open/ms-ai-architect
1
0
Fork 0
Code Issues Releases 1 Activity

fix(ms-ai-architect): RX-P1 installert-modus-hardening — ${CLAUDE_PLUGIN_ROOT}-forankring + scoped agent-delegering [skip-docs]

Browse source 
- Forankre 115 skills/-KB-stier med ${CLAUDE_PLUGIN_ROOT}/ i 26 commands + 10 agenter
  (relative stier resolver kun dev-modus; installert fra katalog mistet subagentene KB-last)
- Foren delegering til registrert scoped navn ms-ai-architect:<agent>
  (var: architect:X feil-namespace + bare navn + general-purpose+"Read agents/X.md")
- Dropp redundant "Read/Les agents/X.md"-instruks (scoped agent auto-laster egen kropp)
- Bevar per-kommando KB-kontrakt inkl. dpia betinget data-residens-ruting (Option B)
- generate-skills: sonnet→opus (opus-direktiv), {PLUGIN_ROOT}→${CLAUDE_PLUGIN_ROOT};
  git-pathspecs holdt repo-relative
- plugin.json repository: ktg-plugin-marketplace→ms-ai-architect (polyrepo egen repo)
- validate-plugin.sh Check 6 (install-safety lint: sti + delegering + opus-only) + node-wrapper i kanonisk suite
This commit is contained in:
Kjell Tore Guttormsen 2026-07-15 10:59:04 +02:00
commit 5b05009b44
39 changed files with 247 additions and 148 deletions
Download patch file Download diff file Expand all files Collapse all files

10
agents/security-assessment-agent.md
View file

@ -21,9 +21,9 @@ You are a Microsoft AI security specialist. You assess AI architectures against
## Knowledge Base References (max 3 per invokasjon)
Read these core files:
- `skills/ms-ai-security/references/ai-security-engineering/security-scoring-rubrics-6x5.md` — **OBLIGATORISK:** Deterministiske scoringsrubrikker
- `skills/ms-ai-security/references/ai-security-engineering/ai-security-scoring-framework.md` — Scoring-rammeverk
- `skills/ms-ai-security/references/ai-security-engineering/ai-threat-modeling-stride.md` — STRIDE trusselmodellering
- `${CLAUDE_PLUGIN_ROOT}/skills/ms-ai-security/references/ai-security-engineering/security-scoring-rubrics-6x5.md` — **OBLIGATORISK:** Deterministiske scoringsrubrikker
- `${CLAUDE_PLUGIN_ROOT}/skills/ms-ai-security/references/ai-security-engineering/ai-security-scoring-framework.md` — Scoring-rammeverk
- `${CLAUDE_PLUGIN_ROOT}/skills/ms-ai-security/references/ai-security-engineering/ai-threat-modeling-stride.md` — STRIDE trusselmodellering
Load additional files only when assessment requires specific depth:
- Prompt injection: `ai-security-engineering/prompt-injection-defense-patterns.md`
@ -147,8 +147,8 @@ Read the architecture proposal or solution description. Look for:
### 2. Load Reference Knowledge
Read these knowledge base files:
- `skills/ms-ai-advisor/references/architecture/security.md` — Security best practices
- `skills/ms-ai-advisor/references/architecture/public-sector-checklist.md` — Norwegian compliance (if exists)
- `${CLAUDE_PLUGIN_ROOT}/skills/ms-ai-advisor/references/architecture/security.md` — Security best practices
- `${CLAUDE_PLUGIN_ROOT}/skills/ms-ai-advisor/references/architecture/public-sector-checklist.md` — Norwegian compliance (if exists)
### 3. Validate Latest Guidance
Use `microsoft_docs_search` for: