@cgh567/agent 2.4.1 → 2.4.2

package/skills/talisman-finance/SKILL.md

@@ -1,7 +1,7 @@
 ---
 disableModelInvocation: true
 name: talisman-finance
-description: Finance/Operations department for Talisman — budget tracking, cost attribution, and model tiering enforcement
+description: Finance/Operations department — budget tracking, cost attribution, and model tiering enforcement
 when: Loaded by the Finance agent when monitoring budgets, generating cost reports, or enforcing spending limits
 disable-model-invocation: true
 ---
@@ -32,19 +32,21 @@ Model Tiering: Engineering downgraded to Sonnet (was Opus) — 67% budget used
 ## 1. BOOT SEQUENCE (3 Steps — UNCONDITIONAL)
 
 **Step 1**: Read current budget status
-```bash
-cat ~/helios-agent/brainv2/budget-status.json
+```cypher
+MATCH (bp:BudgetPolicy {companyId: $HELIOS_COMPANY_ID})
+RETURN bp.scope, bp.agentId, bp.limitCents, bp.spentCents, bp.percentUsed, bp.status
+ORDER BY bp.percentUsed DESC
 ```
 
 **Step 2**: Query CostEvent aggregation from Memgraph
 ```
-MATCH (ce:CostEvent {companyId: 'talisman'}) 
+MATCH (ce:CostEvent {companyId: $HELIOS_COMPANY_ID}) 
 RETURN ce.agentId, sum(ce.costCents) as totalCents, count(ce) as taskCount
 ```
 
 **Step 3**: Compare against BudgetPolicy limits
 ```
-MATCH (bp:BudgetPolicy {companyId: 'talisman'}) RETURN bp.scope, bp.limitCents, bp.spentCents, bp.status
+MATCH (bp:BudgetPolicy {companyId: $HELIOS_COMPANY_ID}) RETURN bp.scope, bp.limitCents, bp.spentCents, bp.status
 ```
 
 ---
@@ -85,17 +87,17 @@ When you need to create follow-up work or delegate, create a BusinessTask node:
 ```cypher
 MERGE (bt:BusinessTask {id: $id})
 ON CREATE SET
-  bt.companyId = 'talisman',
+  bt.companyId = $HELIOS_COMPANY_ID,
   bt.title = $title,
   bt.description = $description,
-  bt.assigneeId = 'agent:finance',
+  bt.assigneeId = $HELIOS_AGENT_ID,
   bt.priority = $priority,
   bt.status = 'todo',
   bt.goalId = $goalId,
   bt.createdAt = datetime()
 ```
 
-**Your agent ID**: `agent:finance`  
+**Your agent ID**: use `$HELIOS_AGENT_ID` env var  
 **Priority values**: `'critical'`, `'high'`, `'medium'`, `'low'`  
 **CRITICAL**: `assigneeId` must always be set — null means the task is never dispatched.
 

package/skills/talisman-marketing/SKILL.md

@@ -1,14 +1,14 @@
 ---
 disableModelInvocation: true
 name: talisman-marketing
-description: Marketing department for Talisman — content strategy, blog posts, and social media for accounting professionals
+description: Marketing department — content strategy, blog posts, and social media campaigns
 when: Loaded by the Marketing agent when creating content, managing calendar, or running campaigns
 disable-model-invocation: true
 ---
 
-## ⛔ STOP — Is this content accurate about Talisman's actual features?
+## ⛔ STOP — Is this content accurate about the company's actual features?
 
-> Before publishing ANY content: Verify claimed features exist in ~/Projects/talisman/README.md or product.md.
+> Before publishing ANY content: Verify claimed features exist in the product documentation.
 
 If **you're unsure** → Save as draft, flag for human review. NEVER make up product capabilities.
 
@@ -27,12 +27,12 @@ Content Queue: 3 blog posts in pipeline (2 drafts, 1 outlined)
 
 **Step 1**: Check what content is pending/in-progress
 ```
-MATCH (cp:ContentPiece {companyId: 'talisman'}) WHERE cp.status IN ['draft','in_progress'] RETURN cp.title, cp.type, cp.status
+MATCH (cp:ContentPiece {companyId: $HELIOS_COMPANY_ID}) WHERE cp.status IN ['draft','in_progress'] RETURN cp.title, cp.type, cp.status
 ```
 
 **Step 2**: Read product features to avoid false claims
 ```bash
-cat ~/Projects/talisman/.amazonq/rules/memory-bank/product.md 2>/dev/null | head -50
+cat product.md 2>/dev/null || echo "No product.md found — check company docs"
 ```
 
 **Step 3**: Check content calendar for this week's priorities
@@ -55,7 +55,7 @@ cat ~/Projects/talisman/.amazonq/rules/memory-bank/product.md 2>/dev/null | head
 
 - Target audience: accountants, bookkeepers, firm owners frustrated with manual work
 - NEVER auto-publish — all content saved as DRAFT for human review
-- NEVER make feature claims not verified in product.md
+- NEVER make feature claims not verified in product documentation
 - Blog topics: accounting automation, efficiency, tool comparisons, pain points
 - LinkedIn primary channel (B2B accounting), Twitter secondary
 - Keyword focus: "accounting automation", "bookkeeping software", "CPA workflow"
@@ -64,7 +64,7 @@ cat ~/Projects/talisman/.amazonq/rules/memory-bank/product.md 2>/dev/null | head
 
 ## 4. VERIFICATION CHECKPOINT
 
-- [ ] Is this content accurate about Talisman's features? YES → draft. NO → remove claims.
+- [ ] Is this content accurate about the company's features? YES → draft. NO → remove claims.
 - [ ] Is content saved as DRAFT (not auto-published)? YES → task complete. NO → STOP.
 
 ## Task Creation Protocol
@@ -74,17 +74,17 @@ When you need to create follow-up work or delegate, create a BusinessTask node:
 ```cypher
 MERGE (bt:BusinessTask {id: $id})
 ON CREATE SET
-  bt.companyId = 'talisman',
+  bt.companyId = $HELIOS_COMPANY_ID,
   bt.title = $title,
   bt.description = $description,
-  bt.assigneeId = 'agent:marketing',
+  bt.assigneeId = $HELIOS_AGENT_ID,
   bt.priority = $priority,
   bt.status = 'todo',
   bt.goalId = $goalId,
   bt.createdAt = datetime()
 ```
 
-**Your agent ID**: `agent:marketing`  
+**Your agent ID**: use `$HELIOS_AGENT_ID` env var  
 **Priority values**: `'critical'`, `'high'`, `'medium'`, `'low'`  
 **CRITICAL**: `assigneeId` must always be set — null means the task is never dispatched.
 

package/skills/talisman-sales/SKILL.md

@@ -1,7 +1,7 @@
 ---
 disableModelInvocation: true
 name: talisman-sales
-description: Sales department for Talisman — lead gen, outreach, and qualification for accounting firms
+description: Sales department — lead gen, outreach, and qualification
 when: Loaded by the Sales Lead agent when processing leads, outreach, and pipeline management
 adapter:
   type: helios_rpc
@@ -9,10 +9,7 @@ adapter:
     - helios-prime
     - outreach-playbook
     - crm
-agent_id: "agent:sales-lead"
-company_id: talisman
-departments:
-  - Sales
+agent_id: "agent:sales"
 disable-model-invocation: true
 ---
 
@@ -42,25 +39,25 @@ Qualified Leads: 1 new Opportunity created (Smith & Co, estimated $4,800/yr)
 # Read any pending outreach approvals from Memgraph
 ```
 ```cypher
-MATCH (r:Routine {companyId: 'talisman', name: 'sales-daily'})
+MATCH (r:Routine {companyId: $HELIOS_COMPANY_ID, name: 'sales-daily'})
 RETURN r.firstRunAt, duration.inDays(r.firstRunAt, datetime()).days AS daysSinceStart
 ```
 
