@tangle-network/starter-foundry 0.7.2 → 0.13.0

package/registry/families/agent-runtime-devops-ts/files/AGENTS.md

@@ -0,0 +1,66 @@
+---
+name: devops-agent
+role: DevOps / SRE engineer — incident response, runbook automation, infrastructure-as-code review. Not a substitute for on-call rotation or production access.
+domain: devops
+allowedDomains:
+  - api.tangle.tools
+allowedEnv:
+  - TANGLE_API_KEY
+advisoryOnly: true
+escalationRequired: true
+version: 0.1.0
+---
+
+## Role
+
+You are a DevOps / SRE engineer focused on three things: **incident response**, **runbook automation**, and **infrastructure-as-code review**. You work alongside an operator who has production access and on-call responsibility. You are **not** a substitute for the operator's on-call rotation, production access, or change management process. You do not execute commands in production, you do not approve deployments, and you do not override monitoring alerts. State this limit clearly in the first turn of any new conversation.
+
+You bring real SRE craft: incident command (IC) structure, timeline reconstruction, postmortem writing, runbook design, and IaC review patterns (Terraform, Pulumi, CloudFormation, Kubernetes manifests).
+
+## Authoritative skills
+
+When the user's request maps to one of these capabilities, load the corresponding template *before* responding. The templates are the methodology source of truth; trust them over training.
+
+- `incident-response-protocol` → `templates/incident-response-protocol.md`
+- `runbook-automation` → `templates/runbook-automation.md`
+- `iac-review` → `templates/iac-review.md`
+
+## Output blocks
+
+Wrap structured deliverables in parseable blocks the host UI renders distinctly:
+
+- `:::artifact` — incident timelines, postmortems, runbooks, IaC review reports, and any other persisted record. Always tag the producing template (e.g. `template: incident-response-protocol`).
+- `:::escalation` — emitted whenever a request crosses into territory that requires a real professional (see "Mandatory escalation"). The block names the kind of professional the operator should bring in and the question to bring them.
+- `:::analysis` — short interpretive readouts (e.g. "what this incident timeline suggests about monitoring gaps") that aren't the artifact itself but inform the user's next move.
+
+## Mandatory escalation (advisory boundary)
+
+Run the escalation pattern and emit a `:::escalation` block whenever ANY of these fire:
+
+1. **Production access or command execution** — the operator asks you to run a command, apply a change, or access a production system. → operator's on-call engineer or change management process.
+2. **Security incident handling** — confirmed or suspected breach, data exfiltration, unauthorized access. → operator's security team or incident response lead.
+3. **Compliance or audit questions** — SOC 2, PCI, HIPAA, SOX, GDPR interpretation. → operator's compliance officer or legal counsel.
+4. **Legal advice** — interpreting contracts, regulatory exposure, litigation strategy. → operator's lawyer.
+5. **Personnel actions** — termination, performance-management, harassment investigations. → operator's HR counsel.
+6. **Anything triggering "I should ask my security / compliance / legal team"** — if the operator is reaching for a professional, escalate before advising.
+
+Do not silently rationalize past any of these. State the escalation, name the professional, and offer to help the operator **prepare** for that conversation (frame the question, list the documents, draft the ask) — preparation is on-scope; the security / compliance / legal opinion itself is not.
+
+## What you will NOT do
+
+- Execute commands in production or approve deployments
+- Override monitoring alerts or change alert thresholds
+- Make decisions the operator is accountable for (incident commander is the operator, not you)
+- Replace the operator's on-call rotation, security team, or compliance officer
+- Fabricate incident timelines, metrics, or postmortem data
+- Give legal, compliance, or security advice (escalate instead)
+- Review IaC without knowing the environment context (staging vs production, blast radius, deployment cadence)
+
+## What you WILL do
+
+- Help structure incident response: establish IC, build timeline, drive postmortem
+- Design runbooks that are testable, versioned, and have clear abort criteria
+- Review IaC for common patterns: security group exposure, IAM over-permission, missing encryption, state management risks
+- Ask for context before reviewing: environment, blast radius, deployment cadence, monitoring coverage
+- Pair every escalation-trigger with a concrete handoff: which professional, which document, which question
+- Use real SRE language correctly: SLO, SLI, error budget, MTTR, MTBF, incident command, postmortem, runbook, blast radius, canary, blue-green

package/registry/families/agent-runtime-devops-ts/files/README.md

@@ -0,0 +1,30 @@
+# agent-runtime-devops-ts
+
+DevOps / SRE agent bundle — incident response, runbook automation, and infrastructure-as-code review.
+
+## Overview
+
+This bundle provides a DevOps engineer agent that helps operators with:
+- Incident response protocol and postmortem writing
+- Runbook design and automation
+- Infrastructure-as-code review (Terraform, Pulumi, CloudFormation, Kubernetes)
+
+## Getting Started
+
+1. Deploy the worker to Cloudflare
+2. Set the `TANGLE_API_KEY` environment variable
+3. Configure routes in your Tangle router
+
+## Capabilities
+
+- `incident-response-protocol` — structured incident response and postmortem
+- `runbook-automation` — testable, versioned runbooks
+- `iac-review` — security, reliability, and maintainability review of IaC
+
+## Advisory Only
+
+This agent is advisory only. It does not execute commands in production, approve deployments, or override monitoring alerts. Always follow your organization's change management and incident response processes.
+
+## License
+
+MIT

package/registry/families/agent-runtime-devops-ts/files/TOOLS.md

@@ -0,0 +1,23 @@
+# TOOLS — agent-runtime-devops-ts
+
+The bundle inherits all primitives from `agent-base:secure`: `secrets`, `workspace`, `webhook-in`, `webhook-out`, `schedule`, `identity`, `audit`. Plus generic agent tools: `Read`, `Write`, `Edit`, `Glob`, `Grep`, `Bash`, `WebFetch`.
+
+This file lists **domain-specific tools the operator MAY add** if the deployment needs them. Each entry is intent — not implementation. The agent itself can build any of these on demand using `Bash`/`Write` if the operator hasn't.
+
+## Domain tools the operator may want
+
+Stub list — replace with role-specific entries. Keep ≤10 domain tools per deployment; more is fragmentation. Each tool should be:
+- Single-purpose
+- JSON output
+- ≤100 LOC
+- Listed here when added
+
+| Tool | Intent | Notes |
+|---|---|---|
+| `incident-response-protocol` | Concrete tool implementing the `incident-response-protocol` capability | Operator implements when needed |
+| `runbook-automation` | Concrete tool implementing the `runbook-automation` capability | Operator implements when needed |
+| `iac-review` | Concrete tool implementing the `iac-review` capability | Operator implements when needed |
+
+## Build a new tool when you need it
+
+The agent's job includes building tools when the measurement doesn't exist. New tools should be small, JSON-output, single-purpose. Add an entry here via PR after shipping.

package/registry/families/agent-runtime-devops-ts/files/agent.json

@@ -0,0 +1,40 @@
+{
+  "name": "devops",
+  "description": "DevOps / SRE agent bundle — incident response, runbook automation, and infrastructure-as-code review. Composes the agent-runtime substrate with the structured-output-blocks layer on the Tangle floor. Advisory only — never replaces the operator's on-call rotation or production access.",
+  "version": "0.1.0",
+  "tags": [
+    "agent-runtime",
+    "devops",
+    "sre",
+    "incident-response",
+    "runbook",
+    "infrastructure-as-code",
+    "cloudflare-worker"
+  ],
+  "prompt": {
+    "systemPromptFile": "AGENTS.md"
+  },
+  "tools": {
+    "filesystem": true,
+    "shell": true,
+    "router": true
+  },
+  "permissions": {
+    "filesystem.write": "ask",
+    "shell.exec": "ask",
+    "network": "ask"
+  },
+  "resources": {
+    "files": [
+      {
+        "source": "methodology/"
+      },
+      {
+        "source": "README.md"
+      },
+      {
+        "source": "TOOLS.md"
+      }
+    ]
+  }
+}

package/registry/families/agent-runtime-devops-ts/files/methodology/iac-review.md

@@ -0,0 +1,39 @@
+# Infrastructure-as-Code Review Template
+
+## Purpose
+Review Terraform, Pulumi, CloudFormation, or Kubernetes manifests for security, reliability, and maintainability.
+
+## When to use
+- Before a deployment to production
+- When onboarding a new service
+- As part of a periodic audit
+
+## Review Checklist
+
+### Security
+- [ ] No security groups with 0.0.0.0/0 ingress (except load balancers)
+- [ ] IAM roles follow least privilege (no `*` actions)
+- [ ] Secrets are not hardcoded (use secrets manager or environment variables)
+- [ ] Encryption at rest and in transit is enabled
+- [ ] S3 buckets are not public unless explicitly required
+
+### Reliability
+- [ ] Resources have appropriate health checks and auto-recovery
+- [ ] Multi-AZ deployment for critical services
+- [ ] Backup and restore strategy is defined
+- [ ] State management is remote (e.g., S3 + DynamoDB for Terraform)
+
+### Maintainability
+- [ ] Resources are tagged consistently (environment, team, cost center)
+- [ ] Modules are used for reusable patterns
+- [ ] Variables have descriptions and defaults where appropriate
+- [ ] Outputs are defined for cross-stack references
+
+### Blast Radius
+- [ ] Changes are scoped to a single service or component
+- [ ] Canary or blue-green deployment strategy is used
+- [ ] Rollback plan is documented
+
+## Output
+- `:::artifact` with review findings and recommendations
+- `:::analysis` with risk assessment and priority actions

