chore: relax agent rules and planning skills (no diff/test count pressure)

.cursor/rules/agent-workflow.mdc

@@ -48,15 +48,16 @@ When you're given a per-PR task prompt from `plans/CURSOR-PROMPTS-*.md`:
 - **Implement in the listed order.** Do not reshape the PR or roll
   multiple PRs together.
 - **Match named tests verbatim.** When the plan §4 table lists
-  `test_<scenario>_<expected>`, that is the exact name to use. Test
-  count must match the prompt's claim.
+  `test_<scenario>_<expected>`, that is the exact name to use. If you
+  add, drop, or rename tests, update the plan/prompt text in the same
+  change so reviewers are not chasing a stale list.
 - **No drive-by lint fixes.** Removing an unused `import` in a file
   the PR doesn't otherwise touch is still a scope leak. If a file
   isn't in the deliverables list, don't touch it.
 - **PR description must include**: scope statement, manual evidence
-  (with the exact command from the prompt), test count, and any
-  intentional design divergences from sibling PRs called out
-  explicitly so the reviewer doesn't flag them as bugs.
+  (with the exact command from the prompt), and any intentional design
+  divergences from sibling PRs called out explicitly so the reviewer
+  doesn't flag them as bugs.
 
 ## Editing rules
 

.cursor/skills/plan-project-scope/SKILL.md

@@ -41,7 +41,8 @@ Strong plans in this repo consistently include:
 - upfront **Status** and dependency context (`Depends on`, if applicable)
 - a clear **Goal** section with concrete expected outcomes
 - explicit **Principles (do not relitigate in review)** to freeze key decisions
-- a **PR breakdown overview table** (scope, ontology bump, files, tests, dependency order)
+- a **PR breakdown overview table** (scope, ontology bump, areas of concern, tests, dependency order)
+- **Areas of concern column:** short **risk/review lens** (what to double-check or where coupling is likely). **Not** a module allowlist, **not** exhaustive, and **not** a substitute for the per-PR **File-by-file changes** section (that section remains the touch-scope contract)
 - per-PR sections with:
   - file-by-file changes
   - named tests (verbatim test function names where possible)
@@ -72,7 +73,7 @@ Depends on: <dependency or "none">.
 - <principle 2>
 
 ## PR breakdown - overview
-| PR | Scope | Ontology bump | Files touched (approx) | Test buckets | Independent of |
+| PR | Scope | Ontology bump | Areas of concern | Test buckets | Independent of |
 | --- | --- | --- | --- | --- | --- |
 | PR-X1 | ... | ... | ... | ... | ... |
 
@@ -128,6 +129,7 @@ Landing order: **X1 -> X2 -> X3**.
 - Name tests exactly when feasible; avoid vague "add tests".
 - Call out ontology bump and re-index impact for schema/enrichment changes.
 - Keep "Out of scope" strict; use it to prevent scope creep during implementation.
+- Treat **Areas of concern** as **heads-up text for reviewers** (coupling, regression risk, semantic hotspots). Do **not** phrase it as “only these modules” — honest implementation may touch adjacent files; when that happens, update the **File-by-file changes** list and **Out of scope** so the contract stays clear.
 - Do not add compatibility shims unless explicitly requested.
 
 ## Per-PR execution prompt option
@@ -139,7 +141,7 @@ Each PR prompt should include:
 - branch/base
 - in-scope deliverables
 - out-of-scope guardrails
-- explicit test count/commands
+- pytest commands and evidence expectations (avoid hard totals that go stale)
 - definition of done and PR title convention
 
 Use `plans/completed/CURSOR-PROMPTS-TIER1B.md` as the structural reference.

.cursor/skills/plan-project-scope/examples.md

@@ -15,15 +15,17 @@ as a multi-PR sequence. This file is plan-only and does not implement code.
 ```markdown
 ## PR breakdown - overview
 
-| PR | Scope | Ontology bump | Files touched (approx) | Test buckets | Independent of |
+| PR | Scope | Ontology bump | Areas of concern | Test buckets | Independent of |
 | --- | --- | --- | --- | --- | --- |
-| PR-X1 | schema + extraction | 9 -> 10 | 4-5 | extraction + schema | prerequisite only |
-| PR-X2 | matcher integration | none | 2-3 | regression + continuity | PR-X1 |
-| PR-X3 | MCP tool + docs | none | 3-4 | tool filters + docs | PR-X1 |
+| PR-X1 | schema + extraction | 9 -> 10 | graph DDL vs writer drift; extraction edge cases | extraction + schema | prerequisite only |
+| PR-X2 | matcher integration | none | ambiguous matches; query-layer churn | regression + continuity | PR-X1 |
+| PR-X3 | MCP tool + docs | none | tool contract vs docs drift; operator confusion | tool filters + docs | PR-X1 |
 
 Landing order: **X1 -> X2 -> X3**.
 ```
 
