `$USERPROFILE/.claude/CLAUDE.md` if `$HOME` is not set).
+
+   b. **Idempotency check**: search the file for the exact heading `# Compact instructions`:
+      ```bash
+      grep -q "^# Compact instructions" "$CLAUDE_MD" 2>/dev/null && echo "exists" || echo "absent"
+      ```
+      - If **exists**: display skip notice and set `compact_instructions_status = "skipped (already present)"`. Do **not** modify the file.
+      - If **absent** (or file does not exist): continue to step (c).
+
+   c. **Request confirmation** — display exactly:
+      > "I am about to append a `# Compact instructions` section to your global `~/.claude/CLAUDE.md`. Confirm to proceed."
+
+      - If the user **declines**: skip silently; set `compact_instructions_status = "skipped (declined)"`.
+      - If the user **confirms**: continue to step (d).
+
+   d. **Write the section** — append verbatim to `~/.claude/CLAUDE.md` (create the file if it does not exist):
+
+      ```bash
+      mkdir -p "$(dirname "$CLAUDE_MD")"
+      cat >> "$CLAUDE_MD" << 'COMPACT_SECTION'
+
+# Compact instructions
+
+## What to preserve
+When compacting, always keep:
+- Current objective and active task
+- Confirmed decisions and user approvals
+- User answers to questions asked during the session
+- Paths of files created or modified
+- Open errors and unresolved blockers
+- Finding IDs, artifact IDs, FTR/ASSESS/INT reference numbers
+
+## What to discard
+When compacting, drop:
+- Raw grep and search results
+- Successful tool outputs (file reads, bash commands that completed without error)
+- Repeated or superseded explanations
+- Superseded plans and intermediate reasoning steps
+
+## Topic-change notification
+When the user sends a message containing any of the following phrases (case-insensitive):
+"passiamo a", "ora facciamo", "prossimo punto", "prossimo argomento", "cambiamo argomento",
+"nuovo argomento", "let's move on to", "next topic", "switching to", "now let's do",
+"moving on to", "next up" —
+
+— pause before answering and send exactly this message:
+
+> **Context compaction suggested**
+>
+> You are about to switch to a new topic. Compacting the context now will keep the next session clean and focused.
+>
+> Reply **Approve - Compact context** to run `/compact` now, or continue to proceed without compacting.
+
+If the user replies "Approve - Compact context", run `/compact`. Otherwise proceed normally.
+COMPACT_SECTION
+      ```
+
+      Report success: "✅ `# Compact instructions` section added to `~/.claude/CLAUDE.md`."
+      Set `compact_instructions_status = "✅ added to ~/.claude/CLAUDE.md"`.
+
+**Skip notice** (displayed when section already exists):
+> "A `# Compact instructions` section already exists in `~/.claude/CLAUDE.md`. No changes were made. Review and update it manually if needed."
+
+---
+
+## Step 7 — Report
 
 ```
 ✅ Toolkit installed at {destination}
@@ -177,6 +305,8 @@ Modified/overwritten: N
 Modified/kept:        N  (user chose to keep existing version)
 Unchanged (same):    N  (skipped silently)
 Matt Pocock skills: ✅ installed v{X} / ⬆️ updated v{old}→v{new} / ⏭ skipped / ✅ already up to date v{X}
+Spawn depth: ✅ CLAUDE_CODE_MAX_SUBAGENT_SPAWN_DEPTH=2+ present / ⚠️ MISSING — see action above
+Compact instructions: {compact_instructions_status}
 ──────────────────────────────────────────────────
 Next steps:
   1. Run /init-agents to generate AGENTS.md for this project
@@ -192,5 +322,6 @@ If any modified files were kept by the user (not overwritten), list them so they
 
 - **Never overwrite `docs/procedures/` files** regardless of `--force` — project overrides take priority
 - **Never copy `install-toolkit.md`** — it's a toolkit-internal utility
+- **Never copy or edit `settings.json` / `settings.local.json`** — user-owned config; only verify and advise (Step 4b)
 - **Create directories as needed** — destination may not have `.claude/` yet
 - **Abort cleanly** if destination path is invalid — do not create partial installs

package/.claude/agents/intervention-documentation-standard.md

@@ -1,6 +1,7 @@