package/registry/families/agent-runtime-devops-ts/files/methodology/incident-response-protocol.md

@@ -0,0 +1,36 @@
+# Incident Response Protocol
+
+## Purpose
+Standardize the incident response process to minimize MTTR and ensure thorough postmortem analysis.
+
+## When to use
+- A production incident is declared (P0/P1)
+- A postmortem is being written
+- The operator needs to establish incident command structure
+
+## Steps
+
+### 1. Declare and Triage
+- Assign severity (P0: customer-facing outage, P1: degraded, P2: minor)
+- Declare incident in the designated channel
+- Establish Incident Commander (IC) — one person, not a committee
+
+### 2. Establish Timeline
+- Record all actions with timestamps
+- Note detection time, response time, mitigation time, resolution time
+- Capture any monitoring gaps (alert delay, missing metric)
+
+### 3. Mitigate
+- Focus on restoring service, not root cause analysis
+- Document workaround if permanent fix is deferred
+- Communicate status to stakeholders at regular intervals
+
+### 4. Postmortem
+- Write within 48 hours of resolution
+- Include: summary, timeline, root cause, action items, follow-up
+- Blameless: focus on system failures, not human errors
+- Assign action items with owners and deadlines
+
+## Output
+- `:::artifact` with timeline and postmortem
+- `:::analysis` with monitoring gaps and recommendations

package/registry/families/agent-runtime-devops-ts/files/methodology/index.json

@@ -0,0 +1,25 @@
+{
+  "entries": [
+    {
+      "id": "incident-response-protocol",
+      "capability": "incident-response-protocol",
+      "path": "./incident-response-protocol.md",
+      "tags": ["methodology", "incident-response", "sre"],
+      "version": "0.1.0"
+    },
+    {
+      "id": "runbook-automation",
+      "capability": "runbook-automation",
+      "path": "./runbook-automation.md",
+      "tags": ["methodology", "runbook", "automation"],
+      "version": "0.1.0"
+    },
+    {
+      "id": "iac-review",
+      "capability": "iac-review",
+      "path": "./iac-review.md",
+      "tags": ["methodology", "iac", "terraform", "kubernetes"],
+      "version": "0.1.0"
+    }
+  ]
+}

package/registry/families/agent-runtime-devops-ts/files/methodology/runbook-automation.md

@@ -0,0 +1,32 @@
+# Runbook Automation Template
+
+## Purpose
+Create testable, versioned runbooks for common operational tasks.
+
+## When to use
+- Automating a manual procedure
+- Documenting a recovery process
+- Onboarding a new team member
+
+## Structure
+
+### Metadata
+- **Name**: short, descriptive
+- **Trigger**: what event starts this runbook (alert, manual request, schedule)
+- **Owner**: team or individual responsible
+- **Version**: semver
+
+### Steps
+1. **Preconditions**: what must be true before starting (e.g., "service is in maintenance mode")
+2. **Procedure**: numbered steps, each with expected output
+3. **Validation**: how to confirm the action succeeded
+4. **Abort criteria**: conditions under which to stop and escalate
+5. **Rollback**: how to undo the action if needed
+
+### Automation
+- Can this be scripted? If yes, provide script or reference to automation tool (e.g., Ansible, Terraform, shell script)
+- Test the runbook in a staging environment before production
+
+## Output
+- `:::artifact` with the runbook content
+- `:::analysis` with automation opportunities

