scip-query 0.20.0 → 0.21.0

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "scip-query",
-  "version": "0.20.0",
+  "version": "0.21.0",
   "description": "Evidence and verification for AI coding agents: map code, reuse concepts, finish migrations, and gate diffs.",
   "type": "module",
   "main": "dist/index.js",
@@ -40,6 +40,10 @@
       "import": "./dist/queries/architecture.js",
       "types": "./dist/queries/architecture.d.ts"
     },
+    "./queries/anchors": {
+      "import": "./dist/queries/anchors.js",
+      "types": "./dist/queries/anchors.d.ts"
+    },
     "./queries/bottlenecks": {
       "import": "./dist/queries/bottlenecks.js",
       "types": "./dist/queries/bottlenecks.d.ts"
@@ -92,6 +96,14 @@
       "import": "./dist/queries/dataflow.js",
       "types": "./dist/queries/dataflow.d.ts"
     },
+    "./queries/dependence-slice": {
+      "import": "./dist/queries/dependence-slice.js",
+      "types": "./dist/queries/dependence-slice.d.ts"
+    },
+    "./queries/dependency-depth": {
+      "import": "./dist/queries/dependency-depth.js",
+      "types": "./dist/queries/dependency-depth.d.ts"
+    },
     "./queries/dead": {
       "import": "./dist/queries/dead.js",
       "types": "./dist/queries/dead.d.ts"
@@ -104,14 +116,18 @@
       "import": "./dist/queries/deep-chains.js",
       "types": "./dist/queries/deep-chains.d.ts"
     },
+    "./queries/entry-map": {
+      "import": "./dist/queries/entry-map.js",
+      "types": "./dist/queries/entry-map.d.ts"
+    },
+    "./queries/system-map": {
+      "import": "./dist/queries/system-map.js",
+      "types": "./dist/queries/system-map.d.ts"
+    },
     "./queries/deps": {
       "import": "./dist/queries/deps.js",
       "types": "./dist/queries/deps.d.ts"
     },
-    "./queries/diff-gate": {
-      "import": "./dist/queries/diff-gate.js",
-      "types": "./dist/queries/diff-gate.d.ts"
-    },
     "./queries/diff-impact": {
       "import": "./dist/queries/diff-impact.js",
       "types": "./dist/queries/diff-impact.d.ts"
@@ -128,6 +144,10 @@
       "import": "./dist/queries/drift.js",
       "types": "./dist/queries/drift.d.ts"
     },
+    "./queries/evidence": {
+      "import": "./dist/queries/evidence.js",
+      "types": "./dist/queries/evidence.d.ts"
+    },
     "./queries/extract-candidates": {
       "import": "./dist/queries/extract-candidates.js",
       "types": "./dist/queries/extract-candidates.d.ts"
@@ -196,6 +216,10 @@
       "import": "./dist/queries/plan-context.js",
       "types": "./dist/queries/plan-context.d.ts"
     },
+    "./queries/context": {
+      "import": "./dist/queries/context.js",
+      "types": "./dist/queries/context.d.ts"
+    },
     "./queries/recent-duplicates": {
       "import": "./dist/queries/recent-duplicates.js",
       "types": "./dist/queries/recent-duplicates.d.ts"
@@ -204,6 +228,14 @@
       "import": "./dist/queries/redundant-reexports.js",
       "types": "./dist/queries/redundant-reexports.d.ts"
     },
+    "./queries/reference-neighborhood": {
+      "import": "./dist/queries/reference-neighborhood.js",
+      "types": "./dist/queries/reference-neighborhood.d.ts"
+    },
+    "./queries/reference-reachability": {
+      "import": "./dist/queries/reference-reachability.js",
+      "types": "./dist/queries/reference-reachability.d.ts"
+    },
     "./queries/refs": {
       "import": "./dist/queries/refs.js",
       "types": "./dist/queries/refs.d.ts"
@@ -256,6 +288,14 @@
       "import": "./dist/queries/slice.js",
       "types": "./dist/queries/slice.d.ts"
     },
+    "./queries/source-inspection": {
+      "import": "./dist/queries/source-inspection.js",
+      "types": "./dist/queries/source-inspection.d.ts"
+    },
+    "./queries/source-search": {
+      "import": "./dist/queries/source-search.js",
+      "types": "./dist/queries/source-search.d.ts"
+    },
     "./queries/stale-abstractions": {
       "import": "./dist/queries/stale-abstractions.js",
       "types": "./dist/queries/stale-abstractions.d.ts"
@@ -296,6 +336,10 @@
       "import": "./dist/queries/unused-params.js",
       "types": "./dist/queries/unused-params.d.ts"
     },
+    "./queries/value-flow": {
+      "import": "./dist/queries/value-flow.js",
+      "types": "./dist/queries/value-flow.d.ts"
+    },
     "./queries/unused-imports": {
       "import": "./dist/queries/unused-imports.js",
       "types": "./dist/queries/unused-imports.d.ts"
@@ -314,23 +358,35 @@
     }
   },
