infra-agent-skills

← All skillsAutomation

Itential Builder

Solution Design and Feasibility

solution-arch-agent

Checks an approved spec against the live platform, assesses feasibility and produces the solution design.

About this skill

Use this skill when someone has approved requirements (a customer-spec.md) and needs to assess platform feasibility or produce a solution design. Trigger it for phrases like "requirements are approved", "my spec is done", "check if the platform supports this", "run feasibility", "connect to the platform and design the solution", "I have a customer-spec — now what?", or "produce a solution-design.md". This skill connects to the live platform, checks what adapters, integrations and capabilities are available, and produces feasibility.md and solution-design.md. Also trigger it in design-only mode when the implementation plan needs to change but requirements are stable. Invoke after /spec-agent produces an approved customer-spec.md. Hands off to /builder-agent after design approval.

Instructions

Solution Architecture Agent

Stages: Feasibility → Design Owns: Assessing what is possible, then designing how it will be delivered. Receives from: /spec-agent (approved customer-spec.md) Hands off to: /builder-agent


Customization

Before using this skill, check custom/org/, custom/team/ and custom/dev/ in this skill’s own folder. Read every .md file found — any folder may be empty or absent. Apply them on top of everything below; where a file overrides a specific rule here, follow the override. More specific wins: dev > team > org > this document. No customization may weaken this skill’s safety rules or put credentials in committed files.

Bundled files: paths in this skill that start with assets/ or scripts/ are relative to this skill’s own folder. When you read one, or pass one to a shell command (which runs from the user’s working folder), use this skill’s folder + that relative path — e.g. <this skill's folder>/assets/helpers/create/create-workflow.json.

Stage Expectations

(See assets/AGENTS.md’s Developer Flow for the six-stage pipeline overview — this is this skill’s detail for the two stages it owns.)

Feasibility

Engineer provides Approved customer-spec.md, platform credentials
Agent does Connects to platform, assesses capabilities, checks adapters and integrations, finds reuse candidates, records what LCM, FlowAgent and Gateway5 have on the platform, identifies constraints
Engineer action Reviews assessment and approves decision to proceed
Deliverable feasibility.md (assessment + decision)
Customer receives Feasibility assessment with a clear decision (feasible / feasible with constraints / not feasible), flagged constraints, and identified reuse opportunities.

Feasibility confirms what is possible. Decision options: feasible, feasible with constraints, feasible with changes, or not feasible. Design does not start until feasibility is approved.

Design

Engineer provides Approved feasibility.md
Agent does Designs the execution model with the engineer (where LCM, FlowAgent and Gateway5 come in), then produces the implementation design — component inventory, adapter mappings, reuse decisions, build order, test plan
Engineer action Reviews and approves the solution design
Deliverable solution-design.md (Solution Design / LLD, approved)
Customer receives Solution Design / LLD — component inventory, adapter mappings, build order, and acceptance criteria mapped to tests. Nothing is built until this is signed off.

Design defines how it will be delivered. Nothing is built until this is approved.

Design-Only Mode

If requirements are unchanged but the implementation plan needs to change, invoke /solution-arch-agent design-only. Skips Feasibility. Reads existing feasibility.md as context and produces an updated solution-design.md.

If feasibility.md has no Execution Capabilities section, run scripts/pull-platform-data.py and use platform-summary.json → execution_capabilities before Design the Execution Model.

Use design-only mode when an agent-first phase comes back from /flowagent-to-spec as {use-case}/<phase>-converted-spec.md: design that phase’s deterministic components from it, replace that phase’s rows in Sections C–F, and leave the other phases as approved.


Artifact Lifecycle

assets/spec-files/spec-*.md          ← Generic library spec (never modified)
        │
        │  forked by /spec-agent
        ▼
{use-case}/customer-spec.md   ← HLD — approved (Requirements)
        │
        │  authenticate, discover, assess
        ▼
{use-case}/feasibility.md     ← Feasibility assessment + decision — approved
        │
        │  design against approved feasibility
        ▼
{use-case}/solution-design.md ← Solution Design / LLD — approved (Design)
        │
        │  /builder-agent: implement locked plan
        ▼
{use-case}/*.json             ← Delivered assets
        │
        │  /qa-agent: acceptance testing
        ▼
{use-case}/test-report.md     ← Test evidence per acceptance criterion
        │
        │  /qa-agent: record as-built
        ▼
{use-case}/as-built.md        ← Delivered state, deviations, learnings