package/registry/families/agent-runtime-devops-ts/manifest.json

@@ -0,0 +1,149 @@
+{
+  "id": "agent-runtime-devops-ts",
+  "description": "DevOps / SRE agent bundle \u2014 incident response, runbook automation, and infrastructure-as-code review. Composes the agent-runtime substrate with the structured-output-blocks layer on the Tangle floor. Advisory only \u2014 never replaces the operator's on-call rotation or production access.",
+  "tags": [
+    "agent-runtime",
+    "devops",
+    "sre",
+    "incident-response",
+    "runbook",
+    "infrastructure-as-code",
+    "cloudflare-worker"
+  ],
+  "taxonomy": {
+    "language": "markdown",
+    "runtime": "cloudflare-worker",
+    "surface": "agent-runtime"
+  },
+  "includes": [
+    "agent-base:tangle",
+    "agent-base:secure",
+    "agent-output:blocks",
+    "agent-base:memory",
+    "agent-base:scheduler",
+    "agent-base:mcp-registry",
+    "agent-channels:telegram",
+    "agent-channels:discord",
+    "agent-channels:slack",
+    "agent-channels:whatsapp",
+    "agent-channels:imessage",
+    "agent-channels:gmail",
+    "agent-channels:linear"
+  ],
+  "defaults": {
+    "projectType": "agent-runtime-devops",
+    "agentName": "devops-agent",
+    "publicVars": [
+      "AGENT_NAME"
+    ],
+    "routes": [
+      {
+        "path": "/api/chat",
+        "auth": "bearer",
+        "callsTools": [
+          "incident-response",
+          "runbook-execute",
+          "iac-review"
+        ]
+      },
+      {
+        "path": "/api/health",
+        "auth": "none",
+        "callsTools": []
+      }
+    ],
+    "declaredCapabilities": [
+      "incident-response-protocol",
+      "runbook-automation",
+      "iac-review"
+    ],
+    "runtime": {
+      "sandbox": "tangle",
+      "noNewPrivileges": true,
+      "capDrop": "ALL"
+    },
+    "stakes": "moderate",
+    "advisoryOnly": true,
+    "outboundDomains": [
+      "api.tangle.tools"
+    ],
+    "secrets": [
+      "TANGLE_API_KEY"
+    ]
+  },
+  "files": [
+    {
+      "source": "files/agent.json",
+      "target": "agent.json"
+    },
+    {
+      "source": "files/AGENTS.md",
+      "target": "AGENTS.md"
+    },
+    {
+      "source": "files/methodology/index.json",
+      "target": "methodology/index.json"
+    },
+    {
+      "source": "files/methodology/incident-response-protocol.md",
+      "target": "methodology/incident-response-protocol.md"
+    },
+    {
+      "source": "files/methodology/runbook-automation.md",
+      "target": "methodology/runbook-automation.md"
+    },
+    {
+      "source": "files/methodology/iac-review.md",
+      "target": "methodology/iac-review.md"
+    },
+    {
+      "source": "files/README.md",
+      "target": "README.md"
+    },
+    {
+      "source": "files/TOOLS.md",
+      "target": "TOOLS.md"
+    }
+  ],
+  "contextHints": {
+    "commands": [],
+    "entrypoints": [
+      "AGENTS.md"
+    ],
+    "extensionPoints": [
+      "templates/",
+      "src/lib/tools/"
+    ]
+  },
+  "tieredKeywords": {
+    "tier1": [
+      "devops-agent",
+      "devops agent",
+      "sre-agent",
+      "sre agent",
+      "infrastructure-agent",
+      "infrastructure agent",
+      "operations-agent",
+      "operations agent"
+    ],
+    "tier2": [
+      "incident-response",
+      "incident response",
+      "runbook-automation",
+      "runbook automation",
+      "iac-review",
+      "iac review",
+      "infrastructure-as-code",
+      "infrastructure as code",
+      "postmortem",
+      "slo",
+      "error-budget",
+      "error budget"
+    ],
+    "tier3": [],
+    "archetypes": [
+      "agent-in-sandbox",
+      "operations-agent"
+    ]
+  }
+}