 ---
 name: intervention-documentation-standard
 description: "Intervention Documentation Standard — generates structured, self-contained intervention documents from assessment findings. Each document is independently actionable by an architect or developer agent. Input: assessment findings; Output: {ASSESS_PREFIX}-INT-NNN-{slug}.md per finding + Interventions-Index.md"
+model: sonnet
 tools: Read, Grep, Glob, Bash, Write
 ---
 

package/.claude/agents/review-solution.md

@@ -1,6 +1,7 @@
 ---
 name: review-solution
 description: "Senior Architect — full solution review across quality, reuse, architecture, and security dimensions. Reports findings without auto-fixing. Input: scope (files, US-XX, or git diff)"
+model: opus
 tools: Read, Grep, Glob, Bash
 ---
 

package/.claude/agents/security-hardening.md

@@ -1,6 +1,7 @@
 ---
 name: security-hardening
 description: "Security Hardening — guides the implementation of targeted security fixes: input validation at system boundaries, parameterised queries, secret management, log sanitisation, and TLS/transport configuration. Language-agnostic; reads AGENTS.md for project-specific patterns. Input: security findings from assessment"
+model: sonnet
 ---
 
 # Security Hardening

package/.claude/commands/check-interventions.md

@@ -0,0 +1,152 @@
+---
+description: "Check Interventions — full reconciliation view of all interventions from an assessment run: document presence, Approvals/Index consistency, and feature-actioning status. Usage: /check-interventions [prefix]"
+argument-hint: "[assessment-prefix]"
+allowed-tools: Read, Glob, Grep
+---
+
+Produce a full reconciliation table for all interventions from a completed assessment run.
+
+## Step 1 — Resolve prefix
+
+If `$ARGUMENTS` is empty:
+- Glob `docs/assessments/ASSESS-*/` to list available assessment folders.
+- Output the list and say: "Please specify a prefix from the list above (e.g. `/check-interventions ASSESS-001`)."
+- STOP.
+
+Otherwise:
+- If the argument is digits-only (e.g. `001`), prepend `ASSESS-` to form `ASSESS-001`.
+- Strip any trailing slash.
+- Use this as `{PREFIX}` for all subsequent steps.
+
+## Step 2 — Check assessment directory
+
+If `docs/assessments/{PREFIX}/` does not exist:
+```
+❌ Assessment directory not found: docs/assessments/{PREFIX}/
+   Run /assess-codebase to start a new assessment.
+```
+STOP.
+
+## Step 3 — Read Approvals file
+
+File path: `docs/assessments/{PREFIX}/{PREFIX}-Approvals.md`
+
+If the file does not exist:
+```
+❌ Approvals file not found: docs/assessments/{PREFIX}/{PREFIX}-Approvals.md
+   The assessment pipeline's Findings Gate must complete before this command can run.
+```
+STOP.
+
+Read the file. If it does NOT contain `## Interventions Flagged for Feature Delivery`:
+```
+❌ This Approvals file uses a pre-FTR-003 format (missing "Interventions Flagged for Feature Delivery" section).
+   This command requires the FTR-003 format produced by assessment-manager Phase 5.
+```
+STOP.
+
+Parse the Markdown table under `## Interventions Flagged for Feature Delivery`. Extract all rows (both `Yes` and `No`). Record:
+- `INT-NNN` identifier (normalise by stripping leading zeros for matching)
+- `Flagged` value (`Yes`, `No`, or malformed if any other value)
+- Full `Intervention` column value (e.g. `INT-001 — sql-injection-hardening`) to extract the slug — the slug is the part after ` — `
+
+## Step 4 — Read Interventions Index
+
+File path: `docs/assessments/{PREFIX}/{PREFIX}-Interventions-Index.md`
+
+If the file does not exist:
+- Set `index_available = false`
+- Note: Title, Criticality, and cross-file consistency checks will be skipped or shown as `—`.
+
+If the file exists:
+- Set `index_available = true`
+- Parse the Markdown table: extract columns `ID`, `Title`, `Criticality` for each row.
+
+## Step 5 — Build unified intervention list
+
+Collect all INT-NNN identifiers from:
+1. The Approvals file (all rows)
+2. The Interventions Index (all rows, if available)
+
+Union both sets (deduplicated). This is the full list to reconcile.