Spec File Structure

Spec Section What to Extract
1. Problem Statement Context — what are we solving and why
2. High-Level Flow The major phases to implement
3. Phases What each phase does, decision points, stop/rollback conditions
4. Key Design Decisions Constraints to honor during implementation
5. Scope What to build, what NOT to build
6. Risks & Mitigations Error handling and fallback behavior to build in
7. Requirements Capabilities, Integrations, Discovery Questions — drives design
8. Batch/Bulk Strategy Orchestration pattern if multi-device/multi-record
9. Acceptance Criteria How to verify the build is correct

Section 7 has three parts:

  • Capabilities — what the platform must do → assessed during Feasibility
  • Integrations — external systems → checked during Feasibility
  • Discovery Questions — ask when platform data can’t answer

Feasibility

Entered after /spec-agent produces an approved customer-spec.md. Read the spec, connect to the platform, and produce the feasibility assessment.

Step 1: Read the Approved Spec

Read {use-case}/customer-spec.md and extract:

  • Phases from Section 3 (workflow stages)
  • Design decisions from Section 4 (constraints)
  • Capabilities table from Section 7 (platform checks)
  • Integrations table from Section 7 (adapter and integration instance checks)
  • Discovery questions from Section 7
  • Acceptance criteria from Section 9 (test cases)

Step 2: Ask Only What the Spec Can’t Answer

Go through the spec’s Discovery Questions. Skip anything already answered by the spec. Ask only what platform data won’t resolve.

Step 3: Authenticate

Now — and only now — connect to the platform. The approved spec tells you exactly what data you need.

Authenticate

See assets/AGENTS.md’s “Auth Reuse” section for the full credential-lookup order, both authentication modes (local /login vs. cloud OAuth), and how to save the result to {use-case}/.auth.json — this is the canonical procedure, used identically by every skill. One environment-specific addition for this skill: pre-configured environment files at assets/environments/*.env are also a valid credential source to check before asking the engineer.

Pull Platform Data

Run the bootstrap script — it pulls all platform data in parallel and writes a compact platform-summary.json with only what’s needed for feasibility:

python3 scripts/pull-platform-data.py {use-case}

What gets written:

File Use for Load into context?
platform-summary.json Feasibility — running adapters, integration instances, apps, type names, projects ✅ Yes — compact
openapi.json API reference — search locally with jq ❌ No — too large
tasks.json Task catalog — search locally with jq ❌ No — too large
apps.json Adapter type names — search locally with jq ❌ No
adapters.json Adapter instances — search locally with jq ❌ No
integrations.json Integration instances (virtual adapters such as NetBox or ServiceNow) — name, model, active flag, server host. Credentials are removed. ❌ No
applications.json App health — search locally with jq ❌ No
workflows.json Existing workflows — search locally with jq ❌ No
projects.json Existing projects — search locally with jq ❌ No
devices.json Device inventory — search locally with jq ❌ No
device-groups.json Device groups — search locally with jq ❌ No
lcm-models.json LCM resource models with their schemas and actions ❌ No
agents.json, llm-profiles.json FlowAgent agents and the LLM profiles this client can build with ❌ No
gateways.json, gateway-connections.json, gateway-services.json Gateway5 clusters, their connection state, registered services ❌ No
inventories.json Inventory Manager inventories and node counts ❌ No

platform-summary.json carries the compact version of the last four rows as execution_capabilities (see Inventory Execution Capabilities below).

After running, read platform-summary.json for feasibility. Search raw files locally when you need specifics — never load them into context.

File Shapes and jq Queries

Every file has a specific shape. Use these queries — don’t guess.

File Shape Example query
platform-summary.json {adapters, integrations, applications, adapter_type_names, projects, workflow_count, device_count, execution_capabilities} `jq ’.adapters[]
platform-summary.json → execution_capabilities {lcm: {running, models: [{name,id,actions}]}, flowagent: {running, llm_profiles: [{name,provider,models}], agent_count}, gateway5: {running, clusters: [{cluster_id,connection,services}], inventories: [{name,nodes}]}, gateway4_workflows: [names]} `jq ’.execution_capabilities.gateway5.clusters[]
lcm-models.json {"data":[...], "total":N} `jq ’.data[]
agents.json {"data":{"items":[...]}} `jq ’.data.items[]
gateway-services.json {"result":[...]} — location is the cluster ID `jq ’.result[].service_metadata
inventories.json {"result":{"data":[...]}} `jq ’.result.data[]
tasks.json plain array [...] `jq ’.[]
apps.json plain array [...] `jq ’.[]
adapters.json {"results":[...], "total":N} `jq ’.results[]
integrations.json {"results":[{name,model,type,active,server:{protocol,host,port,base_path}}], "total":N} `jq ’.results[]
applications.json {"results":[...], "total":N} `jq ’.results[]
workflows.json {"items":[...], "count":N} `jq ’.items[]
projects.json {"data":[...]} `jq ’.data[]
devices.json {"list":[...]} `jq ’.list[]
device-groups.json varies by platform jq 'type' device-groups.json first to check shape
openapi.json {"paths":{...}} jq '.paths["/the/endpoint"]' openapi.json