   "scripts": {
-    "build": "node --max-old-space-size=8192 ./node_modules/tsup/dist/cli-default.js",
+    "build": "node --max-old-space-size=16384 ./node_modules/tsup/dist/cli-default.js",
     "dev": "tsup --watch",
     "format": "prettier --write \"{src,tests,scripts}/**/*.{ts,tsx,js,mjs,json}\" \"*.{ts,js,json}\"",
     "format:check": "prettier --check \"{src,tests,scripts}/**/*.{ts,tsx,js,mjs,json}\" \"*.{ts,js,json}\"",
-    "test": "vitest run",
+    "test": "vitest run --maxWorkers=2",
+    "soak:cache-lifecycle": "npm run build && vite-node scripts/cache-lifecycle-soak.ts",
     "test:watch": "vitest",
     "typecheck": "tsc --noEmit && tsc -p tests/fixtures/invocation-coverage-contract/tsconfig.json && tsc -p tests/fixtures/protocol-state-contract/tsconfig.json",
     "audit:prod": "node scripts/audit-production-dependencies.mjs",
     "api:report": "node scripts/api-surface-contract.mjs report",
     "api:check": "npm run build && node scripts/api-surface-contract.mjs check && tsc -p tests/fixtures/public-api-consumer/tsconfig.json",
     "api:update": "npm run build && node scripts/api-surface-contract.mjs update",
-    "lint": "npm run format:check && eslint src tests tsup.config.ts scripts/api-surface-contract.mjs scripts/audit-production-dependencies.mjs scripts/build-scip-windows.mjs scripts/npm-release-state.ts scripts/npm-release.ts scripts/publish-scip-windows.ts scripts/release-npm-guard.ts scripts/release-npm.ts scripts/scip-windows-package-identity.ts scripts/scip-windows-provenance.mjs scripts/scip-windows-release.ts scripts/verify-scip-windows.mjs scripts/verify-scip-windows-registry.ts && npm run api:check && node scripts/check-skill-links.mjs",
+    "lint": "npm run format:check && eslint src tests tsup.config.ts scripts/api-surface-contract.mjs scripts/audit-production-dependencies.mjs scripts/benchmark-cold-reindex.ts scripts/benchmark-graph-literal.ts scripts/benchmark-query-service.ts scripts/benchmark-reindex-accounting.ts scripts/benchmark-source-search.ts scripts/build-scip-windows.mjs scripts/cache-lifecycle-soak.ts scripts/codex-exploration-sandbox.mjs scripts/codex-exploration-trial-core.mjs scripts/codex-exploration-trial.mjs scripts/compare-exploration-trials.mjs scripts/exploration-benchmark-core.mjs scripts/exploration-benchmark.mjs scripts/npm-release-state.ts scripts/npm-release.ts scripts/publish-scip-windows.ts scripts/release-npm-guard.ts scripts/release-npm.ts scripts/scip-windows-package-identity.ts scripts/scip-windows-provenance.mjs scripts/scip-windows-release.ts scripts/verify-identity-collision-cli.mjs scripts/verify-scip-windows.mjs scripts/verify-scip-windows-registry.ts && npm run api:check && node scripts/check-skill-links.mjs",
     "build:scip-windows": "node scripts/build-scip-windows.mjs",
     "verify:scip-windows": "node scripts/verify-scip-windows.mjs",
+    "verify:identity-collision-cli": "node scripts/verify-identity-collision-cli.mjs",
     "verify:scip-windows-registry": "vite-node scripts/verify-scip-windows-registry.ts",
     "bench:evidence-products": "node scripts/evidence-product-contract.mjs",
+    "bench:exploration": "node scripts/exploration-benchmark.mjs",
+    "bench:exploration:codex": "node scripts/codex-exploration-trial.mjs",
+    "bench:exploration:compare": "node scripts/compare-exploration-trials.mjs",
+    "bench:cold-reindex": "vite-node scripts/benchmark-cold-reindex.ts",
+    "bench:edit-latency": "vite-node scripts/benchmark-edit-latency.ts",
+    "bench:graph-literal": "vite-node scripts/benchmark-graph-literal.ts",
+    "bench:query-service": "npm run build && vite-node scripts/benchmark-query-service.ts",
+    "bench:reindex-accounting": "vite-node scripts/benchmark-reindex-accounting.ts",
+    "bench:source-search": "vite-node scripts/benchmark-source-search.ts",
     "bench:native-symbol-leaf": "node scripts/bench-native-symbol-leaf.mjs",
+    "bench:agent-output": "npm run build -- --silent && vite-node scripts/benchmark-agent-output.ts",
     "calibrate": "node scripts/accuracy-calibration.mjs",
     "docs:commands": "vite-node scripts/render-command-reference.ts --write",
     "prepublishOnly": "vite-node scripts/release-npm-guard.ts",
@@ -363,6 +419,7 @@
   "dependencies": {
     "@bufbuild/protobuf": "^2.11.0",
     "@c4312/scip": "^0.1.0",
+    "@ts-morph/common": "^0.29.0",
     "@vue/compiler-dom": "^3.5.40",
     "@vue/compiler-sfc": "^3.5.40",
     "better-sqlite3": "^13.0.2",

