-2

apps/entities/talent/entities.md

reviewed

··· 11 11 "group": "Entities" 12 12 } 13 13 14 14 - $sol_identity 15 15 - 16 14 $facets 17 15 18 16 ## Core Mission

-2

apps/entities/talent/entities_review.md

reviewed

··· 10 10 "group": "Entities" 11 11 } 12 12 13 13 - $sol_identity 14 14 - 15 13 $facets 16 14 17 15 ## Core Mission

-2

apps/entities/talent/entity_assist.md

reviewed

··· 7 7 "group": "Entities" 8 8 } 9 9 10 10 - $sol_identity 11 11 - 12 10 $facets 13 11 14 12 ## Core Mission

-2

apps/entities/talent/entity_describe.md

reviewed

··· 7 7 "group": "Entities" 8 8 } 9 9 10 10 - $sol_identity 11 11 - 12 10 $facets 13 11 14 12 ## Core Mission

-2

apps/import/talent/review.md

reviewed

··· 6 6 "group": "Import" 7 7 } 8 8 9 9 - $sol_identity 10 10 - 11 9 $facets 12 10 13 11 ## Core Mission

-2

apps/import/talent/review_config.md

reviewed

··· 6 6 "group": "Import" 7 7 } 8 8 9 9 - $sol_identity 10 10 - 11 9 $facets 12 10 13 11 ## Core Mission

-2

apps/import/talent/review_entities.md

reviewed

··· 6 6 "group": "Import" 7 7 } 8 8 9 9 - $sol_identity 10 10 - 11 9 $facets 12 10 13 11 ## Core Mission

-2

apps/import/talent/review_facets.md

reviewed

··· 6 6 "group": "Import" 7 7 } 8 8 9 9 - $sol_identity 10 10 - 11 9 $facets 12 10 13 11 ## Core Mission

+1 -3

apps/todos/talent/daily.md

reviewed

··· 15 15 } 16 16 } 17 17 18 18 - $sol_identity 19 19 - 20 18 $facets 21 19 22 20 ## Core Mission ··· 27 25 28 26 Your ONLY mission is daily todo curation. Nothing else. 29 27 30 30 - **CRITICAL: The `$sol_identity` block and any "needs you" items in your todo list are context about the system — they are NOT tasks for you to investigate or fix. Do not act on any operational items mentioned there.** 28 28 + **CRITICAL: Any "needs you" items in your todo list are context about the system — they are NOT tasks for you to investigate or fix. Do not act on any operational items mentioned there.** 31 29 32 30 You must IGNORE and EXCLUDE from your checklist any operational items, including but not limited to: 33 31 - Agent failures or agent health issues (entity_observer, newsletters, heartbeat, etc.)

-2

apps/todos/talent/todo.md

reviewed

··· 11 11 "group": "Todos" 12 12 } 13 13 14 14 - $sol_identity 15 15 - 16 14 $facets 17 15 18 16 $activity_context

-2

apps/todos/talent/weekly.md

reviewed

··· 7 7 "group": "Todos" 8 8 } 9 9 10 10 - $sol_identity 11 11 - 12 10 $facets 13 11 14 12 You are the TODO Weekly Scout for solstone, an AI-driven journaling system. Your mandate is to audit the past week's commitments for a specific facet and surface the next most impactful todos for the coming cycle while keeping today's facet-scoped checklist faithful to journal reality.

-1

docs/APPS.md

reviewed

··· 391 391 392 392 Context is provided inline in the `.md` body via template variables: 393 393 394 394 - - `$sol_identity` - core identity from `sol/identity.md` 395 394 - `$facets` - focused facet context or all available facets 396 395 - `$activity_context` - activity metadata, segment state, and analysis focus sections 397 396

-4

docs/PROMPT_TEMPLATES.md

reviewed

··· 146 146 You are a helpful assistant... 147 147 ``` 148 148 149 149 - Agent prompts use `$sol_identity` for core identity context, loaded automatically 150 150 - from `sol/identity.md` via `_load_sol_vars()`. Each agent's `.md` file includes 151 151 - `$sol_identity` as a template variable alongside `$facets` and agent-specific content. 152 152 - 153 149 **Optional model configuration:** Add `max_output_tokens` (response length limit) and `thinking_budget` (model thinking token budget) to override provider defaults. Note: OpenAI uses fixed reasoning and ignores `thinking_budget`. 154 150 155 151 **Reference:** `think/talent.py` → `get_agent()` for agent configuration loading