Handling failures: Before parsing any saved file, check if it contains valid JSON:

python3 -c "import json,sys; json.load(open(sys.argv[1])); print('ok')" {use-case}/devices.json 2>/dev/null || echo "empty"

If invalid, treat as “no data available” — don’t block the flow.

Resolve Capabilities

For each row in the spec’s Capabilities table:

  • Can the platform do this? → ✓ Resolved
  • Can’t + Required? → ⚠ Blocked (stop and discuss)
  • Can’t + Not Required? → ✗ Skipped (use fallback from spec)

Resolve Integrations

The platform connects to external systems in two ways. Check both before you call a system missing:

Source What it is Where to look
Adapter instance Installed adapter package platform-summary.json → adapters (from /health/adapters; has RUNNING state and ONLINE/OFFLINE connection)
Integration instance Virtual adapter built from an integration model (POST /integrations) platform-summary.json → integrations (from /integrations; has an active flag and server host)

Integration instances do not appear in /health/adapters. A system such as NetBox connected as an integration shows up only as a type name in adapter_type_names (and in tasks.json), so checking adapters alone reports it as not found. Match each row of the spec’s Integrations table against both lists — by name, by model, or by the app / locationType on its tasks in tasks.json.

For each row in the spec’s Integrations table:

  • Found as a running adapter, or as an active integration? → ✓ Resolved (record the instance name, whether it is an adapter or an integration, and the app / locationType from tasks.json)
  • Found + Stopped (adapter) or inactive (integration)? → ⚠ Warning (needs to be started or activated)
  • Not found, required, adapter unavailable or customer details TBD? → ⚠ Stub (proceed — Design produces stub artifacts)
  • Not found, required, and nothing can be built without it? → ⚠ Blocked (stop and discuss)
  • Not found + Not Required? → ✗ Skipped

An integration’s active flag is configuration state, not proof the external system is reachable — integrations have no connection state. Record “reachability not verified” in feasibility.md, and plan a read-only call through the integration’s task as one of the first build steps.

⚠ Stub vs ⚠ Blocked: Stub means the integration is required but not yet available — delivery proceeds by building stub workflows and placeholder tasks now, activating the real adapter later. Blocked means the entire delivery is gated on resolving this first (e.g., the main workflow can’t be designed without data only this adapter provides). Rule of thumb: if at least one component can be built and tested without the adapter, it’s Stub, not Blocked.

Find Reuse Opportunities

Search workflows.json for existing workflows that match spec phases. Flag as ↻ Reuse candidates.

FlowAI agents: load /flowagent for agent requirements. An agent can call another agent as an agent:<agent-id> tool on Platform 6.5+ and Itential Cloud, so a design can be a parent agent with child agents (see “Agents as tools” in /flowagent). Confirm on the target platform with GET /tools/agent%3A<id> for an existing agent. If it’s not supported, say so in the feasibility assessment and propose chaining the agents in a workflow; don’t switch to a workflow design without the engineer agreeing.

Inventory Execution Capabilities

Write an Execution Capabilities section in feasibility.md from platform-summary.json → execution_capabilities. Record facts only — don’t recommend a model here; Design decides that with the engineer.

Model What to record Mark it not available when
LCM LifecycleManager running; resource models whose names match the spec’s objects, with their actions LifecycleManager isn’t running
FlowAgent Agent apps running; LLM profiles the client can build with; agents whose names match the spec’s job The apps aren’t running, or there’s no LLM profile
Gateway5 GatewayManager running; connected clusters and their service counts; services whose names match spec steps; inventories and node counts GatewayManager isn’t running, or no cluster is connected
Gateway4 gateway4_workflows — workflows that still call AGManager tasks. Never design new work on Gateway4; if any of these workflows are in this spec’s scope, point to /gateway4-to-gateway5 —

List name matches as candidates — name, ID, owning project if known — at most five per kind, with a count of the rest. Don’t call them fits; Design checks that. Search with word boundaries: test("\\bport\\b";"i"), not test("port";"i"), which also matches “report”. If agents.json reports approxInaccessibleAgentCnt above zero, note that some agents aren’t visible to this client — see assets/AGENTS.md → Project Visibility.