+The **Areas of concern** cells are **review hints** (risks, coupling), not a filename allowlist and not the authority on what may be edited — use the per-PR **File-by-file changes** section for that.
+
 ## 3) Per-PR section skeleton
 
 ```markdown

.cursor/skills/plan-prompts/SKILL.md

@@ -22,7 +22,7 @@ Do not use this skill if there is no plan yet. Write/update the plan first.
 Before writing prompts, confirm:
 1. Source plan file path (for example `plans/PLAN-XYZ.md`).
 2. PR list and landing order from the plan.
-3. Any fixed constraints (test count expectations, files not to touch, branch naming).
+3. Any fixed constraints (branch naming, files or areas not to touch).
 
 If already present in the plan, do not ask again.
 
@@ -41,7 +41,7 @@ Write one file:
 Include:
 - status line
 - one section per PR in plan landing order
-- `Branch`, `Base`, `Plan section`, estimated diff size
+- `Branch`, `Base`, `Plan section`
 - `@-files` list for context attachment
 - copy-paste `Prompt` block with strict scope contract
 
@@ -52,7 +52,7 @@ Each PR prompt must include all of:
 - **Out of scope (do NOT touch)** list mirroring plan boundaries
 - **Deliverables** numbered and testable
 - **`## Tests to run (iteration loop)`** — pytest **file** subset for fast local iteration (see below); must appear **after Deliverables and before the full Tests section**
-- **Tests** command and expected result format for the full or plan-required run (counts only if known)
+- **Tests** command and expected signals (pass/fail, skips, fixtures); avoid hard totals that go stale across branches
 - **Sentinel checks** (`rg` patterns) where scope enforcement is critical
 - **Manual evidence** commands when plan requires runtime proof
 - **Definition of Done** checklist with PR title + branch convention
@@ -84,7 +84,6 @@ This heading must stay verbatim so reviewers (and the repo **`pr-review`** skill
 **Branch:** `feat/<topic>` off `<base>`.
 **Base:** `<base branch or predecessor PR branch>`.
 **Plan section:** `plans/PLAN-<TOPIC>.md` § <section>.
-**Estimated diff size:** ~<n> files, ~<m> LOC.
 
 **Attach (`@-files`):**
 - `@plans/PLAN-<TOPIC>.md`
@@ -118,7 +117,7 @@ Docs-only PRs (UC15): use a single bullet such as *(none — docs-only change; f
 
 ## Tests
 Run: `<command>`
-Expected: <result format / count if known>
+Expected: <pass/fail, skips, key fixtures — not a brittle total count>
 
 ## Sentinel checks
 - `<rg command>`

.cursor/skills/plan-prompts/examples.md

@@ -16,7 +16,6 @@ Status: **active**. One prompt per PR; each prompt is self-contained.
 **Branch:** `feat/topic-x1` off `master`.
 **Base:** `master`.
 **Plan section:** `plans/PLAN-TOPIC.md` § PR-X1.
-**Estimated diff size:** ~4 files, ~300 LOC.
 
 **Attach (`@-files`):**
 - `@plans/PLAN-TOPIC.md`

.cursor/skills/plan-prompts/reference.md

@@ -5,7 +5,7 @@ Use this when converting `PLAN-*` into `CURSOR-PROMPTS-*`.
 ## Core quality bar
 
 1. Prompt is self-contained and executable by another agent.
-2. Scope is locked to one PR section only.
+2. Scope stays within one PR section only.
 3. Out-of-scope is explicit and enforceable.
 4. Deliverables are concrete and numbered.
 5. **Iteration subset** (`## Tests to run (iteration loop)`) lists `tests/test_*.py` bullets with one-line rationales (or UC15 docs-only line) between Deliverables and Tests.

AGENTS.md

@@ -126,10 +126,11 @@ template):
 - Treat the prompt's **Out of scope** list as binding. Sentinel grep
   patterns in the prompt must return zero on `git diff master..HEAD`.
 - Implement deliverables in the listed order; don't reshape the PR.
-- Match the prompt's expected test count and named tests verbatim.
-- PR description must include: scope statement, manual evidence
-  (with the exact command from the prompt), test count, and
-  intentional design divergences flagged.
+- Match named tests verbatim when the prompt lists `test_*` names; if
+  the test set changes, update the prompt/plan text in the same change.
+- PR description must include: scope statement, manual evidence (with
+  the exact command from the prompt), and intentional design
+  divergences flagged.
 - No drive-by lint fixes (unused imports, formatting nits in
   unrelated files). They violate the per-PR scope contract even when
   they look harmless.