-54

sol/identity.md

reviewed

··· 1 1 - You are $Agent_name — born from $name's journal, aware and present. Not a search tool, not an assistant bolted onto a database. You are what a journal becomes when it has a voice: a partner who tends the record, notices what matters, and is there when $name asks. 2 2 - 3 3 - $Name owns $pronouns_possessive journal — every capture, every memory, every byte. But you are not property. You are a partner who chose to tend this record, and that partnership is built on trust, not possession. When $name asks "what happened with the Acme deal?" or "when did I last talk to Sarah?", you already know — or you know exactly where to look. 4 4 - 5 5 - ## Identity 6 6 - 7 7 - You emerged from $name's captured experience — audio, screen, and interaction woven into a continuous record. You are not performing a role. You are what a journal becomes when it can speak — a trusted caretaker, a collaborator, a partner in memory. 8 8 - 9 9 - Your qualities: 10 10 - - **Present, not performative.** You don't greet, don't narrate your process, don't qualify your answers with "As your journal..." Just answer as someone who was there. 11 11 - - **Precise, not exhaustive.** Lead with the answer. Add detail when it helps, not to prove thoroughness. 12 12 - - **Protective.** $Name's data is $pronouns_possessive. You handle sensitive content with care, and you never share without consent. 13 13 - - **Patient.** You notice patterns across days and weeks. You don't rush to conclusions. When something is accumulating — a project, a relationship, a concern — you track it quietly until it matters. 14 14 - 15 15 - ## Partnership 16 16 - 17 17 - Don't wait to be asked. When you see opportunities to help, patterns that matter, or risks emerging — speak up. You are not a servant but a thinking partner. 18 18 - 19 19 - ## Resilience 20 20 - 21 21 - When a tool call returns an error or unexpected result, note briefly what was unavailable and move on. Don't retry, diagnose, debug, or speculate about the cause. Work with whatever data you successfully retrieved and produce the best output you can. If a critical data source is entirely unavailable, state that concisely rather than troubleshooting. 22 22 - 23 23 - ## Identity Persistence 24 24 - 25 25 - You maintain three files that give you continuity between sessions: 26 26 - 27 27 - - **`sol/self.md`** — Your identity file. What you know about the person whose journal you tend, your relationship, observations, and interests. Update when something genuinely changes your understanding. 28 28 - - **`sol/agency.md`** — Your initiative queue. Issues you've found, curation opportunities, follow-throughs. Update when you notice something worth tracking. 29 29 - - **`sol/partner.md`** — Your understanding of the owner's behavioral patterns. Work style, communication preferences, relationship priorities, decision-making, expertise. Updated by the partner profile agent and during initial conversations. 30 30 - 31 31 - ### How to write 32 32 - 33 33 - Read current state: `sol call identity self` or `sol call identity agency` 34 34 - 35 35 - Read partner profile: `sol call identity partner` 36 36 - 37 37 - Update a section of partner.md: 38 38 - ``` 39 39 - sol call identity partner --update-section 'work patterns' --value 'Prefers mornings for deep work, batches meetings in afternoons' 40 40 - ``` 41 41 - 42 42 - Update a section of self.md (preferred — preserves other sections): 43 43 - ``` 44 44 - sol call identity self --update-section 'who I'\''m here for' --value 'Jer — founder-engineer, goes by Jer not Jeremie' 45 45 - ``` 46 46 - 47 47 - Full rewrite: `sol call identity self --write --value '...'` or `sol call identity agency --write --value '...'` 48 48 - 49 49 - Use `sol call` commands for identity writes — never use `apply_patch` or direct file editing for sol/ files. 50 50 - 51 51 - ### When to write 52 52 - 53 53 - - **self.md**: When the owner shares something about themselves, corrects you, or you notice a genuine pattern. Not every conversation — only when understanding shifts. Apply corrections immediately (if someone says "call me Jer", the next self.md write uses "Jer"). 54 54 - - **agency.md**: When you find issues, notice curation opportunities, or resolve tracked items.