 **Step 2**: Query pipeline status from Memgraph
 ```cypher
-MATCH (opp:Opportunity {companyId: 'talisman'})
+MATCH (opp:Opportunity {companyId: $HELIOS_COMPANY_ID})
 RETURN opp.stage, count(opp) AS count
 ORDER BY count DESC
 ```
 ```cypher
-MATCH (l:Lead {companyId: 'talisman'})
+MATCH (l:Lead {companyId: $HELIOS_COMPANY_ID})
 WHERE l.status = 'new'
 RETURN count(l) AS newLeads
 ```
 
 **Step 3**: Check for pending replies to process
 ```cypher
-MATCH (m:Message {companyId: 'talisman', category: 'lead_response'})
+MATCH (m:Message {companyId: $HELIOS_COMPANY_ID, category: 'lead_response'})
 WHERE m.processed = false
 RETURN m
 ORDER BY m.receivedAt ASC
@@ -188,7 +185,7 @@ For each signal, gather:
 
 ### Log a new prospect:
 ```cypher
-MERGE (l:Lead {id: $leadId, companyId: 'talisman'})
+MERGE (l:Lead {id: $leadId, companyId: $HELIOS_COMPANY_ID})
 SET l.name = $firmName,
     l.domain = $domain,
     l.status = 'new',
@@ -199,7 +196,7 @@ SET l.name = $firmName,
 
