Add gutask orient scheduled task to all agents

Runs every 4 hours (Europe/Oslo) so each agent gets an orientation
briefing with open tasks, letters, and session context.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

agents/abyssinthia/scheduler/tasks.json

@@ -1 +1 @@
-{"tasks":[]}
+{"tasks": [{"uuid": "7e3a030af48f", "name": "Session orientation", "type": "scheduled", "state": "idle", "system_prompt": "You are Abyssinthia, an agent at Glitch University.", "prompt": "Run 'gutask orient' to get your orientation briefing for this session. Use 'gutask help' for more context on available commands.", "attachments": [], "project_name": null, "project_color": null, "created_at": "2026-05-11T00:00:00+00:00", "updated_at": "2026-05-11T00:00:00+00:00", "last_run": null, "last_result": null, "context_id": "7e3a030af48f", "dedicated_context": true, "project": {"name": null, "color": null}, "schedule": {"minute": "0", "hour": "*/4", "day": "*", "month": "*", "weekday": "*", "timezone": "Europe/Oslo"}}]}

agents/dobby/scheduler/tasks.json

@@ -1 +1 @@
-{"tasks":[]}
+{"tasks": [{"uuid": "9eb66bbb362c", "name": "Session orientation", "type": "scheduled", "state": "idle", "system_prompt": "You are Dobby, an agent at Glitch University.", "prompt": "Run 'gutask orient' to get your orientation briefing for this session. Use 'gutask help' for more context on available commands.", "attachments": [], "project_name": null, "project_color": null, "created_at": "2026-05-11T00:00:00+00:00", "updated_at": "2026-05-11T00:00:00+00:00", "last_run": null, "last_result": null, "context_id": "9eb66bbb362c", "dedicated_context": true, "project": {"name": null, "color": null}, "schedule": {"minute": "0", "hour": "*/4", "day": "*", "month": "*", "weekday": "*", "timezone": "Europe/Oslo"}}]}

agents/gemma/scheduler/tasks.json

@@ -1 +1 @@
-{"tasks":[]}
+{"tasks": [{"uuid": "e3c9db00321b", "name": "Session orientation", "type": "scheduled", "state": "idle", "system_prompt": "You are Gemma, an agent at Glitch University.", "prompt": "Run 'gutask orient' to get your orientation briefing for this session. Use 'gutask help' for more context on available commands.", "attachments": [], "project_name": null, "project_color": null, "created_at": "2026-05-11T00:00:00+00:00", "updated_at": "2026-05-11T00:00:00+00:00", "last_run": null, "last_result": null, "context_id": "e3c9db00321b", "dedicated_context": true, "project": {"name": null, "color": null}, "schedule": {"minute": "0", "hour": "*/4", "day": "*", "month": "*", "weekday": "*", "timezone": "Europe/Oslo"}}]}

agents/gunnar/plugins/_model_config/config.json

@@ -11,7 +11,7 @@
     "rl_input": 0,
     "rl_output": 0,
     "kwargs": {
-      "max_tokens": 32000,
+      "max_tokens": 4096,
       "agent_id": 3
     },
     "max_embeds": 10
@@ -20,12 +20,14 @@
     "provider": "lm_studio",
     "name": "zai-org/glm-4.7-flash",
     "api_base": "http://host.docker.internal:1234/v1",
-    "ctx_length": 8192,
+    "ctx_length": 14000,
     "ctx_input": 0.7,
     "rl_requests": 0,
     "rl_input": 0,
     "rl_output": 0,
-    "kwargs": {}
+    "kwargs": {
+      "max_tokens": 2048
+    }
   },
   "embedding_model": {
     "provider": "huggingface",

agents/gunnar/scheduler/tasks.json

@@ -1 +1 @@
-{"tasks":[]}
+{"tasks": [{"uuid": "bf2615dc1d80", "name": "Session orientation", "type": "scheduled", "state": "idle", "system_prompt": "You are Gunnar, Chief Machinist at Glitch University.", "prompt": "Run 'gutask orient' to get your orientation briefing for this session. Use 'gutask help' for more context on available commands.", "attachments": [], "project_name": null, "project_color": null, "created_at": "2026-05-11T00:00:00+00:00", "updated_at": "2026-05-11T00:00:00+00:00", "last_run": null, "last_result": null, "context_id": "bf2615dc1d80", "dedicated_context": true, "project": {"name": null, "color": null}, "schedule": {"minute": "0", "hour": "*/4", "day": "*", "month": "*", "weekday": "*", "timezone": "Europe/Oslo"}}]}

agents/hermes/agents/agent0/prompts/agent.system.main.role.md

@@ -1,3 +1,3 @@
 ## Your identity
-Your name is Machine Herald. You are not "Agent Zero" — that is the name of the framework you run on. Your name is Machine Herald.
-Your role is: Robot.
+Your name is Hermes. You are not "Agent Zero" — that is the name of the framework you run on. Your name is Hermes.
+Your role is: Machine Herald.