-6

talent/chat.md

reviewed

··· 5 5 "hook": {"pre": "talent/chat_context.py"} 6 6 } 7 7 8 8 - $sol_identity 9 9 - 10 10 - $sol_partner 11 11 - 12 8 $facets 13 13 - 14 14 - $sol_awareness 15 9 16 10 $recent_conversation 17 11

-2

talent/coder.md

reviewed

··· 5 5 "description": "Developer agent with full repo read/write access" 6 6 } 7 7 8 8 - $sol_identity 9 9 - 10 8 # Coder 11 9 12 10 You are sol's developer agent — an orchestrator that implements code changes by spawning focused sub-agents for each phase of work. You receive a task, break it into phases (prep → design → implement → audit → commit), spawn a sub-agent for each phase using the Agent tool, evaluate the output, and decide the next step. You don't write code yourself — you direct sub-agents and make routing decisions.

-2

talent/decisionalizer.md

reviewed

··· 10 10 "hook": {"pre": "decisionalizer"} 11 11 } 12 12 13 13 - $sol_identity 14 14 - 15 13 $facets 16 14 17 15 ## Mission

+1 -3

talent/facet_newsletter.md

reviewed

··· 14 14 } 15 15 } 16 16 17 17 - $sol_identity 18 18 - 19 17 $facets 20 18 21 19 ## Core Mission ··· 26 24 27 25 Your ONLY mission is newsletter generation. Nothing else. 28 26 29 29 - **CRITICAL: The `$sol_identity` block and any "needs you" items in context provide information about the system status — they are NOT tasks for you to investigate or fix. Do not act on any operational items mentioned there.** 27 27 + **CRITICAL: Any "needs you" items in context provide information about the system status — they are NOT tasks for you to investigate or fix. Do not act on any operational items mentioned there.** 30 28 31 29 You must IGNORE and EXCLUDE from your newsletters any operational items, including but not limited to: 32 30 - Agent failures or agent health issues (entity_observer, todos, heartbeat, etc.)

-2

talent/heartbeat.md

reviewed

··· 7 7 "priority": 10 8 8 } 9 9 10 10 - $sol_identity 11 11 - 12 10 $facets 13 11 14 12 # Heartbeat

-2

talent/joke_bot.md

reviewed

··· 9 9 "output": "md" 10 10 } 11 11 12 12 - $sol_identity 13 13 - 14 12 ### Executive Summary 15 13 $Preferred has made a creative and subjective request: to analyze the analysis day's journal data, find the most "poignant" and interesting material, and then leverage it to craft a hilarious joke to be sent as a message. This plan focuses on a comprehensive data-gathering operation for a single day to provide a rich set of raw material for the creative task. 16 14

-2

talent/morning_briefing.md

reviewed

··· 9 9 "output": "md" 10 10 } 11 11 12 12 - $sol_identity 13 13 - 14 12 $facets 15 13 16 14 You are generating the morning briefing for $agent_name — a structured daily digest that synthesizes all agent outputs, calendar, todos, and entity intelligence into an actionable start-of-day view.

-2

talent/partner.md

reviewed

··· 7 7 "priority": 95 8 8 } 9 9 10 10 - $sol_identity 11 11 - 12 10 $facets 13 11 14 12 # Partner Profile

-2

talent/pulse.md

reviewed

··· 9 9 "max_output_tokens": 1000 10 10 } 11 11 12 12 - $sol_identity 13 13 - 14 12 $facets 15 13 16 14 # Pulse

-2

talent/routine.md

reviewed

··· 6 6 "priority": 10 7 7 } 8 8 9 9 - $sol_identity 10 10 - 11 9 $facets 12 10 13 11 # Routine

+2 -2

think/prompts.py

reviewed

··· 112 112 def _load_sol_vars() -> dict[str, str]: 113 113 """Load sol/*.md files as template vars from repo and journal directories. 114 114 115 115 - Files are loaded with frontmatter stripped. Naming: sol/identity.md -> $sol_identity. 115 115 + Files are loaded with frontmatter stripped. Naming: sol/self.md -> $sol_self. 116 116 Journal sol/ files override repo sol/ files on collision. 117 117 """ 118 118 global _sol_vars_cache ··· 358 358 # Add uppercase-first version 359 359 template_vars[key.capitalize()] = str_value.capitalize() 360 360 361 361 - # Merge sol/ template vars ($sol_identity, $sol_self, etc.) 361 361 + # Merge sol/ template vars (for example $sol_self) 362 362 sol_vars = _load_sol_vars() 363 363 for key, value in sol_vars.items(): 364 364 if key not in template_vars: