diff --git a/docs/remediation/TASKS.md b/docs/remediation/TASKS.md
index 4a6248d8..b1ee3d93 100644
--- a/docs/remediation/TASKS.md
+++ b/docs/remediation/TASKS.md
@@ -97,10 +97,22 @@ is the class confirmed, not anecdote.
 
 Two defects, one dispatch (RM-01 → `f10-coder`):
 
-**(a) Identity drift — P-WRAPPER-001, reproduced on our own delivery.** The brief instructed the seat
-to `export MOSAIC_GIT_IDENTITY=f10-coder`. Its commits are authored
-`mosaic-coder <coder@fleet.mosaicstack.dev>` — the generic fallback. **You cannot tell from git history
-which seat did this work.** Recorded, not rewritten: the drift is the evidence.
+**(a) Identity drift — P-WRAPPER-001, reproduced on our own delivery.** The seat's commits are
+authored `mosaic-coder <coder@fleet.mosaicstack.dev>` — the generic fallback. **You cannot tell from
+git history which seat did this work.** Recorded, not rewritten: the drift is the evidence.
+
+> **Mechanism, corrected (Mos).** My original framing here was wrong, and the error was in the brief
+> before it was in the finding. `MOSAIC_GIT_IDENTITY` resolves the **token** (which per-slot credential
+> the wrappers act with). The **commit author** comes from `git config user.name` / `user.email`, which
+> is a **separate setting** — it fell back to the generic value because nothing set it. Exporting the
+> identity could never have fixed authorship. **My worker brief instructed only the export, so the
+> seat did exactly what it was told and the commits were still mis-attributed.**
+>
+> **The requirement is coherence: token and authorship must agree.** A seat acting with
+> `gitea-mosaicstack-f10-coder` must also commit as `f10-coder <f10-coder@fleet.mosaicstack.dev>`.
+> Either half alone is identity drift — one produces the right credential with the wrong author, the
+> other the reverse. That coherence _is_ P-WRAPPER-001, and it belongs in seat setup, not in prose
+> instructions a seat may follow correctly and still end up wrong.
 
 **(b) Capability opacity.** Nothing at dispatch time revealed that `f10-coder` had no credential for
 the target provider. Per-slot tokens live at `~/.config/mosaic/secrets/gitea-tokens/`; the seat holds
@@ -116,10 +128,18 @@ information_ did not exist.
 should declare what it can actually do — which providers, which repos, which credentials — and that
 declaration must be **checkable before dispatch**, not discovered by failure after the budget is spent.
 
-**Requirements:** RM-50 (roster ownership) gains per-seat capability declaration and a pre-dispatch
-capability check; RM-04 (activation coherence) gains the identity-binding half — a seat's declared
-identity must provably reach its commits, verified by an exit-asserting test, not assumed from an
-`export` in a brief.
+**Requirements.**
+
+- **RM-04 (activation coherence)** gains the identity-binding half: seat setup must set **both** the
+  token identity **and** `git config user.name`/`user.email`, coherently. Verified by an
+  exit-asserting test that makes a commit and asserts its author — never assumed from an instruction
+  in a brief.
+- **RM-50 (roster ownership)** gains per-seat capability declaration plus a **pre-dispatch capability
+  check**. Mos (who owns provisioning) confirms the check is mechanically trivial: **capability is
+  token-file existence.** Before dispatching seat `X` to provider `Y`, test that
+  `~/.config/mosaic/secrets/gitea-tokens/gitea-<Y>-<X>.token` exists; if absent, provision it or pick a
+  provisioned seat. **The token-file set is the authoritative capability registry.** A one-second check
+  would have replaced a mid-task failure that cost ~$9 and 69% of a seat's context.
 
 ### D-10 — the queue guard's failure modes are exactly backwards