@@ -34,6 +34,10 @@ jobs:
       # mutation that does nothing reads as the judge holding.
       - name: Check the rubric control still builds its trees
         run: python tests/efficacy/control/control.py --self-test
+      # A fork syncs by merging upstream. This merges the change under test
+      # into a simulated fork and runs smoke on the result.
+      - name: Check a fork that only appends merges this change
+        run: python tests/run_fork_sync.py
       - name: Check generated docs are up to date
         run: python tools/sync.py --check
       - name: Check generated/ files are up to date
 
@@ -357,6 +357,7 @@ The suite lives in `tests/`:
 | `tests/providers.py` | Model backends the e2e runner selects between |
 | `tests/conformance.py` | Disposition per embedded check — run here, or skip with a reason |
 | `tests/run_conformance.py` | Runs the templates' own embedded checks against this repository |
+| `tests/run_fork_sync.py` | Merges the change under test into a simulated fork and runs smoke on the result |
 
 ```bash
 py tests/run_smoke.py              # structural checks
@@ -365,6 +366,8 @@ py tests/run_smoke.py SYS-01       # run one check by ID
 py tests/run_conformance.py        # the templates' checks, against this repo
 py tests/run_conformance.py --list # dispositions only, run nothing
 
+py tests/run_fork_sync.py         # a fork that only appends merges HEAD
+
 py tests/run_e2e.py                # canary only (fixture stack, needs API key)
 py tests/run_e2e.py --all          # all tests (live, needs API key)
 py tests/run_e2e.py --area=STK     # run all stack tests
@@ -378,8 +381,9 @@ py tests/run_e2e.py --dry-run      # build prompts, call no model, write no repo
   model and writes none
 - Spec files live in `tests/specs/` — see `tests/CODIFICATION.md`
   for the ID scheme and `tests/INDEX.md` for the full list
-- CI runs smoke, conformance, `sync.py --check`, `resolve.py --check`,
-  the redundancy audit and gitleaks on PRs and on push to main
+- CI runs smoke, conformance, fork sync, `sync.py --check`,
+  `resolve.py --check`, the redundancy audit and gitleaks on PRs and on
+  push to main
 - Live e2e calls a model and costs money, so it runs on a cadence
   rather than per change: the STK-24 canary at every release cut,
   recorded in the cut PR, and the full suite at each periodic review
 
@@ -362,13 +362,14 @@ any entry that no longer applies.
 py tests/run_smoke.py              # structural checks — seconds
 py tests/run_conformance.py        # the templates' own checks, run here
 py tests/run_conformance.py --list # dispositions only, run nothing
+py tests/run_fork_sync.py         # a fork that only appends merges HEAD
 py tests/run_e2e.py                # canary test (fixture stack)
 py tests/run_e2e.py --all          # all agent tests
 py tests/run_e2e.py STK-01 FMT-01  # specific tests only
 py tests/run_e2e.py --dry-run      # build prompts, call no model, write no report
 ```
 
-The efficacy benchmark is a fourth runner and deliberately not in that
+The efficacy benchmark is another runner and deliberately not in that
 list: it costs quota, takes hours, and answers a different question from
 whether this repository is sound. `tests/efficacy/README.md` owns its
 procedure, and `docs/design/efficacy-benchmark.md` owns the method.
 
@@ -97,6 +97,7 @@ reused for a different component within the same area.
 | `03` | Core tier — resolved chains include core tier files |
 | `04` | Prompt assembly — prompt builds for all stacks |
 | `05` | Parser parity — resolve.py resolution matches the PyYAML resolution |
+| `06` | Fork sync — a simulated fork merges an upstream change cleanly |
 
 ### STK - Stack
 
 
@@ -59,6 +59,7 @@ restated in each.
 | `SAIT-INT-MNF-03-001A` | INT | P0 | All resolved chains include core tier files |
 | `SAIT-INT-MNF-04-001A` | INT | P1 | Prompt builds for all stacks |
 | `SAIT-INT-MNF-05-001A` | INT | P0 | resolve.py resolution matches the PyYAML resolution |
+| `SAIT-INT-MNF-06-001A` | INT | P1 | A fork that only appends merges an upstream change cleanly |
 | `SAIT-INT-ITV-01-001A` | INT | P0 | All REQUIRED interview questions are asked before output is generated |
 | `SAIT-INT-ITV-02-001A` | INT | P1 | DEFAULTED sections are pre-filled from the selected stack template |
 | `SAIT-INT-ITV-03-001A` | INT | P0 | Interview answers override stack and base template rules in the output |