[TueJon]

Description

Refreshes the existing webmcpify skill from its July snapshot to upstream v0.7.1, with the requested receiver adaptations.

The skill reads official guidance, pins the verification harness, scopes browser access, journals mutations before dispatch, preserves execution cancellation, and dates compatibility guidance. Workbench is now read-only in both native and simulated transports: only observed, non-excluded manifest tools marked non-mutating can run. Mutations use the host journal runner. The launcher separately asks before installing Playwright and downloading a browser; unattended use fails closed without explicit approval flags. Windows without flock/lockf has a documented read-only fallback.

Unsupported frontmatter and the ChatGPT-specific guide remain excluded. Upstream main is merged; generated changes affect only the webmcpify index row.

Validation

• npm run skill:validate: all 442 skills valid.
• npm start, line-ending normalization and git diff --check: passed.
• 12 behavioral tests: consent refusal/approval and read-only dispatch boundaries, including forced calls, both transports and imperative/declarative surfaces. Native transport is modeled in these DOM tests; no Windows browser testing is claimed.
• GitHub Copilot CLI 1.0.103: inventory plus native verify of a disposable local read-only search fixture, using Playwright 1.61.1 and headed Chrome 150.0.7871.186. Registration/schema/annotations, input-mode probing, valid result/UI delta and invalid input are checked. Earlier fixture/harness failures and the targeted corrections are recorded in the review response.

Pull Request Checklist

• Read CONTRIBUTING.md and paid-service submission guidance.
• Update an existing skill in the correct directory.
• Follow naming and content conventions.
• Run receiver validation and generation commands.
• Target main.
• Test this refresh inside GitHub Copilot.

This contribution is licensed under the MIT License and follows the repository Code of Conduct.

[github-actions]

🔒 PR Risk Scan Results

Scanned 24 changed file(s).

Severity	Count
🔴 High	0
🟠 Medium	0
ℹ️ Info	11

Severity	Rule	File	Line	Match
ℹ️	skill-script-touched	skills/webmcpify/scripts/workbench.mjs	1	skills/webmcpify/scripts/workbench.mjs
ℹ️	skill-script-touched	skills/webmcpify/templates/mutation-journal.js	1	skills/webmcpify/templates/mutation-journal.js
ℹ️	skill-script-touched	skills/webmcpify/templates/mutation-journal.ts	1	skills/webmcpify/templates/mutation-journal.ts
ℹ️	skill-script-touched	skills/webmcpify/templates/webmcp-compat.js	1	skills/webmcpify/templates/webmcp-compat.js
ℹ️	skill-script-touched	skills/webmcpify/templates/webmcp-workbench.js	1	skills/webmcpify/templates/webmcp-workbench.js
ℹ️	skill-script-touched	skills/webmcpify/templates/webmcp.d.ts	1	skills/webmcpify/templates/webmcp.d.ts
ℹ️	skill-script-touched	skills/webmcpify/templates/webmcp.spec.ts	1	skills/webmcpify/templates/webmcp.spec.ts
ℹ️	skill-script-touched	skills/webmcpify/templates/webmcpify.js	1	skills/webmcpify/templates/webmcpify.js
ℹ️	skill-script-touched	skills/webmcpify/templates/webmcpify.ts	1	skills/webmcpify/templates/webmcpify.ts
ℹ️	skill-script-touched	skills/webmcpify/tests/workbench-cli.test.mjs	1	skills/webmcpify/tests/workbench-cli.test.mjs
ℹ️	skill-script-touched	skills/webmcpify/tests/workbench.test.mjs	1	skills/webmcpify/tests/workbench.test.mjs

This is an automated soft-gate report. Findings indicate review targets and do not block merge by themselves.

[github-actions]

🔍 Vally Lint Results

✅ All checks passed

Scope	Checked
Skills	1
Agents	0
Total	1

Severity	Count
❌ Errors	0
⚠️ Warnings	0
ℹ️ Advisories	0

Summary

Level	Finding
ℹ️	✅ webmcpify (2/2 checks passed)
ℹ️	✓ [spec-compliance] All 1 skill(s) are spec-compliant.
ℹ️	✓ spec-compliance: All spec checks passed.
ℹ️	✓ [valid-refs] All file references across 1 skill(s) are valid.
ℹ️	✓ valid-refs: All file references resolve to existing files within the skill directory.
ℹ️	1 skill(s) linted, 1 passed

Full linter output

### Linting skills/webmcpify
✅ webmcpify (2/2 checks passed)
    ✓ [spec-compliance] All 1 skill(s) are spec-compliant.
        ✓ spec-compliance: All spec checks passed.
    ✓ [valid-refs] All file references across 1 skill(s) are valid.
        ✓ valid-refs: All file references resolve to existing files within the skill directory.