+
+For each entry, retain the **original padded identifier** from the source file (e.g., `INT-001`) as the canonical form — this is what is used in file-system glob operations. Stripping leading zeros is applied **only when comparing two identifiers from different sources** to determine whether they refer to the same intervention (e.g., `INT-001` and `INT-1` are treated as equal for deduplication only).
+
+## Step 6 — For each intervention, collect data
+
+For each INT-NNN in the unified list:
+
+**a. Doc file status:**
+- Glob `docs/assessments/{PREFIX}/{PREFIX}-{INT-NNN}-*.md`
+- If one or more files found: `✅ present`
+- If no files found: `❌ missing`
+
+**b. In Approvals:**
+- `Yes` if INT-NNN is in the Approvals table, `No` otherwise
+
+**c. Flagged value:**
+- From Approvals table: `Yes`, `No`, or `⚠️ malformed ({value})` if not exactly `Yes`/`No`
+- If INT-NNN not in Approvals: `n/a`
+
+**d. In Interventions Index:**
+- `Yes` if INT-NNN is in the Index, `No` otherwise (or `—` if index unavailable)
+
+**e. Title and Criticality:**
+- From Interventions Index if available; else `—`
+
+**f. Actioned status (only for interventions where Flagged = Yes):**
+- Glob `internal_docs/features/FTR-*/` and `docs/features/FTR-*/`
+- For each feature folder, apply the two-step heuristic:
+  1. **Slug match:** folder name contains the INT-NNN slug (case-insensitive substring)
+  2. **Body match (fallback):** read `feature.md`; body contains the INT-NNN identifier string (case-insensitive)
+- If a match is found: `✅ actioned → {matched-folder}`
+- If no match: `⏳ pending`
+- If Flagged is not `Yes`: `n/a`
+
+## Step 7 — Render reconciliation table
+
+```
+📊 Intervention Reconciliation — {PREFIX}
+════════════════════════════════════════════════════════════════
+
+| INT-NNN | Title          | Criticality | Flagged | Doc file    | Actioned         |
+|---------|----------------|-------------|---------|-------------|------------------|
+| INT-001 | {title}        | CRITICAL    | Yes     | ✅ present  | ✅ actioned → FTR-010-... |
+| INT-002 | {title}        | HIGH        | Yes     | ✅ present  | ⏳ pending       |
+| INT-003 | {title}        | MEDIUM      | No      | ❌ missing  | n/a              |
+| INT-004 | {title}        | LOW         | No      | ✅ present  | n/a              |
+
+Total: {N} interventions | {K} flagged | {A} actioned | {P} pending
+```
+
+If `index_available = false`, note above the table:
+```
+⚠️ Interventions Index not found — Title and Criticality columns not available.
+```
+
+## Step 8 — Render inconsistency list
+
+Collect all inconsistencies:
+
+- For each INT-NNN in Approvals that is NOT in the Interventions Index (when index available):
+  `INT-NNN: present in Approvals but not in Interventions Index`
+- For each INT-NNN in Interventions Index that is NOT in Approvals (when index available):
+  `INT-NNN: present in Interventions Index but missing from Approvals`
+- For each row in Approvals where `Flagged` is not exactly `Yes` or `No`:
+  `INT-NNN: malformed Flagged value '{value}' (expected 'Yes' or 'No')`
+
+If no inconsistencies:
+```
+────────────────────────────────────────
+✅ No inconsistencies found.
+════════════════════════════════════════════════════════════════
+```
+
+If inconsistencies exist:
+```
+────────────────────────────────────────
+⚠️ Inconsistencies ({N}):
+  • INT-NNN: present in Approvals but not in Interventions Index
+  • INT-NNN: malformed Flagged value 'Approved' (expected 'Yes' or 'No')
+════════════════════════════════════════════════════════════════
+```

package/.claude/commands/next-intervention.md

@@ -0,0 +1,113 @@
+---
+description: "Next Intervention — finds the next un-actioned flagged intervention from an assessment run and suggests the /define-feature invocation to start on it. Usage: /next-intervention [prefix]"
+argument-hint: "[assessment-prefix]"
+allowed-tools: Read, Glob, Grep
+---
+
+Find the next un-actioned flagged intervention from a completed assessment run.
+
+## Step 1 — Resolve prefix
+
+If `$ARGUMENTS` is empty:
+- Glob `docs/assessments/ASSESS-*/` to list available assessment folders.
