2026-05-18 16:55:46 +02:00
|
|
|
# NetKingdom — Claude Code Instructions
|
|
|
|
|
|
|
|
|
|
@SCOPE.md
|
|
|
|
|
@.claude/rules/repo-identity.md
|
|
|
|
|
@.claude/rules/session-protocol.md
|
|
|
|
|
@.claude/rules/first-session.md
|
|
|
|
|
@.claude/rules/workplan-convention.md
|
|
|
|
|
@.claude/rules/stack-and-commands.md
|
|
|
|
|
@.claude/rules/architecture.md
|
|
|
|
|
@.claude/rules/repo-boundary.md
|
2026-06-18 22:48:38 +02:00
|
|
|
@.claude/rules/credential-routing.md
|
2026-05-18 16:55:46 +02:00
|
|
|
@.claude/rules/agents.md
|
2026-10-03 15:25:38 +02:00
|
|
|
|
|
|
|
|
<!-- BEGIN EMERGENT-SECURITY-PILOT -->
|
|
|
|
|
## NetKingdom situational knowledge pilot
|
|
|
|
|
|
|
|
|
|
For security-related work, read the shared
|
|
|
|
|
[Emergent Security orientation](../emergent-security/knowledge/cards/start.md)
|
|
|
|
|
and the task's card in that package. From this repository root, validate and read:
|
|
|
|
|
|
|
|
|
|
```bash
|
|
|
|
|
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`.
|
|
|
|
|
<!-- END EMERGENT-SECURITY-PILOT -->
|
2026-10-24 23:12:37 +02:00
|
|
|
|
|
|
|
|
<!-- BEGIN NETKINGDOM-SECURITY-QUICKSTART -->
|
|
|
|
|
## 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.
|
|
|
|
|
<!-- END NETKINGDOM-SECURITY-QUICKSTART -->
|
