polish: six fixes from skill-migration reviews

Three minor-issues + three optional follow-ups identified by
the three parallel reviewers of debug/docwriter/audit,
fieldtest/planner/brainstorm, and implement. None blocking;
all close calibrated gaps the bulk migration left.

Minor-issues:
- audit/SKILL.md: handoff field `regression_results` now
  explicitly carries "raw output verbatim (no rounding, no
  summarisation)" — restores the verbatim-numbers emphasis
  the original `bench_numbers` field name implied.
- audit/agents/bencher.md: hypothesis examples grouped by
  axis (Tail-latency / Count reduction / Scalability /
  Overhead vs floor) with concrete numerical anchors (2× of
  median, ≥80%, 10-million-element, ±15%). Subjects stay
  domain-neutral but the calibrated bite returns. The
  preamble enumerates plausible subjects (allocators, query
  plans, request handlers, parsing strategies, codecs,
  caches) so the reader has concrete domains to anchor on.
- implement/agents/implementer.md: "Architecture rules"
  section gains a 5-bullet kind-list (determinism contracts;
  backend / FFI constraints; schema versions; memory /
  resource models; effect / capability discipline) so the
  implementer has scaffolding to look for even when the
  project's CLAUDE.md is sparse. The "BLOCKED on
  contradiction" mechanism stays the load-bearing rule.

Optional follow-ups:
- brainstorm/SKILL.md Step 7.5: failure-mode procedure
  restores the structured backlog-issue fields (Title /
  Label / Body with `depends on:` and `context:` lines)
  and the milestone-container option for big deferred work
  (Gitea milestones, GitHub milestones, Linear projects).
- templates/CLAUDE.md.fragment: adds an optional
  "Lockstep-invariant pairs" section so projects that have
  cross-file pairings can declare them in a way the
  architect agent and plan-recon agent already know to
  consult. Projects without such pairings omit the section;
  both agents handle absence gracefully.

No discipline regressions; no Iron Law / Common Rationalisations
/ Red Flags edits. Pure scaffold-and-anchor improvements.

audit/SKILL.md

@@ -116,7 +116,7 @@ The orchestrator picks per item:
 | Field | Content |
 |-------|---------|
 | `drift_items` | prioritised list (path + 1-line justification) from architect |
-| `regression_results` | per script: exit code + raw output |
+| `regression_results` | per script: exit code + **raw output verbatim** (no rounding, no summarisation — the orchestrator second-guesses with the full numbers) |
 | `recommendation` | per-item: `fix` / `ratify` / `carry-on` |
 
 The orchestrator decides the per-item outcome; `audit` does

audit/agents/bencher.md

@@ -68,19 +68,25 @@ NO POLICY VERDICTS. THE ORCHESTRATOR DECIDES; YOU SUPPLY EVIDENCE.
 ## Standard methodology
 
 Every measurement starts with a hypothesis stated as a
-falsifiable claim, not a vague comparison. Examples (the
-specific subject varies per project):
+falsifiable claim, not a vague comparison. The subject
+varies per project (allocator variants, query plans,
+request handlers, parsing strategies, codec implementations,
+cache layers, …); the *shape* of a useful hypothesis does
+not:
 
-- "Variant A's p99 per-operation latency is within 2× of
-  median under continuous pressure with a >100 MB working
-  set."
-- "Optimisation X reduces total resource consumption by ≥80%
-  on the canonical fixture vs the same fixture without it."
-- "Variant A allows running the long-form workload without
-  resource exhaustion; the unoptimised variant exhausts
-  before completion."
-- "Variant A's overhead vs the raw-cost floor on the canonical
-  fixture is within ±15% of the recorded baseline."
+- **Tail-latency under pressure:** "Subject A's p99
+  per-operation latency is within 2× of its median under
+  continuous pressure with a >100 MB working set."
+- **Count / volume reduction:** "Optimisation X reduces
+  total resource consumption by ≥80% on a workload that
+  exercises the optimised code path vs the same workload
+  bypassing it."
+- **Scalability ceiling:** "Subject A successfully
+  processes a 10-million-element workload without resource
+  exhaustion; the unoptimised variant fails below 1 million."
+- **Overhead vs floor:** "Subject A's overhead vs the
+  raw-cost floor on the canonical fixture is within ±15% of
+  the recorded baseline."
 
 Then design the workload to *exercise* the claim. Specifically: