Split AGENTS.md into a router, and prove the scripts/ gates

.editorconfig

@@ -69,6 +69,11 @@ end_of_line = lf
 [host-setup/agent-safety/*.py]
 end_of_line = lf
 
+# The repo lint/review scripts are shebang-executable tooling run by path, so a CRLF shebang would
+# break direct execution on a Unix host. Pinned in .gitattributes to match.
+[scripts/*.py]
+end_of_line = lf
+
 # uv regenerates uv.lock with LF on every platform, so pin it or an EOL check (editorconfig-checker/CI)
 # reds on every `uv lock`/`uv sync` until the file is manually reconverted - same rationale as the
 # shebang/Dockerfile pins (a tool owns the ending). A Python repo on the CRLF default carries this; a repo

.gitattributes

@@ -15,13 +15,19 @@ catalog/snippets/husky/pre-commit text eol=lf
 
 # Vanilla `.py` follows the CRLF default - Python's universal newlines accept CRLF, and it is
 # commonly edited on Windows. Pin LF only for a `.py` executed directly via its shebang, by path -
-# here the CI validation entry point, the fleet-audit runner, and the agent-safety hook and its
-# installer. Do not re-add a blanket `*.py text eol=lf`.
+# here the CI validation entry point, the fleet-audit runner, the agent-safety hook and its
+# installer, and the repo lint/review scripts with their tests. Do not re-add a blanket
+# `*.py text eol=lf`.
 spec/validate.py text eol=lf
 spec/audit.py text eol=lf
 spec/fidelity_honesty.py text eol=lf
 host-setup/agent-safety/gh-write-guard.py text eol=lf
 host-setup/agent-safety/install.py text eol=lf
+scripts/prose_lint.py text eol=lf
+scripts/repo_gate.py text eol=lf
+scripts/pr_review.py text eol=lf
+scripts/test_prose_lint.py text eol=lf
+scripts/test_repo_gate.py text eol=lf
 
 # uv regenerates uv.lock with LF on every platform; pin it so git enforces LF on checkout/renormalize and a
 # CRLF-default repo does not fight the tool on every `uv lock`/`uv sync`. A repo with no lockfile is unaffected.

.github/copilot-instructions.md

@@ -2,15 +2,15 @@
 
 Repository conventions for GitHub Copilot (and any other AI agent reading this file).
 
-The **canonical guide is [AGENTS.md](../AGENTS.md)** at the repo root - read it first, including the [PR Review Etiquette](../AGENTS.md#pr-review-etiquette) review-loop contract this file's runbook implements. This file is intentionally narrow: commit/PR-title conventions (summarized inline so VS Code's commit-message and PR-title generators have them), guidance for reviewing carried fleet content, plus the GitHub Copilot Review Runbook.
+The **canonical guide is [AGENTS.md](../AGENTS.md)** at the repo root - read it first, then the [PR Review Etiquette](../GOVERNANCE.md#pr-review-etiquette) review-loop contract this file's runbook implements. This file is intentionally narrow: commit/PR-title conventions (summarized inline so VS Code's commit-message and PR-title generators have them), guidance for reviewing carried fleet content, plus the GitHub Copilot Review Runbook.
 
 For code-style rules, see [`CODESTYLE.md`](../CODESTYLE.md) at the repo root - one guide with a General section plus a section per language the repo uses.
 
-Do not duplicate language-specific rules here. **Project-specific conventions and API/behavioral contracts also belong in [AGENTS.md](../AGENTS.md), not here** - this file is intentionally limited to the inline commit/PR-title summary, the guidance for reviewing carried fleet content, and the GitHub Copilot Review Runbook. Non-Copilot agents (Claude Code, Codex, Cursor, ...) are not directed to this file and don't read it by default, so any rule a reviewer must honor has to live in `AGENTS.md` to be provider-independent.
+Do not duplicate language-specific rules here. **Project-specific conventions and API/behavioral contracts also belong in [GOVERNANCE.md](../GOVERNANCE.md), not here** - this file is intentionally limited to the inline commit/PR-title summary, the guidance for reviewing carried fleet content, and the GitHub Copilot Review Runbook. Non-Copilot agents (Claude Code, Codex, Cursor, ...) are not directed to this file and don't read it by default, so any rule a reviewer must honor has to live in `AGENTS.md` to be provider-independent.
 
 ## Commit Messages and Pull Request Titles
 
-Summarized for VS Code's generators; the full rules, rationale, and examples are in [AGENTS.md "Pull Request Title and Commit Message Conventions"](../AGENTS.md#pull-request-title-and-commit-message-conventions).
+Summarized for VS Code's generators. The full rules, rationale, and examples are in [GOVERNANCE.md "Pull Request Title and Commit Message Conventions"](../GOVERNANCE.md#pull-request-title-and-commit-message-conventions).
 
 - Imperative subject, <= 72 characters, no trailing period; optional blank-line-separated body for the non-obvious *why*.
 - US English, title case with lowercase short bind words; no vague titles, no `Co-Authored-By:` unless asked, no release-bump magnitude (NBGV handles versioning). Dependabot's `Bump X from Y to Z` titles are fine.
@@ -27,9 +27,9 @@ Two constraints follow when reviewing that content.
 
