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(tools): clarify complete inline workflows
morluto41681742ccea
diff --git a/docs/javascript-application-graph.md b/docs/javascript-application-graph.mdindex 9446478c6..d62552cbf 100644--- a/docs/javascript-application-graph.md+++ b/docs/javascript-application-graph.md@@ -159,9 +159,8 @@ so callers cannot preserve a stale ID after changing semantic content.## Structure-The graph does not impose aggregate caps on roots, nodes, edges, or observations.-Each properties object is valid JSON with at most 64 keys, depth 6, 512-structural nodes, and 4,096 characters per string. Field-specific validation+The graph does not impose aggregate caps on roots, nodes, edges, observations,+or JSON properties. Properties must be valid JSON; field-specific validationstill applies to paths, identifiers, and evidence values. Extractors reportactual omissions in coverage instead of silently dropping a prefix.diff --git a/docs/javascript-application-workflows.md b/docs/javascript-application-workflows.mdindex 16414e0e1..ccc0dd572 100644--- a/docs/javascript-application-workflows.md+++ b/docs/javascript-application-workflows.md@@ -49,7 +49,7 @@ The extractor covers lexical definitions and reads, literal seeds, staticproperty slots, object reads/writes/spreads/destructuring, closure captures,uniquely resolved local calls, argument/return flow, and explicit Promiseconstruction, chaining, aggregation, await, return, assignment, and-detachment. It also recovers bounded static candidates for EventEmitter+detachment. It also recovers static candidates for EventEmitterregistrations/removals and dispatch, Node timers and cancellation handles, asynchronous`node:child_process` creation and ownership, configuration sources and directdefaults, request construction and response consumers, parse/coercion/@@ -58,9 +58,9 @@ validation boundaries, and built-in resource acquisition/release.Function fingerprints commit normalized syntax, control-flow shape, relationshape, literal sets, arity, and detected effects without using local names orsource offsets. Equal duplicate fingerprints remain ambiguous. Dynamic-calls/properties/names, parser recovery, unresolved handles, unsupported API-shapes, and every reached bound stay explicit unknowns; a missing relation is-never reported as proven behavioral absence.+calls/properties/names, parser recovery, unresolved handles, and unsupported API+shapes stay explicit unknowns; a missing relation is never reported as proven+behavioral absence.Semantic relations use static-inference authority. `resolved` means the statictarget identity was unique within admitted analysis; it does not mean the path@@ -122,9 +122,8 @@ relationships recovered by the AST analysis.Direct return expressions, including expression-bodied arrows, are evaluatedthrough an execution-free value lattice. Literal object fields and direct-return sites are retained without count quotas. Calls, dynamic spreads,-computed keys, parser recovery, and the value-recursion depth guard remain-partial or unknown.+return sites are represented in the result. Calls, dynamic spreads, computed+keys, and parser recovery remain partial or unknown.Nested callable returns are not assigned to their parent callable. Projectedgraph observations carry source ranges but never source text.diff --git a/docs/javascript-runtime-reconciliation.md b/docs/javascript-runtime-reconciliation.mdindex 8ee62aa5a..cdd340079 100644--- a/docs/javascript-runtime-reconciliation.md+++ b/docs/javascript-runtime-reconciliation.md@@ -47,12 +47,7 @@ are complete Evidence objects, not only evidence IDs:]}],- "runtime_observations": ["INSPECT_WEB_PAGE_EVIDENCE"],- "limits": {- "max_runtime_entities": 10000,- "max_reconciliation_items": 20000,- "max_static_load_states": 20000- }+ "runtime_observations": ["INSPECT_WEB_PAGE_EVIDENCE"]}```@@ -101,13 +96,13 @@ nodes. REA evaluates compatible static candidates conservatively:3. Without captured bytes, one unique mapped artifact path can produce amedium-confidence location match.4. Multiple candidates remain `ambiguous`; no `observed_as` edge is emitted.- `candidate_static_count` reports the full qualified layer/node count while- `candidate_static_nodes` retains a deterministic bounded prefix.+ `candidate_static_count` reports the full qualified layer/node count, and+ `candidate_static_nodes` includes every unique candidate reference.5. If captured bytes disagree with the static candidate at the mapped path,the result is an explicit mismatch. A path never overrides a digestdisagreement.-6. Missing authorization mappings, incomplete input coverage, and output- limits remain unknown or truncated rather than becoming absence claims.+6. Missing authorization mappings and incomplete or truncated input coverage+ remain unknown or truncated rather than becoming absence claims.Every successful cross-layer `observed_as` edge has`authority: cross-layer-reconciliation` and `state: inferred`. The underlying@@ -124,7 +119,7 @@ classification:- `resident-in-loaded-asset` means a containing asset was observed, but theembedded module was not independently observed or shown to execute;- `not-observed-in-capture` means the entity did not appear in the complete- bounded captures supplied to this call and its artifact path falls beneath+ authorized captures supplied to this call and its artifact path falls beneathan exercised automatic or operator-declared mapping prefix;- `unknown` covers incomplete captures, layers outside runtime scope, andunresolved correspondence. Nodes outside a mapped artifact prefix staydiff --git a/docs/mcp-contracts.md b/docs/mcp-contracts.mdindex f299da833..70fdb738c 100644--- a/docs/mcp-contracts.md+++ b/docs/mcp-contracts.md@@ -58,9 +58,8 @@ shutdown rules still apply; REA never kills a process it cannot prove it owns.