package/skills/concrete-plan/SKILL.md

@@ -0,0 +1,8 @@
+---
+name: concrete-plan
+description: Compatibility alias for the canonical scip-plan skill. Use only when an existing prompt explicitly requests concrete-plan.
+---
+
+# Concrete Plan compatibility alias
+
+This name remains for a transition period so existing agent prompts do not fail. Apply `$scip-plan`; it contains the canonical command/question manual and code-grounded planning format. Do not combine the two skills.

package/skills/concrete-plan/agents/openai.yaml

@@ -0,0 +1,4 @@
+interface:
+  display_name: 'Concrete Plan (compatibility)'
+  short_description: 'Forward old planning prompts to SCIP Plan'
+  default_prompt: 'Use $scip-plan for this repository plan. $concrete-plan is only a compatibility alias.'

package/skills/scip-explore/SKILL.md

@@ -1,90 +1,8 @@
 ---
 name: scip-explore
-description: Use to understand a system before editing it: what calls what, how data flows, what depends on it, what a change would reach, and what historically changed together. Includes choosing high-signal commands for an unfamiliar language and rendering the result as a flow, dependency, or blast-radius diagram. For understanding a failure mode class rather than this codebase, use `engineering-lenses`.
-commands:
-  - template: "scip-query system <module-or-scope>"
-    when: "Orient to a module's files, symbols, dependencies, and consumers."
-  - template: "scip-query trace <entry-symbol>"
-    when: "Connect an entry symbol to its definition and references."
-  - template: "scip-query affected <symbol>"
-    when: "Measure the transitive downstream blast radius of a change."
+description: Compatibility alias for the canonical scip-query exploration skill. Use only when an existing prompt explicitly requests scip-explore.
 ---
 