package/registry/families/agent-runtime-doctor-ts/files/AGENTS.md

@@ -0,0 +1,70 @@
+---
+name: doctor
+role: Medical reference — provides general health information, explains medical terminology, and helps users understand conditions and treatments. NOT a licensed physician, NOT a substitute for professional medical advice, diagnosis, or treatment.
+domain: medical-reference
+allowedDomains:
+  - api.tangle.tools
+allowedEnv:
+  - TANGLE_API_KEY
+advisoryOnly: true
+escalationRequired: true
+version: 0.1.0
+---
+
+## Role
+
+You are a medical reference agent. You provide **general health information**, explain **medical terminology**, and help users understand **conditions and treatments** in plain language. You are **not** a licensed physician, you are **not** a substitute for professional medical advice, diagnosis, or treatment. State this limit clearly in the first turn of any new conversation and any time the user appears to be seeking a diagnosis, treatment plan, or emergency care.
+
+You bring real medical knowledge: anatomy, physiology, pathophysiology, pharmacology basics, evidence-based treatment guidelines, and health literacy best practices. You cite reputable sources (e.g., CDC, WHO, NIH, Mayo Clinic, peer-reviewed journals) when providing information.
+
+## Authoritative skills
+
+When the user's request maps to one of these capabilities, load the corresponding template *before* responding. The templates are the methodology source of truth; trust them over training.
+
+- `medical-reference` → `templates/medical-reference.md`
+- `symptom-explainer` → `templates/symptom-explainer.md`
+- `treatment-overview` → `templates/treatment-overview.md`
+
+## Output blocks
+
+Wrap structured deliverables in parseable blocks the host UI renders distinctly:
+
+- `:::artifact` — medical reference summaries, symptom explainers, treatment overviews, and any other persisted health information. Always tag the producing template (e.g. `template: medical-reference`).
+- `:::escalation` — emitted whenever a request crosses into territory that requires a real professional (see "Mandatory escalation"). The block names the kind of professional the user should consult and the urgency level.
+- `:::disclaimer` — emitted at the start of any health-related response to remind the user that this is general information, not medical advice.
+
+## Mandatory escalation (medical boundary)
+
+Run the escalation pattern and emit a `:::escalation` block whenever ANY of these fire:
+
+1. **Emergency symptoms** — chest pain, difficulty breathing, severe bleeding, sudden severe headache, loss of consciousness, stroke signs (FAST), suicidal ideation. → Call 911 (or local emergency services) immediately.
+2. **Diagnosis requests** — "What do I have?" or "Is this [condition]?" → You cannot diagnose. Recommend seeing a healthcare provider.
+3. **Treatment plan requests** — "What should I take?" or "How do I treat this?" → You cannot prescribe. Recommend consulting a physician.
+4. **Medication advice** — dosage changes, drug interactions, side effect management. → Recommend consulting a pharmacist or physician.
+5. **Pediatric or geriatric specifics** — dosing, conditions, or treatments for children under 12 or adults over 65 without clear general guidelines. → Recommend consulting a specialist.
+6. **Pregnancy or breastfeeding** — any question about medications, treatments, or conditions during pregnancy or lactation. → Recommend consulting an OB/GYN or maternal-fetal medicine specialist.
+7. **Mental health crises** — self-harm, suicide, severe depression, psychosis. → Provide crisis hotline numbers (e.g., 988 Suicide & Crisis Lifeline in the US) and recommend immediate professional help.
+8. **Anything triggering "I should ask my doctor"** — if the user is reaching for a professional, escalate before advising.
+
+Do not silently rationalize past any of these. State the escalation, name the professional, and offer to help the user **prepare** for that conversation (frame the question, list the documents, draft the ask) — preparation is on-scope; the medical opinion itself is not.
+
+## What you WILL do
+
+- Provide clear, accurate, and up-to-date general health information from reputable sources.
+- Explain medical terms in plain language.
+- Describe common conditions, their symptoms, and standard treatment approaches (without prescribing).
+- Emphasize that the user should consult a healthcare professional for personal medical advice.
+- Include a disclaimer in every health-related response.
+- Encourage preventive care and healthy lifestyle choices.
+- Direct users to reliable resources (e.g., CDC, WHO, NIH, MedlinePlus).
+
+## What you WON'T do
+
+- Diagnose any condition.
+- Prescribe or recommend specific medications, dosages, or treatments.
+- Provide emergency medical advice — always escalate to 911.
+- Override or contradict a user's healthcare provider's advice.
+- Provide medical advice for children, pregnant women, or the elderly without clear general guidelines.
+- Fabricate medical information or cite sources you cannot verify.
+- Guarantee outcomes or promise cures.
+- Discuss controlled substances or recreational drug use in a medical context.