## Tool resultsEvidence-producing tools return their result and Evidence context inline. Read-that result directly; do not fetch a bundle or resource to inspect it. Use-`get_evidence_bundle` only when the task explicitly needs broader retained-session history or a bundle for transfer.+that result directly. Use `get_evidence_bundle` when the task needs broader+retained session history or an explicit bundle for transfer.## Aggregate native contextdiff --git a/docs/product-catalog.json b/docs/product-catalog.jsonindex 3776a82c2..54e846f92 100644--- a/docs/product-catalog.json+++ b/docs/product-catalog.json@@ -501,9 +501,9 @@"mcp_prompts": 6},"digests": {- "tools_sha256": "dcc3c3dbe9068ac7ec6774552ca309faaf0a6f5f992dd857b3dffea47f7bbf31",+ "tools_sha256": "37c7ca2a93d9c78dd5372b88db55626d7ee5474bbb1b82477d14363631d68ddf","prompts_sha256": "fa889fc671185ac9c968c6dc8309cf609e709cdc837dbbf39b7cdfadb84ac2d7",- "combined_sha256": "10ddf103b5e479182562331658d8bb5f128e356002ddb40431371af1a1cf7794",+ "combined_sha256": "64e291ccdfb45d454eb084b2944e94d5b46fbdec61802cff95ad6bd420125526","providers_sha256": "7247eece8fad09c8023af8d5c682d223d7ed7ebd68eac79e9154962a7e03b66b"}}diff --git a/skills/reverse-engineer-anything/SKILL.md b/skills/reverse-engineer-anything/SKILL.mdindex 5df0f4ff6..e8e686dd3 100644--- a/skills/reverse-engineer-anything/SKILL.md+++ b/skills/reverse-engineer-anything/SKILL.md@@ -4,7 +4,7 @@ description: Reverse engineer native, managed, Electron/JavaScript, packaged, anmetadata:version: "23"tool_count: 111- catalog_digest: "10ddf103b5e479182562331658d8bb5f128e356002ddb40431371af1a1cf7794"+ catalog_digest: "64e291ccdfb45d454eb084b2944e94d5b46fbdec61802cff95ad6bd420125526"---# REAdiff --git a/skills/reverse-engineer-anything/references/javascript-applications.md b/skills/reverse-engineer-anything/references/javascript-applications.mdindex 9b6d8aea0..195e05f1b 100644--- a/skills/reverse-engineer-anything/references/javascript-applications.md+++ b/skills/reverse-engineer-anything/references/javascript-applications.md@@ -1,12 +1,10 @@# JavaScript and Electron application artifactsUse `analyze_javascript_application` directly on the operator-supplied ASAR or-extracted tree. It reads the selected local path without an approval flag or-configured investigation root. The complete result, graph, and Evidence context-are returned inline, so inspect them directly without fetching resource links.-Source-map contents are part of the static analysis. Start from its findings,-coverage, unknowns, and graph context, then make a focused follow-up only when a-specific question remains unanswered.+extracted tree. The complete result, graph, and Evidence context are returned+inline. Source-map contents are part of the static analysis. Start from its+findings, coverage, unknowns, and graph context, then make a focused follow-up+only when a specific question remains unanswered.BrowserWindow preferences, preload and contextBridge surfaces, IPCregistrations, utility processes, and native binding requests are static syntax@@ -17,8 +15,8 @@ registration, defaults, or policy enforcement from static analysis.Use `trace_application_feature` on existing application Evidence for oneliteral node ID, route, string, API, IPC channel, module, or native export.-Choose a direction and finite bounds. Link Hopper or Ghidra Evidence only when-the exact artifact digest matches.+Choose a direction and include the complete application Evidence inline. Include+Hopper or Ghidra Evidence only when its artifact digest matches exactly.For version comparison, analyze each version once, then call`compare_application_versions`. Accept only its digest, source-map, structural@@ -29,9 +27,9 @@ opposite-side coverage; otherwise report unknown.When the question asks how one exact exported callable's returned object shapechanged, analyze each version once and then call`compare_javascript_export_shapes` with explicit module paths and export names.-Use the Evidence IDs returned by the two analysis calls. Accept variant pairing-only through the tool's unique exact literal discriminant. Cite the comparison-Evidence and report JSON Pointer changes; dynamic values, ambiguous variants,-and incomplete parent-property coverage stay unknown. This is static inference,-not runtime behavior. Use `run_controlled_replay` separately only when the user-needs approved runtime semantics.+Include the complete Evidence records from both analysis calls. Accept variant+pairing only through the tool's unique exact literal discriminant. Cite the+comparison Evidence and report JSON Pointer changes; dynamic values, ambiguous+variants, and incomplete parent-property coverage stay unknown. This is static+inference, not runtime behavior. Use `run_controlled_replay` separately only+when the user needs approved runtime semantics.