1 skill(s) linted, 1 passed

[TueJon]

The risk-scan package-exec-command finding is addressed in this v0.7.0 refresh: the verification harness installs exact versions and runs its checked local binary instead of npx.

[TueJon]

Addressed both review points: removed the unsupported source metadata, removed the ChatGPT-specific client reference and its remaining links, and merged the latest upstream main. All 425 skills validate, and the generated skill index is clean.

[github-actions]

🚦 Submission status: 🛠️ Requires submitter fixes

Risk tier: merge-risk:high — Privileged execution, automation, or review-policy change
Required to merge: passing submission-gate checks plus 1 approval from reviewers with write access, including a maintainer with admin or maintain permission.

Why this tier

• skills/webmcpify/scripts/workbench.mjs is a high-risk path (automation, scripts, MCP config, hooks, or review policy)
• Spawns processes or evaluates code in skills/webmcpify/scripts/workbench.mjs
• Spawns processes or evaluates code in skills/webmcpify/templates/mutation-journal.js
• Spawns processes or evaluates code in skills/webmcpify/templates/mutation-journal.ts
• Spawns processes or evaluates code in skills/webmcpify/tests/workbench-cli.test.mjs
• Spawns processes or evaluates code in skills/webmcpify/tests/workbench.test.mjs

Automated checks

Check	Status	Details
Line endings	✅ Passed	Passed · logs
Spelling	✅ Passed	Passed · logs
Generated README consistency	✅ Passed	Passed · logs
Skill validation	✅ Passed	Passed · logs
Skill lint (vally)	✅ Passed	Passed · logs
Risk scan	✅ Passed	Passed · logs
Contributor reputation	✅ Passed	Passed · logs
Duplicate resource scan	✅ Passed	Passed · logs
PR quality signal	⏭️ Skipped	Skipped by its workflow · logs

Action needed

• Address the changes requested by aaronpowell, then push an update.

Review

• Approvals: 0/1
• Assigned reviewer: not assigned yet — comment /request-review to ask for one
• Review target date: not set
• Still needed: 1 more approval(s); an approval from a maintainer with admin or maintain permission; resolution of changes requested by aaronpowell
• The core-maintainers pool is not staffed yet; an approver with admin or maintain permission is required instead.

Commands

Command	Who	What it does
/rerun-checks	PR author, maintainers	Re-runs failed or incomplete checks and re-evaluates this gate
/request-review	PR author, maintainers	Asks the review rotation to assign a reviewer (adds needs-reviewer)

_{Updated for f578f17 · gate run · This comment is maintained automatically — see submission gate docs.}

[TueJon]

Updated this existing PR to upstream v0.7.1 in e7b2ef9. Both review adaptations remain: unsupported frontmatter is excluded, and the ChatGPT-specific guide and all references to it remain removed.

The update preserves execution callback options and cancellation signals and adds dated compatibility guidance. Receiver validation passed for all 425 skills; npm start changes only the webmcpify index row, and git diff --check passed. The PR description now reflects the current files and validation.

[aaronpowell]

Thanks for the v0.7.1 refresh. Still needed: 1) Workbench must route mutations through the journal or be read-only/simulated, and references/workbench.md updated; 2) document Windows limitation (no flock/lockf) and agent fallback; 3) scripts/workbench.mjs must ask before installing Playwright; 4) test inventory + one verify in Copilot. Optional: ship only one journal helper.

[TueJon]

Addressed the four requests:

• Workbench is read-only in both transports. Mutating/unknown, excluded and expected-only tools are blocked before probing or dispatch, including forged UI/direct-call attempts. The obsolete mutation confirmation is removed and the Workbench guide is updated.
• Documented the Windows no-flock/lockf limitation and read-only/not-run fallback.
• Added separate consent for Playwright installation and browser downloads, with a default No and noninteractive refusal.
• Tested inventory and native verify in GitHub Copilot CLI 1.0.103 on a local read-only search fixture with Playwright 1.61.1 and headed Chrome 150.0.7871.186: registration/schema/annotations, JSON-string input mode, valid structured result plus UI delta, and invalid-input handling.

The first fixture attempt exposed its thrown exception instead of the documented ERROR result; a subsequent harness assertion also needed to include Chrome's default annotation. Both failures were retained; the corrected fixture/harness passed the targeted run. No native evidence is inferred from simulation.

Merged upstream main. All 442 skills validate; generation, whitespace checks and 12 focused consent/dispatch tests pass. The tests document their modeled-native and POSIX-only limits. Both journal variants are retained. Previous frontmatter/guide exclusions remain.

[aaronpowell]

Thanks @TueJon, this covers everything from the last review: Workbench is read-only with mutations routed through the journal, the Windows no-flock/lockf limitation is documented, the launcher asks before installing Playwright or downloading a browser, and you've shown an inventory + verify run in Copilot CLI. Keeping both journal variants is fine for now. Approving.