Reverse engineer anything with agents, from app behavior down to native binaries.
TypeScript agent-skillsai-agentsbinary-analysisclaude-codeclicodexcordisdecompilerdeveloper-toolsdshdsh-pluginghidrahopperllmmcpmodel-context-protocolreareverse-engineeringstatic-analysistouhou
docs(contracts)!: explain canonical URL and skill metadata ownership
morlutoe36afa112fd7
diff --git a/docs/installation.md b/docs/installation.mdindex fecbe4aa0..1152dd848 100644--- a/docs/installation.md+++ b/docs/installation.md@@ -199,6 +199,12 @@ use the shared `~/.agents/skills` directory. A mixed selection plans bothpaths. Selecting the skill without a client uses the shared directory. Setupleaves existing skill copies in other locations untouched.+`doctor --skill --json` verifies the selected copies against the bundled+instructions and references. Consumers should use `identity.skill.state`,+`installed_version`, and `installed_tool_count` for skill readiness. The+obsolete `installed_catalog_digest` field has been removed; current catalog+identity remains available at `identity.catalog`.+After selection, review the plan's exact paths and changes and approve beforeREA writes files or installs Hopper. You can cancel at any prompt.diff --git a/docs/javascript-application-graph.md b/docs/javascript-application-graph.mdindex fd87b00ee..2290491a5 100644--- a/docs/javascript-application-graph.md+++ b/docs/javascript-application-graph.md@@ -81,6 +81,10 @@ one physical source map. The full URL is kept out of node identity, displaylabel, and edge properties, so large inline data URLs are stored once persource-map reference.+Consumers previously reading `edge.properties.declared_url` should follow+`target_node_id` and select the observation by `declared_url_sha256` instead.+Node labels serve display; the observation preserves the original URL.+For example, a source-owned synthetic fixture proves this path without using athird-party application:diff --git a/docs/javascript-artifact-reconstruction.md b/docs/javascript-artifact-reconstruction.mdindex 372934b7a..881b244d6 100644--- a/docs/javascript-artifact-reconstruction.md+++ b/docs/javascript-artifact-reconstruction.md@@ -112,6 +112,13 @@ Field selection remains useful when the caller needs asmaller view, for example `--format json --filter-outputevidence_id,normalized_result.statistics`. Streaming output does not bound thememory needed to construct the analysis graph itself.++CLI workflows still parse each JSON input as one value. A valid input exceeding+the Node runtime's maximum string length returns `resource_constraint` with+`input_reason: "too-large"` and the runtime limit. Produce smaller independent+analysis inputs before retrying; streaming output does not imply streaming+input parsing.+MCP prepares the complete repeated response incrementally against the pinnedSDK's 10 MiB stdio receive-buffer budget. Oversized results return an actionabletransport constraint and the exact same-session Evidence reference. Use