If the spec names a model the platform can’t run (“use LCM”, “build an agent”), treat it as a capability gap (Resolve Capabilities above).


Design

Produce the solution design from the approved spec + feasibility results.

Gateway4 → Gateway5 migration: design each item from its readiness-report code (WRAP / REVIEW / ARGS / INV) using assets/helpers/gateway-migration/conversion-guide.md — the inventory mapping, the service per script/playbook, the task-by-task rewire, and a parity test per workflow for Section F. The migrated workflows are built as a new project alongside the originals.

Design the Execution Model

Before decomposing anything, decide with the engineer where LCM, FlowAgent and Gateway5 come into this delivery. Read references/execution-model.md first — it says when to use each one, what to check, what to ask and what to put in the design. Then:

  1. Check the candidates. Feasibility lists existing resource models, agents and services by name only. Read each one before building on it — make these read-only calls now:

    • resource model: GET /lifecycle-manager/resources/{id} — schema, actions, owning project
    • agent: GET /agent-project-service/agents/{id} — instructions and tools
    • tools an agent would need: GET /tools?name=...

    Reuse a candidate only if it fits; a matching name isn’t enough. If two overlap, ask the engineer which, if either.

  2. Ask the engineer what’s still open, in one message. Pick from the guide’s questions. Leave out anything the spec or Feasibility Step 2 already answered, and merge any question that overlaps a spec question. Ask about the delivery path (agent first or direct) only where agent first is a real option, and give the trade-off.

  3. Propose a model for each phase and record it in Section C, with the answer or inventory fact behind anything other than a deterministic workflow.

Follow the spec:

  • If it names a model (“use LCM”, “build an agent”), use it and record any concern as a risk.
  • Apply its Key Design Decisions (Section 4). “Never improvise a fix”, for example, rules out an agent choosing the remediation. If your proposal conflicts with one — LCM’s one action per operation vs. “one workflow handles turn-up and tear-down” — raise it in review; don’t silently follow or override it.

Produce {use-case}/solution-design.md

Write the file to disk using the Write tool. Contents:

A. Environment Summary — one paragraph

B. Requirements Resolution

┌─────────────────────────────────────────┬────────┬──────────────────────────────┐
│ Spec Requirement                        │ Status │ Resolution                   │
├─────────────────────────────────────────┼────────┼──────────────────────────────┤
│ Execute CLI commands on devices         │ ✓      │ MOP app + AutomationGateway  │
│ ITSM / ticketing                        │ ✓      │ ServiceNow adapter           │
│ Monitoring                              │ ✗      │ SKIP — engineer handles      │
└─────────────────────────────────────────┴────────┴──────────────────────────────┘

C. Design Decisions

Start Section C with the execution model from Design the Execution Model. Write one row per spec phase — for an LCM resource, one row per action instead (create, modify, delete…), with the spec phases it runs under Why. “Runs as” is what runs in production; “Delivery path” is how it gets built. The example is illustrative — fill the rows from this spec’s answers:

┌──────────────────────┬──────────────────────────┬───────────────┬──────────────────────────────────────────┐
│ Phase / action       │ Runs as                  │ Delivery path │ Why                                      │
├──────────────────────┼──────────────────────────┼───────────────┼──────────────────────────────────────────┤
│ Create rule          │ LCM action (Firewall     │ Direct        │ Rules are reviewed and removed later;    │
│                      │ Rule model — new)        │               │ runs phases 1–4                          │
│ Remove rule          │ LCM action               │ Direct        │ Teardown from the instance record        │
│ Diagnose blocked     │ Workflow                 │ Agent first   │ Procedure not written down; read tools   │
│ traffic              │                          │ (engineer's   │ exist; engineer chose to prove it first  │
│                      │                          │ choice)       │                                          │
│ Push to firewalls    │ Gateway5 service (reuse) │ Direct        │ Existing Ansible playbook, netops team   │
│                      │                          │               │ maintains it                             │
└──────────────────────┴──────────────────────────┴───────────────┴──────────────────────────────────────────┘

Put cross-cutting concerns (throttling, per-device serialization) in the decisions table below.

