Rebrand canonical tagline to the deterministic merge gate

[pengfei-threemoonslab]

Summary

• Brand-wide canonical-tagline replacement — Local-first, static Tool-Use Readiness release gate for AI agent tool surfaces → The deterministic merge gate for AI-generated agent capability changes (the "Merge Gate" repositioning). Atomic across every contract-enforced surface (tests/test_public_surface_contract.py) plus all remaining repo-wide occurrences. Engine/logic unchanged — copy and positioning only.
• README gains a hero headline ("Your coding agent changed what your AI agent can do — Agents Shipgate tells you whether it can merge."), a local-first/static trust sub-line, and a verify-first quickstart; the design-partner CTA is reframed to "bring us one AI-generated PR."
• Kept "Tool-Use Readiness" as the category/wedge and the "Tool-Use Readiness Report" artifact name — only the one-sentence tagline changed. The standalone category phrase "Tool-Use Readiness release gate" intentionally stays.

Reviewer notes:

• Generated surfaces were regenerated from source, not hand-edited: the four block renderers + adoption-kits/*/SKILL.md → .cursor/rules/agents-shipgate.mdc, both committed SKILL.md copies, the slash command, and benchmark templates. SHA snapshots in tests/test_agent_instructions_renderers.py and prior_render_sha256 in the kit metadata were bumped accordingly.
• The report/packet disclaimer copy embeds the tagline, so all samples/*/expected/{report.md,packet.md,packet.json,packet.html} goldens were regenerated via run_scan (byte-exact to the golden tests). No schema version change.
• llms-full.txt regenerated via scripts/build-llms-full.py.
• Release vehicle (v0.11 minor vs v1.0) is a separate decision and is not part of this PR.

Type

• Check or risk-model change
• Input adapter change
• CLI or GitHub Action behavior — --help / scan docstring copy only
• Report, schema, or SARIF output — report/packet disclaimer copy only (no schema change)
• Documentation only — not only docs; also touches CLI help + report copy

Verification

CI is authoritative for python -m ruff check ., python -m compileall -q src tests, and python -m pytest.

Additional local checks run:

• python -m pytest → 2368 passed, 4 skipped, 0 failed
• python -m pytest tests/test_public_surface_contract.py (brand enforcer) → green
• python scripts/generate_schemas.py --check → clean
• python -m ruff check . → clean
• Repo-wide sweep for the old tagline sentence → 0 occurrences

Release-readiness notes

• No user-code import added to default scan paths
• No network access added to default scan paths
• New or changed check IDs are documented in docs/checks.md — N/A (no check changes)
• Report/schema changes are additive or documented in STABILITY.md — disclaimer copy only; report/packet schema versions unchanged

🤖 Generated with Claude Code