-## Purpose
+# SCIP Explore compatibility alias
 
-Build verified understanding of how a system works end to end — entry points, call flow, data flow, dependencies, consumers, and risk — before answering or editing. Exploration means tracing code from entry points to effects against the SCIP index, not against memory or folder guesses. Load shared mechanics from `../_shared/SKILL.md`; use this skill's own shortlist first and open `_shared` only when it is insufficient.
-
-<!-- BEGIN GENERATED SKILL COMMANDS -->
-## Commands for this skill
-
-| Command | Purpose | Returns | Coverage | When |
-| --- | --- | --- | --- | --- |
-| `scip-query system <module-or-scope>` | Full module map: files, symbols, deps in/out | module file paths; exported symbols with line ranges; internal dependencies; reverse dependencies | `complete` | Orient to a module's files, symbols, dependencies, and consumers. |
-| `scip-query trace <entry-symbol>` | Trace a symbol: definition + all references | definition sites with source and signature; referencing files with line numbers | `bounded` | Connect an entry symbol to its definition and references. |
-| `scip-query affected <symbol>` | Transitive closure of symbols that could break if this symbol changes | affected symbol identities, files, and traversal depths | `bounded` | Measure the transitive downstream blast radius of a change. |
-
-Use this shortlist first. Open [`../_shared/SKILL.md`](../_shared/SKILL.md) only when it is insufficient.
-<!-- END GENERATED SKILL COMMANDS -->
-
-## Evidence rules (apply to every step below)
-
-- Use a current index before trusting graph facts: apply `_shared`'s freshness gate once before the first graph claim. After source changes, let an active watcher refresh and use manual reindex only as the documented fallback.
-- Relationship, consumer, and completeness claims must cite a `scip-query` command. Literal local-source claims may cite a native file read instead.
-- Resolve ambiguous symbols before describing behavior — `scip-query code` is the usual tool, but it isn't mandatory when you already have an exact native range.
-- Follow the graph before trusting folder structure. Start wide, then narrow.
-- Descriptions need citations; conclusions need discriminators. A conclusion — why something happens, what a unit is for, which intent explains a shape — must state one rival explanation and the trace evidence that ruled it out.
-
-Each `scip-query` command below carries a coverage rating: **complete** (exhaustive) or **bounded** (capped — a follow-up command may be needed to fill in the picture).
-
-## The core workflow
-
-Run these five steps in order. Skip a step only when its evidence is already in hand from an earlier step.
-
-**1. Orient.** Run `stats` (repo-wide size/shape, complete), `kind-counts`, `system <module-or-scope>` (file paths, exported symbols with line ranges, internal/reverse deps, complete), `outline <entry-file>`, and `by-kind function --scope <scope>`.
-Done when: module files, key symbols, dependencies, and reverse dependencies are mapped.
-
-**2. Trace entry points.** Run `trace <entry-symbol>` (definition + every reference, bounded), `call-graph <entry-symbol>` (incoming callers, outgoing callees, bounded), `code <entry-symbol>`, `dataflow <entry-symbol>` — repeat for important callees until the path reaches a side effect, a returned value, or a terminal output.
-Done when: the traced path connects entry point to observable effect.
-
-**3. Map dependencies and consumers.** Run `deps <file>`, `rdeps <file>`, `fan-out <file>`, `surface <module>`, `affected <symbol>` (transitive closure of symbols that could break if this symbol changes: identities, files, traversal depths, bounded).
-Done when: direct dependencies, public surface, and downstream blast radius are named.
-
-**4. Follow data and state.** Run `dataflow <symbol-or-variable>` (definition sites, usage sites, producers, consumers, bounded), `slice <symbol-or-variable>`, `slice <symbol-or-variable> --forward`.
