net-kingdom/AGENTS.md

NetKingdom — Agent Instructions

Repo Identity

Purpose: NetKingdom infrastructure and IAM platform — orchestrates SSO/MFA, multi-user onboarding, and the Keycape/Keycloak IAM profile across the NetKingdom environment.

Domain: infotech Repo slug: net-kingdom Topic ID: cee7bedf-2b48-46ef-8601-006474f2ad7a Workplan prefix: NK-WP-

---

State Hub Integration

The Custodian State Hub tracks work across all domains. Interact via HTTP REST — there is no MCP server for Codex agents.

Context	URL
Local workstation	http://127.0.0.1:8000
Remote (railiance01, in-cluster)	http://10.43.68.154:8000
Optional local edge relay	http://127.0.0.1:18080

When an operator has enabled the edge relay, set API_BASE to the relay URL. Queueable writes return an explicit queued receipt if the central hub is unreachable. Treat that as pending local evidence, then ask the operator to run statehub outbox status/replay after connectivity returns.

Orient at session start

# Offline brief — works without hub connection
cat .custodian-brief.md

# Active workplans for this domain
curl -s "http://127.0.0.1:8000/workplans/?topic_id=cee7bedf-2b48-46ef-8601-006474f2ad7a&status=active" \
  | python3 -m json.tool

# Check inbox
curl -s "http://127.0.0.1:8000/messages/?to_agent=net-kingdom&unread_only=true" \
  | python3 -m json.tool

Mark a message read:

curl -s -X PATCH "http://127.0.0.1:8000/messages/<id>/read" \
  -H "Content-Type: application/json" -d '{}'

Log progress (required at session close)

curl -s -X POST http://127.0.0.1:8000/progress/ \
  -H "Content-Type: application/json" \
  -d '{
    "summary": "what was done",
    "event_type": "note",
    "author": "codex",
    "workplan_id": "<uuid>",
    "task_id": "<uuid>"
  }'

Omit workplan_id / task_id when not applicable.

Update task status

curl -s -X PATCH "http://127.0.0.1:8000/tasks/<task_id>" \
  -H "Content-Type: application/json" \
  -d '{"status": "progress"}'
# values: wait | todo | progress | done | cancel

Flag a task for human review

curl -s -X PATCH "http://127.0.0.1:8000/tasks/<task_id>" \
  -H "Content-Type: application/json" \
  -d '{"needs_human": true, "intervention_note": "reason"}'

---

Session Protocol

Start:

1. cat .custodian-brief.md — domain goal and open workplans (offline-safe)
2. Check inbox: GET /messages/?to_agent=net-kingdom&unread_only=true; mark read
3. Scan workplans: ls workplans/ — note status: ready, active, or blocked files and open tasks
4. Check human-needed tasks: GET /tasks/?needs_human=true

During work:

• Update task statuses in workplan files as tasks progress
• Record significant decisions via POST /decisions/

Close:

1. Update workplan file task statuses to reflect progress
2. Log: POST /progress/ with a summary of what changed
3. After workplan file changes, run:

   statehub fix-consistency
   

   Coding agents should run this directly; ask the operator only if the CLI or State Hub API is unavailable. This syncs task status from files into the hub DB.

---

Credential and access routing

Audience: Codex, Claude Code, Grok, and custodian agents that call llm-connect for inference. Run this check before requesting secrets, API keys, SSH access, login tokens, or database passwords — in any repo, not only ops-warden.

ops-warden issues SSH certificates only (warden sign, cert_command). Every other credential need belongs to another subsystem. Do not message ops-warden on State Hub expecting a secret value; the reply is a pointer, not a key.

Lookup (do this first)

warden route find "<describe your need>" --json
warden route show <catalog-id> --json

Requires the warden CLI from ~/ops-warden (uv tool install . or uv run warden).

Agent runtime	How to orient
Codex / Grok (shell, HTTP State Hub)	warden route commands above; inbox to_agent=net-kingdom is for coordination, not secret vending
Claude Code (MCP when available)	get_domain_summary("custodian") for workplans; still use warden route for credential ownership
llm-connect (inference service)	Never put secret retrieval in prompts; route custody to OpenBao/operator paths surfaced by warden route

Quick routing table

I need…	Owner	ops-warden executes?
SSH cert (adm/agt/atm)	ops-warden	Yes — warden sign
API key, DB password, provider token	OpenBao (railiance-platform)	No — route only
Login / OIDC / MFA	key-cape / Keycloak	No — route only
Authorization decision	flex-auth	No — route only
activity-core → issue-core emission	activity-core + issue-core	No — warden route show activity-core-issue-sink
SSH tunnel	ops-bridge (+ cert_command from warden)	No — route only

Anti-patterns (do not do these)

• POST /messages/ to ops-warden asking for ISSUE_CORE_API_KEY, OPENROUTER_API_KEY, etc.
• Inventing warden secret, warden login, warden bao, warden tunnel — they do not exist
• Pasting secrets into Git, State Hub, workplans, logs, or chat

Other capabilities (reuse-surface)

Non-credential capabilities are usually discovered through reuse-surface federation (reuse-surface registry / capability.* indexes). Credential routing is inlined in every repo's agent instructions because it is high-frequency, high-risk, and easy to get wrong.