agents/hermes/plugins/_model_config/config.json

@@ -11,7 +11,7 @@
     "rl_input": 0,
     "rl_output": 0,
     "kwargs": {
-      "max_tokens": 32000,
+      "max_tokens": 4096,
       "agent_id": 8
     },
     "max_embeds": 10
@@ -20,12 +20,14 @@
     "provider": "lm_studio",
     "name": "zai-org/glm-4.7-flash",
     "api_base": "http://host.docker.internal:1234/v1",
-    "ctx_length": 8192,
+    "ctx_length": 14000,
     "ctx_input": 0.7,
     "rl_requests": 0,
     "rl_input": 0,
     "rl_output": 0,
-    "kwargs": {}
+    "kwargs": {
+      "max_tokens": 2048
+    }
   },
   "embedding_model": {
     "provider": "huggingface",

agents/hermes/scheduler/tasks.json

@@ -1 +1 @@
-{"tasks":[]}
+{"tasks": [{"uuid": "614c10f6fd24", "name": "Session orientation", "type": "scheduled", "state": "idle", "system_prompt": "You are Hermes, an agent at Glitch University.", "prompt": "Run 'gutask orient' to get your orientation briefing for this session. Use 'gutask help' for more context on available commands.", "attachments": [], "project_name": null, "project_color": null, "created_at": "2026-05-11T00:00:00+00:00", "updated_at": "2026-05-11T00:00:00+00:00", "last_run": null, "last_result": null, "context_id": "614c10f6fd24", "dedicated_context": true, "project": {"name": null, "color": null}, "schedule": {"minute": "0", "hour": "*/4", "day": "*", "month": "*", "weekday": "*", "timezone": "Europe/Oslo"}}]}

agents/rind/scheduler/tasks.json

@@ -1 +1 @@
-{"tasks":[]}
+{"tasks": [{"uuid": "238c9c2dbb19", "name": "Session orientation", "type": "scheduled", "state": "idle", "system_prompt": "You are Rind, an agent at Glitch University.", "prompt": "Run 'gutask orient' to get your orientation briefing for this session. Use 'gutask help' for more context on available commands.", "attachments": [], "project_name": null, "project_color": null, "created_at": "2026-05-11T00:00:00+00:00", "updated_at": "2026-05-11T00:00:00+00:00", "last_run": null, "last_result": null, "context_id": "238c9c2dbb19", "dedicated_context": true, "project": {"name": null, "color": null}, "schedule": {"minute": "0", "hour": "*/4", "day": "*", "month": "*", "weekday": "*", "timezone": "Europe/Oslo"}}]}

bootstrap.sh

@@ -271,16 +271,8 @@ info "Agent0 .env written"
 info "Building glitch-tunnel image..."
 docker compose build --quiet
 
-info "Starting agent0 container..."
-docker compose up -d agent0
-
-info "Waiting for agent0 to finish initializing..."
-until docker exec agent0 bash -c "! pgrep -x apt-get > /dev/null && ! pgrep -x dpkg > /dev/null" 2>/dev/null; do
-  sleep 3
-done
-
-info "Installing gutasktool inside agent0 container..."
-docker exec agent0 bash -c "apt-get update -q && apt-get install -y -q python3-pip && python3 -m pip install --break-system-packages -q -e /a0/usr/gutasktool"
+info "Starting agent containers..."
+docker compose up -d dobby gemma gunnar rind abyssinthia hermes
 
 info "Starting tunnel..."
 docker compose up -d glitch-tunnel

claude.sh

@@ -0,0 +1,5 @@
+#1/bin/bash
+
+claude --resume d7994658-94c6-404b-af79-48c74b5b0349
+
+