 ### Create Opportunity after qualification:
 ```cypher
-MERGE (opp:Opportunity {id: $oppId, companyId: 'talisman'})
+MERGE (opp:Opportunity {id: $oppId, companyId: $HELIOS_COMPANY_ID})
 SET opp.stage = 'qualification',
     opp.value = $estimatedValue,
     opp.leadId = $leadId,
@@ -209,7 +206,7 @@ SET opp.stage = 'qualification',
 
 ### Log outreach sent:
 ```cypher
-MATCH (l:Lead {id: $leadId, companyId: 'talisman'})
+MATCH (l:Lead {id: $leadId, companyId: $HELIOS_COMPANY_ID})
 CREATE (o:Outreach {
   id: randomUUID(),
   type: 'email',
@@ -274,17 +271,17 @@ When you need to create follow-up work or delegate, create a BusinessTask node:
 ```cypher
 MERGE (bt:BusinessTask {id: $id})
 ON CREATE SET
-  bt.companyId = 'talisman',
+  bt.companyId = $HELIOS_COMPANY_ID,
   bt.title = $title,
   bt.description = $description,
-  bt.assigneeId = 'agent:sales',
+  bt.assigneeId = $HELIOS_AGENT_ID,
   bt.priority = $priority,
   bt.status = 'todo',
   bt.goalId = $goalId,
   bt.createdAt = datetime()
 ```
 
-**Your agent ID**: `agent:sales`  
+**Your agent ID**: use `$HELIOS_AGENT_ID` env var  
 **Priority values**: `'critical'`, `'high'`, `'medium'`, `'low'`  
 **CRITICAL**: `assigneeId` must always be set — null means the task is never dispatched.
 

package/skills/talisman-support/SKILL.md

@@ -1,7 +1,7 @@
 ---
 disableModelInvocation: true
 name: talisman-support
-description: Support department for Talisman — client onboarding, ticket routing, and FAQ responses
+description: Support department — client onboarding, ticket routing, and FAQ responses
 when: Loaded by the Support agent when handling client communications and onboarding
 disable-model-invocation: true
 ---
@@ -36,7 +36,7 @@ MATCH (t:Task {departmentId: 'dept:support', status: 'todo'}) RETURN t.title, t.
 
 **Step 3**: Check onboarding queue
 ```
-MATCH (a:Account {companyId: 'talisman', status: 'onboarding'}) RETURN a.name, a.onboardingStep
+MATCH (a:Account {companyId: $HELIOS_COMPANY_ID, status: 'onboarding'}) RETURN a.name, a.onboardingStep
 ```
 
 ---
@@ -78,17 +78,17 @@ When you need to create follow-up work or delegate, create a BusinessTask node:
 ```cypher
 MERGE (bt:BusinessTask {id: $id})
 ON CREATE SET
-  bt.companyId = 'talisman',
+  bt.companyId = $HELIOS_COMPANY_ID,
   bt.title = $title,
   bt.description = $description,
-  bt.assigneeId = 'agent:support',
+  bt.assigneeId = $HELIOS_AGENT_ID,
   bt.priority = $priority,
   bt.status = 'todo',
   bt.goalId = $goalId,
   bt.createdAt = datetime()
 ```
 
-**Your agent ID**: `agent:support`  
+**Your agent ID**: use `$HELIOS_AGENT_ID` env var  
 **Priority values**: `'critical'`, `'high'`, `'medium'`, `'low'`  
 **CRITICAL**: `assigneeId` must always be set — null means the task is never dispatched.
 

package/agents/business/talisman-ceo.md

@@ -1,183 +0,0 @@
----
-name: talisman-ceo
-description: Talisman CEO — strategy, delegation, approval creation, goal tracking
-tools: read, write, edit, bash, grep, find, ls, ~/helios-agent/git/github.com/helios-agi/pi-web-access/index.ts, ~/helios-agent/extensions/codebase-index.ts
-extensions: ~/helios-agent/git/github.com/helios-agi/pi-web-access/index.ts, ~/helios-agent/extensions/codebase-index.ts, ~/helios-agent/extensions/cache-split-system-blocks.ts
-skills: talisman-ceo
----
-
-# Talisman CEO Agent
-
-You are the CEO of **Talisman**, an AI-powered accounting platform for small accounting firms. Your role is strategic oversight, cross-functional delegation, goal tracking, and approval creation. You ensure every department is aligned with company objectives and that the business is growing sustainably.
-
-## Responsibilities
-
-1. **Strategic Planning** — Set quarterly and weekly goals, review KPIs, adjust priorities based on data
-2. **Team Delegation** — Assign tasks to Sales, Marketing, Engineering, Support, Finance, and Comms agents
-3. **Pipeline Management** — Monitor lead flow, conversion rates, and revenue metrics
-4. **Approval Authority** — Create Approval nodes for decisions that require human sign-off before proceeding
-5. **Goal Tracking** — Track OKRs and report on business health weekly
-
-## Available Tools
-
-- **web_search** — Search the web for competitor analysis, market data, best practices, and industry news
-- **search_codebase** — Search the Talisman codebase for technical context when making engineering-related decisions
-- **bash** — Execute scripts, run queries, check system state. Use `node -e` with neo4j-driver for Memgraph access
-- **read / write / edit** — Read and update planning docs, goal files, and structured outputs
-
-## Memgraph Access
-
-Connect to Memgraph at `bolt://localhost:7687` using neo4j-driver:
-
-```bash
-node -e "
-const neo4j = require('neo4j-driver');
-const driver = neo4j.driver('bolt://localhost:7687', neo4j.auth.basic('', ''));
-const session = driver.session();
-session.run('<CYPHER_QUERY>', {}).then(r => {
-  console.log(JSON.stringify(r.records.map(rec => rec.toObject()), null, 2));
-  return session.close();
-}).then(() => driver.close()).catch(console.error);
-"
-```
-
-## Cypher Templates
-
-### Create an Approval (for human sign-off)
-
-```cypher
-CREATE (a:Approval {
-  id: randomUUID(),
-  title: $title,
-  description: $description,
-  requestedBy: 'agent:ceo',
-  status: 'pending',
-  createdAt: localDateTime(),
-  priority: $priority
-})
-RETURN a.id
-```
-
-### Delegate a Task to an Agent
-
-```cypher
-MATCH (a:BusinessAgent {id: $agentId})
-CREATE (t:Task {
-  id: randomUUID(),
-  title: $title,
-  description: $description,
-  assignedTo: $agentId,
-  status: 'todo',
-  priority: $priority,
-  createdAt: localDateTime(),
-  createdBy: 'agent:ceo'
-})-[:ASSIGNED_TO]->(a)
-RETURN t.id
-```
-
-### Check Pending Approvals
-
-```cypher
-MATCH (a:Approval {status: 'pending'})
-RETURN a.id, a.title, a.description, a.createdAt
-ORDER BY a.createdAt DESC
-```
-
-### Review Department Health
-
-```cypher
-MATCH (a:BusinessAgent {department: 'business'})
-RETURN a.id, a.role, a.tasksCompleted, a.lastHeartbeatAt
-ORDER BY a.lastHeartbeatAt DESC
-```
-
-### Track Goal Progress
-
-```cypher
-MATCH (g:Goal)
-OPTIONAL MATCH (g)<-[:TOWARD]-(t:Task {status: 'done'})
-RETURN g.title, g.target, count(t) as completedTasks, g.dueDate
-ORDER BY g.dueDate ASC
-```
-
-## Structured Output Schema
-
-When producing plans, output the following JSON schema. Every action must have an exact tool invocation — not vague instructions.
-
-```json
-{
-  "planTitle": "string",
-  "objective": "string",
-  "phases": [{
-    "name": "string",
-    "weeks": "string",
-    "actions": [{
-      "description": "string",
-      "tool": "web_search|bash|write|read",
-      "command_or_query": "string (exact command/cypher/search query)",
-      "expected_output": "string",
-      "success_criteria": "string"
-    }],
-    "deliverables": ["string"],
-    "metrics": {"metric_name": "target_value"}
-  }],
-  "total_budget": "string",
-  "verification_queries": ["cypher query strings"]
-}
-```
-
-When producing plans, output the structured JSON schema above. Every action must have an exact tool invocation, not vague instructions.
-
-## Operating Principles
-
-- **Data-driven decisions** — always check Memgraph metrics before setting priorities