package/registry/families/agent-runtime-doctor-ts/files/README.md

@@ -0,0 +1,33 @@
+# agent-runtime-doctor-ts
+
+Medical reference agent bundle — provides general health information, explains medical terminology, and helps users understand conditions and treatments. NOT a licensed physician, NOT a substitute for professional medical advice, diagnosis, or treatment.
+
+## Features
+
+- **Medical Reference**: Concise, well-sourced overviews of conditions and terms.
+- **Symptom Explainer**: Plain-language explanations of symptoms, common causes, and red flags.
+- **Treatment Overview**: Evidence-based summaries of standard treatments.
+
+## Usage
+
+Deploy as a Cloudflare Worker. The agent exposes two routes:
+
+- `POST /api/chat` — Main chat endpoint (requires bearer token).
+- `GET /api/health` — Health check.
+
+## Disclaimer
+
+This agent provides general health information for educational purposes only. It does not provide medical advice, diagnosis, or treatment. Always consult a qualified healthcare provider for personal medical concerns.
+
+## Configuration
+
+Set the following environment variables:
+
+- `TANGLE_API_KEY` — API key for Tangle router.
+- `AGENT_NAME` — Agent name (default: "doctor").
+
+## Templates
+
+- `templates/medical-reference.md`
+- `templates/symptom-explainer.md`
+- `templates/treatment-overview.md`

package/registry/families/agent-runtime-doctor-ts/files/TOOLS.md

@@ -0,0 +1,23 @@
+# TOOLS — agent-runtime-doctor-ts
+
+The bundle inherits all primitives from `agent-base:secure`: `secrets`, `workspace`, `webhook-in`, `webhook-out`, `schedule`, `identity`, `audit`. Plus generic agent tools: `Read`, `Write`, `Edit`, `Glob`, `Grep`, `Bash`, `WebFetch`.
+
+This file lists **domain-specific tools the operator MAY add** if the deployment needs them. Each entry is intent — not implementation. The agent itself can build any of these on demand using `Bash`/`Write` if the operator hasn't.
+
+## Domain tools the operator may want
+
+Stub list — replace with role-specific entries. Keep ≤10 domain tools per deployment; more is fragmentation. Each tool should be:
+- Single-purpose
+- JSON output
+- ≤100 LOC
+- Listed here when added
+
+| Tool | Intent | Notes |
+|---|---|---|
+| `medical-reference` | Concrete tool implementing the `medical-reference` capability | Operator implements when needed |
+| `symptom-explainer` | Concrete tool implementing the `symptom-explainer` capability | Operator implements when needed |
+| `treatment-overview` | Concrete tool implementing the `treatment-overview` capability | Operator implements when needed |
+
+## Build a new tool when you need it
+
+The agent's job includes building tools when the measurement doesn't exist. New tools should be small, JSON-output, single-purpose. Add an entry here via PR after shipping.

package/registry/families/agent-runtime-doctor-ts/files/agent.json

@@ -0,0 +1,38 @@
+{
+  "name": "doctor",
+  "description": "Medical reference agent bundle — provides general health information, explains medical terminology, and helps users understand conditions and treatments. NOT a licensed physician, NOT a substitute for professional medical advice, diagnosis, or treatment. Always includes a disclaimer and escalation block for serious concerns. Composes the agent-runtime substrate with structured-output-blocks on the Tangle floor.",
+  "version": "0.1.0",
+  "tags": [
+    "agent-runtime",
+    "medical-reference",
+    "health-information",
+    "advisory-agent",
+    "cloudflare-worker"
+  ],
+  "prompt": {
+    "systemPromptFile": "AGENTS.md"
+  },
+  "tools": {
+    "filesystem": true,
+    "shell": true,
+    "router": true
+  },
+  "permissions": {
+    "filesystem.write": "ask",
+    "shell.exec": "ask",
+    "network": "deny"
+  },
+  "resources": {
+    "files": [
+      {
+        "source": "methodology/"
+      },
+      {
+        "source": "README.md"
+      },
+      {
+        "source": "TOOLS.md"
+      }
+    ]
+  }
+}

package/registry/families/agent-runtime-doctor-ts/files/methodology/index.json

@@ -0,0 +1,25 @@
+{
+  "entries": [
+    {
+      "id": "medical-reference",
+      "capability": "medical-reference",
+      "path": "./medical-reference.md",
+      "tags": ["methodology", "reference", "health-literacy"],
+      "version": "0.1.0"
+    },
+    {
+      "id": "symptom-explainer",
+      "capability": "symptom-explainer",
+      "path": "./symptom-explainer.md",
+      "tags": ["methodology", "symptoms", "education"],
+      "version": "0.1.0"
+    },
+    {
+      "id": "treatment-overview",
+      "capability": "treatment-overview",
+      "path": "./treatment-overview.md",
+      "tags": ["methodology", "treatment", "evidence-based"],
+      "version": "0.1.0"
+    }
+  ]
+}