メニュー
Aggregated architecture context for a scope — CALM nodes + ADRs + fitness functions + quality attributes. PURE data; the Architect persona is in the parent agent's prompt.
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
SOC 職業分類に基づく
Append one hash-chained audit event to okrs/<id>/audit/events/<run-id>.jsonl. Returns the new chain head.
Replay the hash chain over an existing audit JSONL; returns the chain head on success, the first integrity failure reason on failure.
Query the mesh's threat library for entries matching a concern (e.g. "identity", "data-licensing").
Academic paper search via arXiv. Returns ranked paper results per query envelope.
Aggregated quality context for a scope — quality attribute definitions + performance SLOs + reliability targets per BAR.
Aggregated security context for a scope — STRIDE threats + OWASP refs + NIST controls + prior threat-model docs. PURE data; the Security persona is in the parent agent's prompt.
| name | context-architecture |
| description | Aggregated architecture context for a scope — CALM nodes + ADRs + fitness functions + quality attributes. PURE data; the Architect persona is in the parent agent's prompt. |
| version | 0.1.0 |
| purity | pure-data |
| runtime | research-runner |
| command | npx @maintainabilityai/research-runner@~0.1.64 skill-context-architecture |
Walks the mesh and assembles the structured-data input the Architect persona reasons against. No LLM inside (the persona lives in the parent agent's system prompt per §5.4); this skill is the grounding-data half.
| Field | Type | Required | Default | Description |
|---|---|---|---|---|
platformId | string | yes | — | Platform to aggregate over. |
barIds | string[] | yes | — | BARs to aggregate over. |
| Field | Type | Description |
|---|---|---|
ok | boolean | |
calmNodes | { id, type, relatedThreats[], relatedAdrs[] }[] | Union across the in-scope BARs + platform. |
relationships | { source, dest, kind }[] | Edges from each BAR's CALM. |
adrs | AdrRecord[] | All ADRs in scope. |
fitnessFunctions | FitnessFunction[] | Per-BAR fitness funcs. |
qualityAttributes | QualityAttribute[] | Per-BAR QAs. |
echo '{"platformId":"PLT-IMDB","barIds":["APP-IMDB-001","APP-IMDB-002"]}' \
| npx @maintainabilityai/research-runner@~0.1.64 skill-context-architecture
Walks each in-scope BAR + the platform, applies a "what's relevant" filter, returns structured JSON. See §7.4 for the canonical output shape. CLI subcommand backend lands in B-PR1a.
{ok: false, reason: 'mesh-walk-failed'} only on filesystem errors. Empty BARs return ok: true with empty arrays.