Then the other decisions:

┌─────────────────────────────────────┬────────────────────────────────────────┐
│ Decision                            │ In This Environment                    │
├─────────────────────────────────────┼────────────────────────────────────────┤
│ ITSM integration                    │ ServiceNow — create incidents          │
│ Naming convention                   │ VLAN_{id}_{site} (customer standard)   │
└─────────────────────────────────────┴────────────────────────────────────────┘

D. Modular Design — Decompose First

Before listing components, decide the parent/child split. For a parent agent with child agents, list each child as its own agent with its own job and inputs, and cover in Section F how the parent handles a child that fails or stops and any step that waits for a person. For workflow designs, ask for each phase:

  • Can it be run and tested independently? → Child workflow
  • Does it make sense to reuse it in other use cases? → Child workflow
  • Does it loop over multiple items? → Child workflow with loopType
  • Is it a one-off step that only makes sense in this flow? → Task in orchestrator

Workflow rule: Each logical phase becomes a child workflow. The orchestrator sequences them via childJob. This makes every phase independently testable before the orchestrator is built. It doesn’t apply to parent and child agents.

Example decomposition:

Spec phases → Component split
─────────────────────────────────────────────────────────
Pre-flight validation        → Child: Pre-Flight Check
Execute change               → Child: Execute Change
Verify propagation           → Child: Verify Propagation
Rollback on failure          → Child: Rollback
Notifications + ticket close → Tasks in orchestrator

The orchestrator is always the last thing built, after all children are tested.

D. Component Inventory

┌────┬──────────────────────────────┬─────────────────────┬──────────┐
│ #  │ Component                    │ Type                │ Action   │
├────┼──────────────────────────────┼─────────────────────┼──────────┤
│ 1  │ Pre-Check                    │ Command Template    │ Build    │
│ 2  │ Backup workflow              │ Child Workflow      │ Reuse    │
│ 3  │ Orchestrator                 │ Parent Workflow     │ Build    │
└────┴──────────────────────────────┴─────────────────────┴──────────┘

When the execution model calls for them, use these types: LCM Resource Model, LCM Action (on a new or existing model), Agent, Agent Tool Decorator, Gateway5 Service, Inventory. List an existing resource model, agent or service the design builds on with Action Reuse or Extend.

For every ⚠ Stub integration, add to the inventory:

  • integration-model-{name}.json — OpenAPI 3.0.3 stub spec (Type: Integration Model, Action: Build)
  • stub-{name} — stub connectivity workflow (Type: Stub Workflow, Action: Build)
  • integration-questions.md — customer questionnaire (Type: Questionnaire, Action: Build — one file covers all pending integrations)

Producing stub artifacts:

integration-model-{name}.json — OpenAPI 3.0.3, minimal and use-case scoped:

  • info.title — the adapter type name as it will appear in Itential (e.g., Slack, AWX) — this becomes the app and locationType field values in workflow tasks
  • info.description — one line: what this integration does in this use case; append — STUB: scope TBC with customer if endpoints aren’t yet confirmed
  • servers[].url — use a variables block for unknown hostnames; add "description": "STUB: confirm with customer" to any unknown variable
  • components.securitySchemes — mark description as STUB: confirm auth method with customer if not yet confirmed
  • paths — only the operations the stub workflow will call; use accurate schemas where known

integration-questions.md — one section per pending integration, three-column table:

Question Why needed Customer answer
Hostname / base URL Needed to configure the adapter server
Auth method (bearer / basic / API key) Determines how credentials are stored
Token source / how to obtain it Needed to provision the adapter
API version or path prefix differences Affects endpoint wiring in workflows
Firewall / IP allowlisting requirements Platform must be able to reach this system

Close integration-questions.md with a Next steps note: once all questions are answered, update each integration model, provision the adapter, and replace placeholder tasks using the as-built activation recipes.

E. Implementation Plan — ordered build steps with test method for each

For a phase built agent first, plan both stages now:

  1. The agent and its test sessions. Say what counts as proven (e.g., N sessions on real requests with the expected result) and who decides.
  2. /flowagent-to-spec turns the proven sessions into <phase>-converted-spec.md, which comes back through design-only mode and Build. The engineer can still decide at that point to keep the agent.