 ## GitHub Copilot Review Runbook
 
-> This runbook implements the [AGENTS.md "PR Review Etiquette"](../AGENTS.md#pr-review-etiquette) review-loop contract for GitHub Copilot. Without it in-repo, an agent has no pointer to the reliable Copilot mechanics and falls back to known-broken paths (the no-op `POST /requested_reviewers`, the wrong bot-login filter). In the API snippets below, fill the `<owner>` / `<repo>` / `<N>` placeholders.
+> This runbook implements the [GOVERNANCE.md "PR Review Etiquette"](../GOVERNANCE.md#pr-review-etiquette) review-loop contract for GitHub Copilot. Without it in-repo, an agent has no pointer to the reliable Copilot mechanics and falls back to known-broken paths (the no-op `POST /requested_reviewers`, the wrong bot-login filter). In the API snippets below, fill the `<owner>` / `<repo>` / `<N>` placeholders.
 
-Use this section for provider-specific mechanics. The expected review loop *contract* (request review on every push, verify head-SHA coverage, triage findings, reply + resolve, escalate when stuck) is defined in [AGENTS.md -> PR Review Etiquette](../AGENTS.md#pr-review-etiquette). This section only describes how to make GitHub Copilot reliably execute it.
+Use this section for provider-specific mechanics. The expected review loop *contract* (request review on every push, verify head-SHA coverage, triage findings, reply + resolve, escalate when stuck) is defined in [GOVERNANCE.md -> PR Review Etiquette](../GOVERNANCE.md#pr-review-etiquette). This section only describes how to make GitHub Copilot reliably execute it.
 
 ### Triggering and Polling
 
@@ -135,7 +135,7 @@ If a review did not run on the current head, retry:
 
 ### Reply and Thread Resolution Workflow
 
-Every id below is captured from a live query into a variable and passed from there - never hand-typed, guessed, or pasted as a `PRRT_...` literal. A node id resolves globally, so a fabricated or stale id does not fail, it writes to a real thread on an unrelated repository. This runbook implements [AGENTS.md "Repository Boundaries and Write Safety"](../AGENTS.md#repository-boundaries-and-write-safety): write only to this repo, capture every id from a live query, and never suppress a mutation's output.
+Every id below is captured from a live query into a variable and passed from there - never hand-typed, guessed, or pasted as a `PRRT_...` literal. A node id resolves globally, so a fabricated or stale id does not fail, it writes to a real thread on an unrelated repository. This runbook implements [GOVERNANCE.md "Repository Boundaries and Write Safety"](../GOVERNANCE.md#repository-boundaries-and-write-safety): write only to this repo, capture every id from a live query, and never suppress a mutation's output.
 
 List unresolved threads. Use `first: 100` with cursor-based pagination; if `hasNextPage` is true, re-run with `after: "<endCursor>"` to retrieve the next page:
 
@@ -206,14 +206,14 @@ Issue-level Copilot comments (those in `issues/<N>/comments`) have no resolution
 Reply-body conventions:
 
 - Accepted bug/style fix: include fixing commit SHA and a one-line summary.
-- Declined style comment: cite the rule (AGENTS.md or the CODESTYLE.md language section) and the existing-tree precedent.
+- Declined style comment: cite the rule (GOVERNANCE.md or the CODESTYLE.md language section) and the existing-tree precedent.
 - Declined architecture proposal: one-sentence rationale.
 - Declined false positive on carried fleet content (a broken-link or dead-cross-reference flag inside byte-locked rule text): cite the "Reviewing Carried Fleet Content" section - the reference is intentional and the text cannot be edited locally.
 
 After the final push, sweep-resolve stale older threads for removed code paths.
 
 ## When in Doubt
 
-Read [AGENTS.md](../AGENTS.md) for this repo's conventions. For code-style rules, [`CODESTYLE.md`](../CODESTYLE.md) (its General section plus the relevant language section) is authoritative. Don't restate any of these files' rules in commit bodies or PR descriptions - keep those focused on the change itself.
+Read [AGENTS.md](../AGENTS.md) to find the section that governs your change, and [GOVERNANCE.md](../GOVERNANCE.md) for the rule text itself. For code-style rules, [`CODESTYLE.md`](../CODESTYLE.md) (its General section plus the relevant language section) is authoritative. Don't restate any of these files' rules in commit bodies or PR descriptions - keep those focused on the change itself.
 
-If you find a gap in the governance itself (this file or AGENTS.md is out of date, a rule is missing, something bit this repo and would bite the next), fix it in the governance docs as part of your change rather than only working around it locally.
+If you find a gap in the governance itself (this file, AGENTS.md, or GOVERNANCE.md is out of date, a rule is missing, something bit this repo and would bite the next), fix it in the governance docs as part of your change rather than only working around it locally.

.github/workflows/validate-task.yml

@@ -48,3 +48,19 @@ jobs:
             jq empty "$f"
           done
           python3 spec/validate.py
+
+      # Each gate in scripts/ is proven by a case that reintroduces the fault it catches.
+      # Standard library only, so no install step and no dependency to pin.
+      - name: Run script self-tests step
+        run: |
+          set -Eeuo pipefail
+          python3 scripts/test_prose_lint.py
+          python3 scripts/test_repo_gate.py
+
+      - name: Check repo gates step
+        run: python3 scripts/repo_gate.py
+
+      # The charset and duplicate-word rules are clean tree-wide, so they gate. The semicolon
+      # rule stays warn-only: going green needs the sweep the prose rule itself forbids.
+      - name: Check prose step
+        run: python3 scripts/prose_lint.py . --check ascii --check dupword