Canon: ~/ops-warden/wiki/CredentialRouting.md · catalog ~/ops-warden/registry/routing/catalog.yaml

---

Workplan Convention (ADR-001)

Work items originate as files in this repo — not in the hub. The hub is a read/cache/index layer that rebuilds from files.

New workplans use the registered NK-WP- prefix. Existing NK-WP, NET-WP and ADHOC IDs, filenames and hub UUIDs remain unchanged; do not renumber historical records to match this convention.

File location: workplans/NK-WP-NNNN-<slug>.md

Archived location: finished workplans may move to workplans/archived/YYMMDD-NK-WP-NNNN-<slug>.md. The YYMMDD prefix is the completion/archive date; the frontmatter id does not change.

Ad Hoc Tasks: small opportunistic fixes discovered during a session use workplans/ADHOC-YYYY-MM-DD.md with task ids ADHOC-YYYY-MM-DD-T01, etc. Use this only for low-risk work completed directly; create a normal workplan for anything needing analysis, design, approval, dependencies, or multiple phases.

Frontmatter:

---
id: NK-WP-NNNN
type: workplan
title: "..."
domain: infotech
repo: net-kingdom
status: proposed | ready | active | blocked | backlog | finished | archived
owner: codex
topic_slug: ...
created: "YYYY-MM-DD"
updated: "YYYY-MM-DD"
state_hub_workstream_id: "<uuid>"   # written by fix-consistency — do not edit
---

Use proposed for a new draft, ready after review against current repo state, and finished after implementation. stalled and needs_review are derived health labels, not frontmatter statuses.

Task block format (one per ## section):

## Task Title

` ` `task
id: NK-WP-NNNN-T01
status: wait | todo | progress | done | cancel
priority: high | medium | low
state_hub_task_id: "<uuid>"         # written by fix-consistency — do not edit
` ` `

Task description text.

Status progression: todo → progress → done; use wait for waiting/blocked work and cancel for stopped work.

To create a new workplan:

1. Write the file following the format above
2. Run statehub fix-consistency --repo net-kingdom directly, as required by the session close protocol. Ask the operator only if the CLI or API is unavailable.

Task refinement after substantial work (required)

Established by operator instruction on 2026-10-16; decision d90b2f1f-cdaf-43b1-99e7-71afb43672bb.

At each substantive checkpoint and before session close, compare the completed work and new knowledge with the current task structure. If substantial work was completed while the workplan's task granularity stayed unchanged, add completed task records for those evidenced outcomes and refine the remaining tasks. A long progress note inside the same broad open task does not satisfy this rule.

• Give each substantial completed deliverable a task with its actual outcome, completion date, evidence and limits. Retrospective recording is allowed; do not invent completion dates, deliveries, native acceptance or approvals.
• Split remaining work into independently manageable deliverables with an owner, next action, completion criteria and real dependencies. Use todo for work that can start; use wait only with a concrete prerequisite and unblock condition.
• Preserve existing task IDs, Hub UUIDs and history. When narrowing an umbrella task, explain the split and map moved scope to the new task IDs. Do not mark the umbrella done unless its retained scope is complete; preserve externally referenced acceptance gates until their dependencies are satisfied.
• Keep task counts honest: extracting completed scope must not count the same outcome twice or imply an effort-based completion percentage. Distinguish source/fixture proof, actual operational proof and owner acceptance.
• Record new risks and out-of-scope findings as explicit disposition/handoff tasks or linked live work records; do not silently expand authorization.

Make these changes in the repository source, commit/push, run the repository's required projection sync, and verify the actual projected task counts, statuses and dependencies. Progress events supplement the task structure; they do not replace it. A checkpoint report must show both substantive outcomes and newly refined remaining work when this rule is triggered.

NetKingdom situational knowledge pilot

For security-related work, read the shared Emergent Security orientation and the task's card in that package. From this repository root, validate and read:

PYTHONPATH=../emergent-security/src python3 -m emergent_security.knowledge --repositories .. show start --audience generic

Use the matching provider audience when known and retrieve the relevant card. Record package version, digest and source status; reload after resume/compaction or a repository switch. A withheld card requires source review; an offline snapshot is orientation only. If the sibling checkout is absent, use the trusted installed emergent-knowledge package or an explicitly reviewed exported bundle; do not silently download or execute a replacement.

This pilot adds situational knowledge, not authority, live readiness or a change to this repository's owner contracts. Work: emergent-security/EMERGENT-WP-0002.

Security quickstart for agents (Claude Code, Codex, Grok)

1. Find the tool: make security-tools lists every security tool, the question it answers, how to run it and whether an agent may run it (tools/security-tools.json is the machine-readable form). Tool availability is not permission.
2. Know the rules: SECURITY-COMPANION.md section 7 ("If you are an agent").
3. Credentials: warden route find "<need>" --json. Never ask for, print or store a secret value.
4. Accounts and accountable automation: canon/standards/service-identity-privilege_v0.1.md, rules SI-14 (agents) and SI-15 (prepare, admit, execute, verify, retain).
5. Your effective authority is everything your tools can reach (SEC-DSM DSM-AGENT-008). Live changes, private keys and production credentials belong to the person: prepare and test on synthetic fixtures, and give them the exact command to run.
6. Leave a trail: commits get assistant trailers from the hook; log State Hub progress with your agent name and session.