[anshita-arya]

Added ADR Watch and Review agent for review checks against Architectural Decision Records (ADRs). The agent generates a scorecard after reviewing code changes. (future work: suggesting code changes based on Review record)

Pull Request Checklist

• I have read and followed the CONTRIBUTING.md guidelines.
• I have read and followed the Guidance for submissions involving paid services.
• My contribution adds a new instruction, prompt, agent, skill, workflow, or canvas extension file in the correct directory.
• The file follows the required naming convention.
• The content is clearly structured and follows the example format.
• I have tested my instructions, prompt, agent, skill, workflow, or canvas extension with GitHub Copilot.
• I have run npm start and verified that README.md is up to date.
• I am targeting the main branch for this pull request.

---

Description

With the current industry trends in software development life cycles , the part of writing code is largely solved, this results in a lot more code being written, but the crux of SDLC still remains, which is designing the systems, making trade-off decisions to ensure aspects like scalability, reliability, and security. Software developers are becoming more like architects while code is being written by agents. Right now, senior engineers make the architecture and design decisions, and all other engineers on the team manually look at those design decisions and architectures, review them, and make sure that their output is conformant to that.

In the Agentic SDLC process, there is also often a silent design drift. Where coding agents, silently make design decisions or alter them. While still producing buildable, runnable code.

The ADR watcher and reviewer agent, build context from ADRs either in the existing repo or from different tools in the ecosystem connected through existing MCPs, verifies whether any changes in the directory are in compliance with the ADR made, and gives a scorecard accordingly.

---

Type of Contribution

• New instruction file.
• New prompt file.
• New agent file.
• New plugin.
• New skill file.
• New agentic workflow.
• New canvas extension.
• Update to existing instruction, prompt, agent, plugin, skill, workflow, or canvas extension.
• Other (please specify):

---

Additional Notes

---

By submitting this pull request, I confirm that my contribution abides by the Code of Conduct and will be licensed under the MIT License.

[github-actions]

🔒 PR Risk Scan Results

Scanned 1 changed file(s).

Severity	Count
🔴 High	0
🟠 Medium	0
ℹ️ Info	0

✅ No matching risk patterns were detected in changed files.

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

[github-actions]

🚦 Submission status: 💬 Review in progress

Risk tier: merge-risk:medium — New or substantially changed resource without privileged execution
Required to merge: passing submission-gate checks plus 1 approval from reviewers with write access.

Why this tier

• Adds 1 file(s), e.g. agents/adr-review.agent.md
• Changes 227 lines (low-risk limit is 40)

Automated checks

Check	Status	Details
Line endings	✅ Passed	Passed · logs
Spelling	✅ Passed	Passed · logs
Generated README consistency	✅ 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

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)
• No staffed reviewer pool owns these files yet; any reviewer with write access counts as the domain reviewer.

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 786ed05 · gate run · This comment is maintained automatically — see submission gate docs.}

[aaronpowell]

This isn't structured correctly for the repo.

[anshita-arya]

@aaronpowell

This isn't structured correctly for the repo.

made changes

[github-actions]

🔍 Vally Lint Results

⚠️ Warnings or advisories found

Scope	Checked
Skills	0
Agents	1
Total	1

Severity	Count
❌ Errors	0
⚠️ Warnings	0
ℹ️ Advisories	1

Summary

Level	Finding
ℹ️	Vally currently lints SKILL.md content. Agent files were detected but skipped:

Full linter output

### Agent files detected (not linted by vally)
ℹ️ Vally currently lints SKILL.md content. Agent files were detected but skipped:
agents/adr-review.agent.md

[aaronpowell]

Could you make the comparison procedure concrete before merge? In agents/adr-review.agent.md, the workflow says to check changed code against an ADR, but it never asks the agent to extract each ADR constraint, identify the relevant changed files/lines, and record evidence and a status for each constraint. Please add those steps and a fallback for missing or ambiguous ADRs. Also, the Jira/Aha retrieval in the “Connected ADR” bullet is not supported by the declared codebase, search, and edit/editFiles tools; please either specify a usable connector or remove that retrieval path and ask the user to provide the ADR. The existing ADR Generator already covers generic ADR document structure, so focus this agent on the traceable review method.

[aaronpowell]

Closing from staleness