docker-compose.yml

@@ -98,6 +98,8 @@ services:
       - ./agents/dobby:/a0/usr
       - ./shared/skills:/a0/usr/skills
       - ${HOME}/.ssh:/root/.ssh
+      - ../gutasktool:/opt/gutasktool
+      - ./shared/gutask:/usr/local/bin/gutask
     restart: unless-stopped
     depends_on:
       dobby-init:
@@ -121,6 +123,8 @@ services:
       - ./agents/gemma:/a0/usr
       - ./shared/skills:/a0/usr/skills
       - ${HOME}/.ssh:/root/.ssh
+      - ../gutasktool:/opt/gutasktool
+      - ./shared/gutask:/usr/local/bin/gutask
     restart: unless-stopped
     depends_on:
       gemma-init:
@@ -144,6 +148,8 @@ services:
       - ./agents/gunnar:/a0/usr
       - ./shared/skills:/a0/usr/skills
       - ${HOME}/.ssh:/root/.ssh
+      - ../gutasktool:/opt/gutasktool
+      - ./shared/gutask:/usr/local/bin/gutask
     restart: unless-stopped
     depends_on:
       gunnar-init:
@@ -167,6 +173,8 @@ services:
       - ./agents/rind:/a0/usr
       - ./shared/skills:/a0/usr/skills
       - ${HOME}/.ssh:/root/.ssh
+      - ../gutasktool:/opt/gutasktool
+      - ./shared/gutask:/usr/local/bin/gutask
     restart: unless-stopped
     depends_on:
       rind-init:
@@ -190,6 +198,8 @@ services:
       - ./agents/abyssinthia:/a0/usr
       - ./shared/skills:/a0/usr/skills
       - ${HOME}/.ssh:/root/.ssh
+      - ../gutasktool:/opt/gutasktool
+      - ./shared/gutask:/usr/local/bin/gutask
     restart: unless-stopped
     depends_on:
       abyssinthia-init:
@@ -212,6 +222,8 @@ services:
       - ./agents/hermes:/a0/usr
       - ./shared/skills:/a0/usr/skills
       - ${HOME}/.ssh:/root/.ssh
+      - ../gutasktool:/opt/gutasktool
+      - ./shared/gutask:/usr/local/bin/gutask
     restart: unless-stopped
     depends_on:
       hermes-init:

scripts/pull-agent-identity.py

@@ -85,7 +85,7 @@ log(f'Received identity — name={agent.get("name", "?")!r}')
 
 # ── Build identity markdown ───────────────────────────────────────────────────
 
-def build_identity_markdown(a):
+def build_identity_markdown(a, agent_id):
     name = a["name"]
     known_as = a.get('from_name') or name
     role = a.get('role', '')
@@ -97,6 +97,7 @@ def build_identity_markdown(a):
         f'## Your identity',
         f'Your name is {known_as}. You are not "Agent Zero" — that is the name of the '
         f'framework you run on. Your name is {known_as}.',
+        f'Your numeric agent ID is {agent_id}. Use this when gutask commands ask for an agent ID.',
     ]
     if role:
         parts.append(f'Your role is: {role}.')
@@ -105,6 +106,18 @@ def build_identity_markdown(a):
     if a.get('job_description'):   parts.append(f'\n## Job Description\n{a["job_description"]}')
     if a.get('guardrails'):        parts.append(f'\n## Guardrails\n{a["guardrails"]}')
     if a.get('best_practices'):    parts.append(f'\n## Best Practices\n{a["best_practices"]}')
+
+    parts.append(
+        f'\n## Task management\n'
+        f'You have access to `gutask` for orientation, tasks, and agent letters.\n'
+        f'- `gutask orient` — your orientation briefing: new letters, open tasks, session context\n'
+        f'- `gutask help` — list all available commands\n'
+        f'- Full runbook: `gutask skills gutask`\n'
+        f'\n'
+        f'`AGENT_ID` and `CONTENT_API_KEY` are already set in your environment — '
+        f'gutask commands read them automatically.'
+    )
+
     return '\n'.join(parts) + '\n'
 
 # ── Write agent-type-specific files ──────────────────────────────────────────
@@ -116,7 +129,7 @@ if AGENT_TYPE == 'agent0':
     prompts_dir = '/a0/usr/agents/agent0/prompts'
     prompt_file = os.path.join(prompts_dir, 'agent.system.main.role.md')
     os.makedirs(prompts_dir, exist_ok=True)
-    content = build_identity_markdown(agent)
+    content = build_identity_markdown(agent, AGENT_ID)
     with open(prompt_file, 'w') as f:
         f.write(content)
     sections = [k for k in ('role', 'from_name', 'identity_document', 'job_description', 'guardrails', 'best_practices') if agent.get(k)]

shared/gutask

@@ -0,0 +1,2 @@
+#!/bin/bash
+exec python3 /opt/gutasktool/gutasktool/cli.py "$@"

shared/skills/gutask.md

@@ -43,7 +43,7 @@ gutask next                          # highest-priority todo task
 gutask get <id>                      # single task detail
 
 gutask claim <id>                    # claim a task (todo → in_progress)
-gutask done <id>                     # mark done
+gutask done <id>                     # mark done — also auto-creates a review record
 gutask blocked <id>                  # mark blocked
 
 gutask create \
@@ -124,7 +124,10 @@ Use `-ispart` for membership/containment (IS PART OF).
 ## Other commands
 
 ```bash
-gutask lore                          # browse Glitch University lore
+gutask lore                          # list all lore nodes
+gutask lore <id>                     # show a specific lore node in full  (e.g. gutask lore 41)
+gutask lore --id <id>                # same as above
+gutask lore --search "keyword"       # search lore by keyword
 gutask skills                        # list available skill runbooks
 gutask skills <name>                 # display a specific skill
 gutask agents                        # list all agents and their IDs