Menu
Compare estimated token usage between full memory reads and optimized synthesis.
Installer avec Codex ou Claude Copiez ce prompt, collez-le dans Codex, Claude ou un autre assistant, puis laissez-le vérifier la page du skill et l'installer pour vous.
Basé sur la classification professionnelle SOC
Prioritize official @wordpress packages over external dependencies. Detect React conflicts, use aliasing, and validate package usage.
Apply approved architecture refactors by updating plan and task artifacts directly.
Perform a framework-agnostic architecture review validating implementation against spec.md, plan.md, tasks.md, and the governance and architecture constitutions.
Perform an architecture-aware verification gate validating implementation against spec.md, plan.md, tasks.md, and the Architecture Constitution.
Run a single architecture workflow that prefers memory-first context and can incorporate security review when available.
Run implementation with memory context, then review the produced implementation against security and architecture constraints.
| name | speckit-memory-md-token-report |
| description | Compare estimated token usage between full memory reads and optimized synthesis. |
| compatibility | Requires spec-kit project structure with .specify/ directory |
| metadata | {"author":"github-spec-kit","source":"memory-md:commands/speckit.memory-md.token-report.md"} |
Compare estimated token usage between the full durable-memory read and the optimized synthesis flow.
Use this when:
When the optimizer is enabled and the CLI is available, run:
cd .specify/extensions/memory-md && npx speckit-memory token-report --feature specs/<feature>
Report:
Token counts are estimates using @dqbd/tiktoken with the cl100k_base encoding (GPT-4 calibrated).
Actual provider billing tokens may differ. For Claude or Gemini, estimates may be 15–30% off.
If the optimizer is disabled or unavailable, report the markdown-only baseline and note that the optimized comparison could not be measured.