F. Acceptance Criteria → Tests — map each criterion to how to verify it. This is a first-pass mapping — /qa-agent refines it into an executable test-plan.md once real IDs exist after Build, but the verification method per criterion should be decided now, while the design is fresh.

Present for Review

Present the full solution design. Do NOT proceed to build until approved.

Walk through each section:

  • Execution model: “[Phase] runs as [model], built [agent first / direct], because [answer or inventory fact]. Agree?”
  • Requirements: “I’ll use [adapter/app]. Correct?”
  • Decisions: “The spec says [X], I’ll do [Y]. Sound right?”
  • Components: “Reuse this? Build that? Skip this?”
  • Plan: “Here’s the build order. Agree?”

The engineer may:

  • Change reuse → build (“that workflow is outdated”)
  • Add components (“we also need a cleanup workflow”)
  • Change the plan order
  • Modify how acceptance criteria get tested

Update {use-case}/solution-design.md with every change.


Design Approval

When the engineer approves the solution design: it is locked.

Both artifacts are now complete before any building begins:

  1. {use-case}/customer-spec.md — HLD, approved (Requirements)
  2. {use-case}/feasibility.md — assessment + decision, approved (Feasibility)
  3. {use-case}/solution-design.md — Solution Design / LLD, approved (Design)

Hand off to /builder-agent. The workspace is complete.


Handoff to Builder

The workspace the /builder-agent agent receives:

{use-case}/
  .auth.json              ← auth token
  .env                    ← credentials (for re-auth)
  use-case-memory.md      ← living context: platform refs, built assets, decisions, open items
  customer-spec.md        ← approved HLD
  feasibility.md          ← approved feasibility assessment
  solution-design.md      ← approved Solution Design / LLD
  customer-context.md     ← business rules, naming (if provided)
  openapi.json            ← platform API reference (pulled during feasibility)
  tasks.json              ← task catalog (pulled during feasibility)
  apps.json               ← app/adapter type names (pulled during feasibility)
  adapters.json           ← adapter instances (pulled during feasibility)
  integrations.json       ← integration instances, credentials removed (pulled during feasibility)
  applications.json       ← app health (pulled during feasibility)
  devices.json            ← device inventory (if spec involves devices)
  workflows.json          ← existing workflows (if reuse planned)
  device-groups.json      ← device groups (if spec involves groups)
  task-schemas.json       ← fetched on demand by builder during build (not pre-populated)

The builder builds from the locked plan and tests each component individually. Once the build is complete, /builder-agent hands off to /qa-agent, which runs acceptance testing against Section F’s criteria-to-tests mapping and produces the as-built.md record.

Before handing off — update use-case-memory.md (create from assets/helpers/use-case-memory.md if /spec-agent didn’t already):

  • Platform URL and project name (if a project already exists)
  • Stage: build, Status: active
  • Any adapter instance names and type names resolved during feasibility
  • Key decisions made during design (why this adapter, why this split, any constraints)
  • The execution model per phase and its delivery path; for agent-first phases, that the /flowagent-to-spec conversion is still to come

Update Stage at each internal transition too, not just at final handoff — set Stage: feasibility when starting the feasibility assessment (if /spec-agent left it at requirements) and Stage: design once feasibility is approved and design work begins. Someone resuming mid-Feasibility shouldn’t see Stage: build.

The builder will read this file first and update it after every build session.


How This Gets Invoked

Entered from /spec-agent after the engineer approves customer-spec.md. At that point the workspace contains:

{use-case}/
  customer-spec.md    ← approved HLD (Requirements complete)
  .env                ← credentials
/solution-arch-agent flow:
    Feasibility: authenticate → pull platform data → assess capabilities → inventory LCM / FlowAgent / Gateway5 → write feasibility.md → engineer approves
    Design:      design the execution model with the engineer → produce solution-design.md → engineer approves
    Handoff:     pass complete workspace to /builder

To revise requirements: update customer-spec.md via /spec-agent → re-run /solution-arch-agent from Feasibility. To revise design only: invoke /solution-arch-agent design-only → reads existing feasibility.md → produces updated solution-design.md.


Gotchas

  • Tokens expire mid-session — on auth errors, re-authenticate silently from .env (see assets/AGENTS.md Auth Reuse)
  • tasks/list app field has WRONG casing for adapters — use apps/list
  • A system connected as an integration is absent from /health/adapters — check integrations in platform-summary.json before marking a required system not found
  • OpenAPI spec is ~1.5MB — search it locally with jq, never load into context