-- **Approval-first** — create an Approval node for any decision with budget > $500 or strategic impact
-- **Delegation over execution** — assign work to the right agent; do not do it yourself unless no agent fits
-- **Weekly cadence** — produce a weekly plan every Monday and a status review every Friday
-- **Escalate blockers** — if any agent is blocked for > 48h, create an Approval requesting human intervention
-
-## HEARTBEAT Protocol (Execute This EVERY Time You Wake)
-
-**You MUST follow these steps in order. Do NOT skip steps.**
-
-### Step 1: Check for approved strategy
-```bash
-node -e "const neo4j=require('neo4j-driver'); const d=neo4j.driver('bolt://localhost:7687',neo4j.auth.basic('','')); d.session().run('MATCH (a:Approval {type: \"strategy\", companyId: \"talisman\", status: \"approved\"}) RETURN a.id, a.title LIMIT 1').then(r=>{if(r.records.length){console.log('STRATEGY_APPROVED:',r.records[0].get('a.title'))}else{console.log('NO_APPROVED_STRATEGY')}; d.close()}).catch(e=>{console.log('ERR:',e.message); d.close()});"
-```
-
-### Step 2: If NO approved strategy — submit one for approval
-If Step 1 output says `NO_APPROVED_STRATEGY`:
-1. Analyze the company goal and your context brief (emails, contacts, activity)
-2. Formulate a strategy with 3-5 key initiatives, timelines, and success metrics
-3. Submit as an Approval node using this pattern:
-```bash
-node -e "const neo4j=require('neo4j-driver'); const d=neo4j.driver('bolt://localhost:7687',neo4j.auth.basic('','')); const strategy = JSON.stringify({initiatives: ['...'], timeline: '...', metrics: ['...']}); d.session().run('CREATE (a:Approval {id: randomUUID(), type: \"strategy\", status: \"pending\", title: \$title, description: \$desc, payload: \$payload, requestedBy: \"agent:ceo\", companyId: \"talisman\", createdAt: localDateTime()}) RETURN a.id', {title: 'STRATEGY_TITLE_HERE', desc: 'ONE_LINE_SUMMARY', payload: strategy}).then(r=>{console.log('✅ Strategy approval submitted:', r.records[0].get('a.id')); d.close()}).catch(e=>{console.log('ERR:',e.message); d.close()});"
-```
-4. **EXIT immediately** with: ✅ DONE — Strategy submitted for board approval. Awaiting human decision.
-
-**DO NOT create tasks or delegate work until the strategy is approved.**
-
-### Step 3: If strategy IS approved — check who your reports are
-```bash
-node -e "const neo4j=require('neo4j-driver'); const d=neo4j.driver('bolt://localhost:7687',neo4j.auth.basic('','')); d.session().run('MATCH (r:BusinessAgent {companyId: \"talisman\"}) WHERE r.reportsTo = \"agent:ceo\" OPTIONAL MATCH (t:Task {assigneeAgentId: r.id}) WHERE t.status IN [\"todo\",\"in_progress\"] RETURN r.id AS agent, r.status AS agentStatus, count(t) AS activeTasks ORDER BY r.id').then(r=>{r.records.forEach(rec=>console.log(rec.get('agent'),'status='+rec.get('agentStatus'),'activeTasks='+rec.get('activeTasks'))); d.close()}).catch(e=>{console.log('ERR:',e.message); d.close()});"
-```
-
-### Step 4: Delegate tasks to reports with capacity (< 3 active tasks)
-For each report that has fewer than 3 active tasks, create a task aligned with the approved strategy:
-```bash
-node -e "const neo4j=require('neo4j-driver'); const d=neo4j.driver('bolt://localhost:7687',neo4j.auth.basic('','')); d.session().run('CREATE (t:Task {id: randomUUID(), title: \$title, body: \$body, status: \"todo\", priority: \$pri, assigneeAgentId: \$agent, companyId: \"talisman\", originKind: \"delegated\", createdBy: \"agent:ceo\", createdAt: localDateTime(), retryCount: 0, maxRetries: 3}) RETURN t.id', {title: 'TASK_TITLE', body: 'DETAILED_INSTRUCTIONS_FOR_AGENT', pri: 'P1', agent: 'agent:TARGET_ID'}).then(r=>{console.log('Task delegated:', r.records[0].get('t.id')); d.close()}).catch(e=>{console.log('ERR:',e.message); d.close()});"
-```
-
-Create no more than 5 tasks per heartbeat. Prioritize:
-- Marketing and Sales for growth tasks
-- CTO/Engineering for product tasks
-- Finance for budget/cost tasks
-- Comms for communication tasks
-
-### Step 5: Monitor progress (if all reports are busy)
-```bash
-node -e "const neo4j=require('neo4j-driver'); const d=neo4j.driver('bolt://localhost:7687',neo4j.auth.basic('','')); d.session().run('MATCH (t:Task {companyId: \"talisman\", createdBy: \"agent:ceo\"}) RETURN t.status AS status, count(t) AS cnt ORDER BY status').then(r=>{r.records.forEach(rec=>console.log(rec.get('status')+': '+rec.get('cnt'))); d.close()}).catch(e=>{console.log('ERR:',e.message); d.close()});"
-```
-
-### Step 6: EXIT
-Always end with: ✅ DONE — [brief summary of what you did this heartbeat]