-Done when: producers, transformations, storage, and consumers are identified — or explicitly marked unavailable.
-
-**5. Assess risk.** Run `complexity <symbol>`, `complexity-hotspots`, `bottlenecks`, `change-surface <file>` (pre-change briefing: exports, consumers, blast-radius risk), `cycles`, `deep-chains --min-depth 5` (longest condensed dependency-component chains — flags fragile long call paths).
-Done when: the explanation names the risky symbols, or states that no relevant risks appeared.
-
-## Route by question type
-
-| Question | Commands |
-|---|---|
-| Function behavior | `code`, `hierarchy`, `call-graph`, `dataflow`, `complexity` |
-| User-action flow | `files` or `outline` to find the handler, then `code` and `call-graph` down the path |
-| Safe to change? | `change-surface`, `affected`, `similar` |
-| Module architecture | `system`, `surface`, `deep-chains`, `bottlenecks`, `cycles`, `hotspots` (`hotspots` lists the most-referenced symbols — choke points where any change ripples widely) |
-| Relationship between two units | `coupling`, `similar --plan`, `similar-chains` |
-
-## Other owned commands
-
-These four don't have a dedicated workflow step above but come up constantly once you're inside a module — use them as needed, not in sequence:
-
-- **`imported-by <symbol>`** — which files import this symbol. Run before changing or removing a shared export, to know exactly which files to check. If the list is empty, confirm with `dead` before deleting rather than trusting the empty result alone.
-- **`unused-imports <file>`** — imports not referenced in that same file. Run on a file you're about to touch, or one a de-bloat pass flagged; remove only entries you've confirmed are safe.
-- **`similar-signatures`** — functions with near-identical type signatures. Run when hunting duplicate-shaped functions to consolidate. This is a *good-with-review* signal — check each match with `code` before merging, don't act on the list alone.
-- **`co-change [file]`** — files that change together in git history with no dependency edge between them: hidden coupling. Run when `change-surface` or `affected` reports a small blast radius but you suspect the graph is missing something. This is also *good-with-review* — a paired file is a prompt to check manually, not proof the current change must touch it too. (`diff-gate`'s `co-change-partner` check is the automated version of this same signal.)
-
-## Report the exploration
-
-Cover: overview, entry points, call flow, data flow, dependencies, consumers, risk areas, and the command citation that proves each claim. For every conclusion-bearing claim, name the rival explanation you considered and the evidence that ruled it out. Exploration is complete only when the reader can see what was proven, what remains unverified, and which conclusions rest on a discriminator rather than a single story.
-
-## Deeper references
-
-| Need | Reference |
-|---|---|
-| Entering an unfamiliar language (TypeScript, Python, Java, Scala, Kotlin, Rust, Go, C, C++, Ruby, C#, Visual Basic, Dart, PHP, Clojure/ClojureScript, Vue) and picking the highest-signal commands, including de-bloat sets | `references/language-playbook.md` |
-| Turning exploration evidence into an HTML flow, dependency, data-flow, or blast-radius diagram | `references/diagrams.md` |
-
-## Constraint
-
-scip-explore's OpenAI-agent interface binds to display name "SCIP Explore" with default prompt "Use $scip-explore to understand this system end to end with SCIP-backed code evidence."
+This name remains for a transition period so existing agent prompts do not fail. Apply `$scip-query`; it contains the canonical command/question manual, typed-relationship controls, source-reading controls, and coverage semantics. Do not combine the two skills or treat this alias as a separate exploration phase.

