Menu
Reuse prior work only when hashes, dependencies, and artifact semantics still support it.
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
Based on SOC occupation classification
Enforce artifact-contract, presence, dependency, freshness, and cross-reference correctness for the artifact graph.
Normalize remote configuration and connection hints into machine-readable, ambiguity-aware remote artifacts.
Run a bounded, evidence-heavy cribdrag workflow for suspected keystream reuse and XOR-style leakage.
Drive decode-first problems through explicit candidate generation, convergence tests, and branch stop conditions.
Map mixed decode-plus-crypto chains into explicit stages, transitions, and evidence-backed branch routes.
Build explicit vulnerability hypotheses with preconditions, discriminators, costs, scores, and attack-family context.
| name | crypto_artifacts-reuse |
| description | Reuse prior work only when hashes, dependencies, and artifact semantics still support it. |
| metadata | {"short-description":"Resume safely from prior artifacts without inheriting stale state"} |
This skill decides whether existing artifacts can be trusted, partially reused, or must be invalidated. It prevents the workflow from repeatedly starting over while also preventing the more dangerous failure mode of inheriting obsolete conclusions.
artifacts/ treeClassify every important artifact into one of four buckets:
For each bucket, write the practical consequence into continuation planning. Do not merely label an artifact stale; say exactly what workflow branches are blocked by that staleness.
When invalidating a route, remove or rewrite all references to it in:
Pass only if continuation plan, stale report, and invalidation consequences all agree on what is safe to reuse and what must be rebuilt.