claude-code-decompiled (research reports)
Summary
A documentation-only collection of 20 independent research reports on Claude Code v2.1.88 covering architecture, agent behavior, permission design, prompt assembly, MCP integration, and context management. Deliberately ships analysis rather than extracted code.
Key Takeaways
- Report set spans permissions, prompt assembly, MCP, and context management
- Documentation-only approach is the cleanest for attribution
- Strong specifics on permission tiers around dangerous tools
Reliability Note
Independent reverse-engineering effort - unofficial, verify against official Anthropic docs and behavior.
Flows informed by this source
5
Design Tool Schemas for Agents
Write tool schemas that constrain model behavior: tight types, enums over strings, and parameters that make misuse hard.
+1 more steps to Done
Best forbuilders who have shipped a basic app before
Hook a Permission Layer onto Dangerous Tools
Intercept dangerous tool calls with a hook layer: pattern rules, approval gates, and blocks that the model cannot talk its way past.
+1 more steps to Done
Best forbuilders who have shipped a basic app before
Sub-Agent Delegation with Context Isolation
Delegate bounded work to sub-agents that run in fresh context and return only distilled results - the pattern behind scalable long tasks.
+1 more steps to Done
Best forproduction-grade builds with strict verification
Deferred Tool Loading
Stop paying context for tools the task never needs: load a core set eagerly and expand the toolset on demand.
+1 more steps to Done
Best forproduction-grade builds with strict verification
Rate and Blast-Radius Limits for Destructive Tools
Cap how much damage any window of agent activity can do: rate limits, change budgets, checkpoints, and undo.
+1 more steps to Done
Best forbuilders who have shipped a basic app before