chore(release): prepare MCP 1.0.24

[escott-]

Bumps the workspace, npm package, MCP Registry metadata and the boundary self-test to 1.0.24, and adds the 1.0.24 changelog.

What ships (2 commits since v1.0.23):

• Agent Coach Kit tool text: the workflow, workflow_save and workflow_delete descriptions and the /coach server instructions describe the coaching behaviour instead of commanding replies and approvals. ChatGPT's permission card for the first workflow_save call warned "Suspicious Instruction" because of that wording. The tools, their parameters and their behaviour are unchanged (ad73c8d)
• Repository only: the same rewording in the Codex Cloud skill, the AGENTS snippet and the ChatGPT plugin skill, and the plugin signs in with ChatGPT's Client ID Metadata Document (5527e2b)

No dependency changes.

Checked on ovh-desktop against main ad73c8d plus this change:

• cargo fmt --all --check; cargo clippy --locked --workspace --all-targets -- -D warnings
• cargo test --locked --workspace --all-targets: 3279 passed, 0 failed, 21 ignored
• account_connection_smoke: 9 tests
• cargo audit --deny warnings (403 crates, no advisories) and cargo deny --locked check
• On a clean archive: release_contract metadata and resolve-version for tag v1.0.24, public_boundary, the four script tests, the adoption and grounding tests, npm test (6 passed)
• The gate binary on /coach, over stateless and legacy transports: exactly the three tools, none of the six flagged phrases in any description or in the instructions returned by initialize and server/discover, the replacement wording present, identical input schemas; the published 1.0.23 fails the 7 wording checks. Lengths: workflow 1332 to 1331, workflow_save 2054 to 2054, workflow_delete 513 to 518, instructions 739 to 737 (the commit message says no description grows; workflow_delete grows by 5, which no limit covers, and the changelog says so)

Release binaries, wire diff, HTTP smoke and real-binary checks come next, before the tag.

🤖 Generated with Claude Code

---

^{Need help on this PR? Tag @codesmith-bot with what you need.}

[claude]

⚠️ Code review skipped — your organization has no extra usage available to pay for this review.

If your organization's extra usage balance is empty, an organization admin can add extra usage credits at claude.ai/admin-settings/usage. If its monthly spend limit was reached, an admin can raise it on the same page. If neither applies, contact Anthropic support.

Once extra usage is available, someone with write access to this repository can comment @claude review on this pull request to trigger a review.