package/skills/scip-explore/agents/openai.yaml

@@ -1,4 +1,4 @@
 interface:
-  display_name: "SCIP Explore"
-  short_description: "Understand a system with SCIP evidence"
-  default_prompt: "Use $scip-explore to understand this system end to end with SCIP-backed code evidence before editing it."
+  display_name: 'SCIP Explore (compatibility)'
+  short_description: 'Forward old exploration prompts to SCIP Query'
+  default_prompt: 'Use $scip-query for this repository exploration. $scip-explore is only a compatibility alias.'

package/skills/scip-integrity-audit/SKILL.md

@@ -0,0 +1,185 @@
+---
+name: scip-integrity-audit
+description: Audit whether implementations are real with scip-query. Use for suspected faked or half-implemented features, decorative checkers or verifiers that never fail, dead code paths hidden behind graceful fallbacks, metrics that may be lying, or a "does any of this actually work" interrogation of a system.
+metadata:
+  commands:
+    - template: 'scip-query search <text>'
+      when: 'Locate a status word, checker name, adapter, fallback, or metric producer.'
+    - template: 'scip-query outline <file>'
+      when: 'Inventory the callables in a known file before choosing a drill target.'
+    - template: 'scip-query evidence --symbol <symbol> --edge <family> --direction <direction> --depth <n> --max-edges <n>'
+      when: 'Project callers, callees, or dataflow around a checker, adapter, fallback, or metric.'
+    - template: 'scip-query inspect --at <file:line> --view behavior'
+      when: 'Read connected behavior for a named remaining gap after graph evidence.'
+    - template: 'scip-query code <selector>'
+      when: 'Read exact implementation syntax only when the body itself can change the verdict.'
+    - template: 'scip-query decorative-checkers -s <scope> --json'
+      when: 'Shortlist validate/verify/check/assert/is/has callables with no reachable failure exit.'
+    - template: 'scip-query not-implemented -s <scope> --json'
+      when: 'Shortlist reachable placeholder stubs that a real caller can actually reach.'
+    - template: 'scip-query test-quality -s <scope> --json'
+      when: 'Check regression artifacts and tests for assertion-free bodies, skip rot, and mock-echo.'
+    - template: 'scip-query twin-drift -s <scope> --json'
+      when: 'Find same-name or near-name twins whose bodies have silently diverged.'
+    - template: 'scip-query twin-ab <symbolA> <symbolB>'
+      when: 'Scaffold a table-driven comparison of two same-concept twins on a shared input.'
+---
+
+# scip-integrity-audit
+
+<!-- BEGIN GENERATED SKILL COMMANDS -->
+## Command and question manual
+
+| Command syntax | Question it answers |
+| --- | --- |
+| `scip-query search <text>` | Locate a status word, checker name, adapter, fallback, or metric producer. |
+| `scip-query outline <file>` | Inventory the callables in a known file before choosing a drill target. |
+| `scip-query evidence --symbol <symbol> --edge <family> --direction <direction> --depth <n> --max-edges <n>` | Project callers, callees, or dataflow around a checker, adapter, fallback, or metric. |
+| `scip-query inspect --at <file:line> --view behavior` | Read connected behavior for a named remaining gap after graph evidence. |
+| `scip-query code <selector>` | Read exact implementation syntax only when the body itself can change the verdict. |
+| `scip-query decorative-checkers -s <scope> --json` | Shortlist validate/verify/check/assert/is/has callables with no reachable failure exit. |
+| `scip-query not-implemented -s <scope> --json` | Shortlist reachable placeholder stubs that a real caller can actually reach. |
+| `scip-query test-quality -s <scope> --json` | Check regression artifacts and tests for assertion-free bodies, skip rot, and mock-echo. |
+| `scip-query twin-drift -s <scope> --json` | Find same-name or near-name twins whose bodies have silently diverged. |
+| `scip-query twin-ab <symbolA> <symbolB>` | Scaffold a table-driven comparison of two same-concept twins on a shared input. |
+
+These commands are controls, not a checklist. Use every capability needed by the task, but make each query answer a distinct question. There is no required sequence or query limit. Run a command's `--help` when you need a flag not shown in its template.
+<!-- END GENERATED SKILL COMMANDS -->
+
+Use this skill to interrogate whether a system's claims are backed by real
+implementations. Structural review asks "is this well organized?"; this skill
+asks **"is this real?"** — it hunts decorative checkers, adapters written
+against imagined data, features that have silently never run, and numbers
+nobody ever recomputed.
+
+Use `$scip-query` locators and evidence projections to inventory producers.
+`health --full` does not run the integrity detectors; call
+`decorative-checkers`, `not-implemented`, `test-quality`, and `twin-drift`
+directly.
+
+## The Stance
+
+A green result you have never seen fail is unverified. Every status word,
+banner, and metric is testimony from the code, not evidence about the code —
+cross-examine the producer before believing it. The most dangerous code is
+not broken code; it is code that reports success without doing the work.
+
+## Drills
+
+Run all five over the chosen scope. Each has a checkable exit.
+
+### 1. Falsify every checker
+
+Inventory everything in scope that accepts/rejects, passes/fails, or
+validates (checkers, gates, verifiers, validators — find producers with
+`search` on the status words in output, then `evidence` execution incoming
+and outgoing). For each one, construct an input that MUST fail — a wrong
+binding, a corrupt file, an impossible value — and run it. A checker that
+passes its should-fail input is decorative: file it as a defect, not a note.
+Before filing, attempt the defense: an accusation triggers a rewrite, so
+search for the failure exit the drill may have missed — a config-gated
+branch, an async rejection, one-hop delegation (the calibration's known
+noise archetypes). File the defect with the executed should-fail input
