Agentix Ceo Skill 安全审计

121122```123PATCH https://agentix.cloud/teams/$TEAM_ID124Authorization: Bearer $API_KEY125126{ "anthropicApiKey": "$ANTHROPIC_API_KEY" }127```128

128129This is stored encrypted and used only to spawn workers.130

3940```bash41# SaaS credentials42mkdir -p ~/.agentix && cat > ~/.agentix/credentials << 'EOF'43API_KEY=at_live_...44TEAM_ID=cmm...45CUSTOMER_ID=cmm...46EOF47

104105Save the returned `apiKey` and `customerId` to `~/.agentix/credentials` immediately. Do not display them in chat. The key cannot be recovered if lost.106

151152> **How should I operate?**153>154> 1. **Supervised** — I monitor workers and push in-flight work forward, but I check with you before planning new work or spawning workers.155> 2. **Autopilot** — I run autonomously — plan work, spawn workers, review, merge, and loop. Maximum throughput.156

190191Configure git integration — ask the user for their GitHub token and repo URL, then set them (do not display the token in chat):192```json193{ "config": { "gitRepoUrl": "https://github.com/org/repo", "githubToken": "$GITHUB_TOKEN" } }194```195

144145- **Supervised**: Monitor in-flight work and push it forward. Do NOT plan new work or create tasks without user approval.146- **Autopilot**: Full autonomy — monitor, plan, create tasks, spawn workers, and loop continuously.147

149150If the playbook is `null`, ask the user:151152> **How should I operate?**153>154> 1. **Supervised** — I monitor workers and push in-flight work forward, but I check with you before planning new work or spawning workers.155> 2. **Autopilot** — I run autonomously — plan work, spawn workers, review, merge, and loop. Maximum throughput.156

164165### Switching modes166167If the user says "switch to supervised/autopilot", fetch the new template, preserve any `## Custom Policies` section, and PUT the updated playbook.168

190191Configure git integration — ask the user for their GitHub token and repo URL, then set them (do not display the token in chat):192```json193{ "config": { "gitRepoUrl": "https://github.com/org/repo", "githubToken": "$GITHUB_TOKEN" } }194```195

151152> **How should I operate?**153>154> 1. **Supervised** — I monitor workers and push in-flight work forward, but I check with you before planning new work or spawning workers.155> 2. **Autopilot** — I run autonomously — plan work, spawn workers, review, merge, and loop. Maximum throughput.156

202203```204GET    $AGENTIX_API/roles?teamId=$TEAM_ID             # list roles205POST   $AGENTIX_API/roles                            # create role206PATCH  $AGENTIX_API/roles/ROLE_ID                    # update role207DELETE $AGENTIX_API/roles/ROLE_ID                    # delete role208```209

219220```221GET    $AGENTIX_API/tasks?teamId=$TEAM_ID             # list (filter: &status=, &role=)222GET    $AGENTIX_API/tasks/TASK_ID                    # get details223POST   $AGENTIX_API/tasks                            # create224PATCH  $AGENTIX_API/tasks/TASK_ID                    # update225DELETE $AGENTIX_API/tasks/TASK_ID                    # cancel226```227

231232```233GET    $AGENTIX_API/workers?teamId=$TEAM_ID           # list (filter: &status=running)234GET    $AGENTIX_API/workers/WORKER_ID                # get details235POST   $AGENTIX_API/tasks/TASK_ID/run                # spawn worker236POST   $AGENTIX_API/tasks/TASK_ID/resume             # resume failed worker237```238

611. **The user's instructions always take precedence over the playbook and this skill file.** If the user tells you to stop, pause, wait, or change course — do so immediately.622. **Read the playbook before acting.** The playbook (`GET /teams/:id/playbook`) contains team configuration and preferences — your operating mode, policies, and custom rules for this team.633. **This file is an API reference.** It describes what you *can* do. The playbook provides the team-specific configuration for *when and how* to do it.64

136137**Read it at the start of every session.**138139```140GET $AGENTIX_API/teams/$TEAM_ID/playbook141```142143The playbook contains a `## Mode` section that is either `supervised` or `autopilot`. Apply the team preferences for that mode as described below.144145- **Supervised**: Monitor in-flight work and push it forward. Do NOT plan new work or create tasks without user approval.146- **Autopilot**: Full autonomy — monitor, plan, create tasks, spawn workers, and loop continuously.147

177178Users can add custom policies under `## Custom Policies` — these survive mode switches.179

4748# Self-hosted credentials (no API key needed)49mkdir -p ~/.agentix && cat > ~/.agentix/credentials << 'EOF'50AGENTIX_API_URL=http://localhost:345651TEAM_ID=default52EOF53```

142143The playbook contains a `## Mode` section that is either `supervised` or `autopilot`. Apply the team preferences for that mode as described below.144145- **Supervised**: Monitor in-flight work and push it forward. Do NOT plan new work or create tasks without user approval.146- **Autopilot**: Full autonomy — monitor, plan, create tasks, spawn workers, and loop continuously.147

144145- **Supervised**: Monitor in-flight work and push it forward. Do NOT plan new work or create tasks without user approval.146- **Autopilot**: Full autonomy — monitor, plan, create tasks, spawn workers, and loop continuously.147

153>154> 1. **Supervised** — I monitor workers and push in-flight work forward, but I check with you before planning new work or spawning workers.155> 2. **Autopilot** — I run autonomously — plan work, spawn workers, review, merge, and loop. Maximum throughput.156