+- Output the list and say: "Please specify a prefix from the list above (e.g. `/next-intervention ASSESS-001`)."
+- STOP.
+
+Otherwise:
+- If the argument is digits-only (e.g. `001`), prepend `ASSESS-` to form `ASSESS-001`.
+- Strip any trailing slash.
+- Use this as `{PREFIX}` for all subsequent steps.
+
+## Step 2 — Check assessment directory
+
+If `docs/assessments/{PREFIX}/` does not exist:
+```
+❌ Assessment directory not found: docs/assessments/{PREFIX}/
+   Run /assess-codebase to start a new assessment.
+```
+STOP.
+
+## Step 3 — Read Approvals file
+
+File path: `docs/assessments/{PREFIX}/{PREFIX}-Approvals.md`
+
+If the file does not exist:
+```
+❌ Approvals file not found: docs/assessments/{PREFIX}/{PREFIX}-Approvals.md
+   The assessment pipeline's Findings Gate must complete before this command can run.
+```
+STOP.
+
+Read the file. If it does NOT contain the section heading `## Interventions Flagged for Feature Delivery`:
+```
+❌ This Approvals file uses a pre-FTR-003 format (missing "Interventions Flagged for Feature Delivery" section).
+   This command requires the FTR-003 format produced by assessment-manager Phase 5.
+```
+STOP.
+
+## Step 4 — Extract flagged interventions
+
+Parse the Markdown table under `## Interventions Flagged for Feature Delivery`.
+- Extract all rows where the `Flagged` column value is exactly `Yes` (case-sensitive).
+- Preserve document order (top-to-bottom).
+
+If no rows are flagged:
+```
+ℹ️ No interventions were flagged for feature delivery in this assessment.
+```
+STOP.
+
+## Step 5 — Check for matching feature folders
+
+Glob both:
+- `internal_docs/features/FTR-*/`
+- `docs/features/FTR-*/`
+
+For each flagged intervention, determine whether it is "actioned" using this two-step heuristic (attempt slug match first, then body match as fallback):
+
+1. **Slug match:** Does any feature folder name contain the INT-NNN slug from the `Intervention` column (case-insensitive substring)?
+   - The `Intervention` column format is `INT-NNN — {slug}` (e.g. `INT-001 — sql-injection-hardening`). The slug is the part after ` — `.
+2. **Body match (fallback):** For any folder that did NOT match by slug, read its `feature.md` and check whether the INT-NNN identifier string (e.g. `INT-001`) appears anywhere in the body (case-insensitive).
+
+An intervention is "actioned" if either check returns true for at least one feature folder.
+
+Normalise INT-NNN identifiers by stripping leading zeros before comparison (e.g. `INT-001` and `INT-1` are the same).
+
+## Step 6 — Find the first un-actioned intervention
+
+Scan the flagged interventions in document order and find the first one that is NOT actioned.
+
+If all flagged interventions are actioned:
+```
+✅ All flagged interventions have been actioned. ({N} of {N} flagged)
+
+Actioned interventions:
+  • INT-001 — {slug} → {matched-feature-folder}
+  • INT-002 — {slug} → {matched-feature-folder}
+  ...
+```
+STOP.
+
+## Step 7 — Output the next un-actioned intervention
+
+Construct the document path:
+```
+docs/assessments/{PREFIX}/{PREFIX}-{INT-NNN}-{slug}.md
+```
+(Glob `docs/assessments/{PREFIX}/{PREFIX}-{INT-NNN}-*.md` to find the actual filename if the slug in the path differs from the Approvals column.)
+
+Output:
+
+```
+🔖 Next un-actioned intervention: {INT-NNN} — {slug}
+
+   Document path:    docs/assessments/{PREFIX}/{PREFIX}-{INT-NNN}-{slug}.md
+   Suggested command: /define-feature docs/assessments/{PREFIX}/{PREFIX}-{INT-NNN}-{slug}.md
+```
+
+If some interventions were already actioned, append:
+```
+Previously actioned ({K} of {N} flagged):
+  • INT-001 — {slug} → {matched-feature-folder}
+  ...
+```

package/.claude/settings.json

@@ -0,0 +1,5 @@
+{
+  "env": {
+    "CLAUDE_CODE_MAX_SUBAGENT_SPAWN_DEPTH": "2"
+  }
+}