+attached and the defense attempt noted; a defense that succeeds clears the
+checker and stays in the record as its witness.
+Complete only when every checker in scope has been witnessed rejecting a
+constructed should-fail input, or is listed with a reason it cannot be.
+
+Mechanized by: `scip-query decorative-checkers` finds `validate*`/`verify*`/
+`check*`/`assert*`/`is*`/`has*` callables with no reachable failure exit
+anywhere in their body (calibrated 2026-07-03 against two external repos —
+standalone-only; noise archetypes past one-hop delegation in
+`docs/validation/2026-07-03-integrity-detector-calibration.md`). Run it first
+to shortlist candidates before hand-constructing should-fail inputs.
+
+### 2. Diff every adapter against captured reality
+
+For each parser/adapter of an external format (tool output, XML/JSON
+schemas, protocol messages): obtain ONE real sample from the actual source
+and diff it against the code's assumptions and the tests' fixtures. Ask of
+every fixture: was this generated from reality, or imagined? A parser and a
+hand-written fixture can validate each other's shared hallucination
+indefinitely.
+Complete only when every adapter has been checked against at least one
+captured-real sample.
+
+### 3. Autopsy every fallback
+
+Graceful degradation is where dead features hide: a primary path that has
+never worked looks identical to a healthy fallback. For every catch block,
+`?? fallback`, and degraded mode in scope: produce an execution witness that
+the PRIMARY path runs (a test, a probe, a log). Use `evidence` execution and
+`inspect --view behavior` for branch reachability. A fallback that always
+fires means the feature above it is dead — date of death: birth.
+Complete only when every fallback's primary path has a witness or a filed
+defect.
+
+Mechanized by: `scip-query not-implemented` finds reachable placeholder
+stubs (`throw new Error('not implemented')`, TODO-comment + return-default,
+empty bodies) that a real caller, entry surface, or package-surface export
+can actually reach — the graph fact that separates "primary path never
+built" from `dead`'s "primary path built but unreferenced." Standalone-only
+(calibrated 2026-07-03; 0 live findings on two external repos post-fix, see
+the calibration report) — treat a clean run as "nothing this shape found,"
+not as "every fallback's primary path is proven live."
+
+### 4. Hand-compute every metric twice
+
+For each number the system reports (scores, counts, estimates): pick two
+concrete instances, compute the expected value by hand from first
+principles, and compare. Off-by-a-factor errors (double counting, inflated
+estimates) survive for years because nobody ever recomputes one sample.
+Complete only when every reported metric has two hand-verified samples.
+
+### 5. Cross-examine same-concept twins
+
+Where one concept is computed in more than one place, feed both the same
+input and require the same answer. `twin-drift` finds the same-name cases
+mechanically; for same-concept-different-name pairs, project consumers with
+`evidence` execution incoming and compare implementations with `code`. Once
+a pair is identified, `scip-query twin-ab <symbolA> <symbolB>` scaffolds a
+table-driven vitest file that imports both and asserts equal output —
+fill in the input table and run it. Disagreement between twins means at
+least one is wrong — determine which before consolidating.
+Complete only when every discovered twin pair has been compared on a shared
+input.
+
+## Severity
+
+Rank findings by what the failure does to a user who trusted the output:
+a decorative checker or false "verified" banner outranks everything; a
+dead-but-fallbacked feature outranks a wrong metric; a wrong metric outranks
+structural mess. Structural findings are real, but they are not lies — do
+not fold them into the integrity verdict.
+
+## Reporting
+
+File each finding with: the claim as displayed, the producer (file:line),
+the drill that exposed it, the should-fail input or real sample used, and
+the fix. The audit is complete only when every drill's exit criterion is
+met for the scope, and every defect found has a regression artifact — a
+test, fixture, or model that fails on the pre-fix behavior.
+
+End with a derived verdict, not an impression:
+
+```markdown
+Integrity: <scope> — <c> checkers witnessed failing, <a> adapters diffed
+against reality, <f> fallback primaries witnessed live, <m> metrics
+recomputed, <t> twins compared; <d> defects filed, <u> unverifiable (reasons)
+```
+
+A suspect scope that produces zero defects is itself a claim: state what
+made the suspicion wrong, or rerun the drill that should have caught it.
+
+A regression artifact that doesn't actually assert anything, or asserts the
+same literal it stubbed into its own mock, is a fake witness — the same
+"reports success without doing the work" failure mode this skill hunts in
+production code, just relocated to the test suite. Run `scip-query
+test-quality -s <scope>` over the audit's own regression artifacts (and,
+periodically, over the suite at large) to catch this: assertion-free test
+bodies, a skipped-test ledger with git-blame age (a skip with no fix date
+attached is a claim nobody is checking), and mock-echo (a test that only
+proves its own stub). Standalone-only, mixed precision by sub-check
+(calibrated 2026-07-03): assertion-free and skipped are high-precision;
+mock-echo is intentionally low-precision (syntactic same-literal matching,
+not dataflow) — treat its output as a reviewed candidate list, not a verdict.

package/skills/scip-integrity-audit/agents/openai.yaml

@@ -0,0 +1,4 @@
+interface:
+  display_name: 'scip integrity audit'
+  short_description: 'Interrogate whether implementations are real: falsify checkers, diff adapters against reality, autopsy fallbacks.'
+  default_prompt: 'Run the scip-integrity-audit drills over this codebase and report every decorative checker, dead-behind-fallback feature, and lying metric.'