chore(agents): add maintaining-agents-files Agent Skill

[fbeaudoincoveo]

What's All This Then?

This PR is a follow up to #7133

Now that we have nice and clean AGENTS.md files for the root and the Atomic package, we need to be able to easily maintain them.

This new maintaining-agents-files Agent Skill can be leveraged by AI agents to verify that each AGENTS.md file in the repository has:

• Valid commands in the Commands section
• Accurate directory representation in the Structure section
• Up-to-date dependency major versions in the Technology section
• Overall correct structure (correct sections, correct structure in each section, no more than 200 lines, etc.)

These checks are not necessarily deterministic, but should help us maintain correct AGENTS.md across the monorepo.

The agent using the skill will not make any changes to the AGENTS.md files but will make recommendations.

Research has demonstrated that AGENTS.md should be very focused, minimal, and should not be written by AI agents. So the goal of this skill is not for AI agents to write our AGENTS.md files but to assist us in keeping them up-to-date with reality and consistent (focus is on information veracity and pattern correctness).

Next Steps

In upcoming PRs, I will:

• Get rid of all .instructions.md files (I already extracted most of the important generic infromation into the proper AGENTS.md, but there's still a lot of info that should be kept and put into Agent Skills).
• Get rid of all .prompt.md files (these will be reworked as Agent Skills).
• Add assuming-personas Agent Skill: this one will enable agents to pick the best expert persona for the job at hand.
• Remove all .agent.md files (we will no longer need them with the assuming-personas Agent Skill)
• Rename .claude folder to .agents, update opencode.json config, and update all references in AGENTS.md and Agent Skills

https://coveord.atlassian.net/browse/KIT-5488

[github-actions]

⚠️ Secrets Reference Detected in Workflow Changes

This pull request modifies GitHub Actions workflow files and includes references to secrets.

Please ensure:

• The secret is properly configured in the repository/organization settings
• The secret name follows naming conventions
• The secret is not being exposed in logs or outputs
• Access to the secret is appropriately scoped

Why am I seeing this?

This comment is automatically added when workflow changes include the word secrets to remind reviewers to verify proper secret handling.

[github-actions]

🔗 Scratch Orgs ready to test this PR:

• ✅ LWS Enabled: Open Org
• ✅ LWS Disabled: Open Org

[Copilot]

Pull request overview

Adds a new Agent Skill intended to guide auditing and maintenance of AGENTS.md files across the monorepo (KIT-5488), by defining a repeatable verification process and section-by-section rules.

Changes:

• Introduces a new .claude/skills/maintaining-agents-files/ skill with a documented audit workflow.
• Defines expected AGENTS.md section structure for root vs package files and concrete verification rules for Commands/Structure/Technology/Principles/Boundaries.
• Adds general constraints for keeping AGENTS.md files concise and non-duplicative.

[Copilot]

The skill description says it verifies the Principles section for AGENTS.md files, but package-level AGENTS.md files in this repo don’t include a Principles section (see “Expected Sections” below). This inconsistency can cause the skill to incorrectly report missing Principles for package AGENTS.md files; consider scoping Principles verification to root AGENTS.md only and adjusting the frontmatter description accordingly.

Suggested change

description: Audits AGENTS.md files in the monorepo for accuracy by verifying Commands, Structure, Technology, Principles, and Boundaries sections against reality (filesystem, package.json). Use when asked to maintain, audit, verify, or update AGENTS.md files, or when checking if agent documentation is stale or out-of-date.

description: Audits AGENTS.md files in the monorepo for accuracy by verifying Commands, Structure, Technology, and Boundaries sections against reality (filesystem, package.json) for all AGENTS.md files, and verifying the Principles section for the root AGENTS.md only. Use when asked to maintain, audit, verify, or update AGENTS.md files, or when checking if agent documentation is stale or out-of-date.

[Copilot]

“### Principles” currently states “Verify: Section exists…”. Since package AGENTS.md files are not expected to have Principles, this rule should explicitly apply only to the root AGENTS.md (or clarify that Principles is optional for package files) to avoid false positives during audits.

Suggested change

	**Verify:** Section exists, both groups present. Do not evaluate whether principles are "correct" — they are human-authored values.
	**Verify:** For the **root `AGENTS.md` only**, the Principles section must exist and both groups must be present. For **package `AGENTS.md` files**, this section is optional; if present, ensure both groups are present. Do not evaluate whether principles are "correct" — they are human-authored values.

[Copilot]

The phrasing “List ls the directory” is grammatically awkward; consider rewording to something like “List the directory with ls …” or “Run ls in the directory …” for clarity.

Suggested change

	| Directories on disk | List `ls` the directory (ignore `node_modules`, `dist`, `.git`, `.turbo`, `coverage`) |
	| Directories on disk | List the directory with `ls` (ignore `node_modules`, `dist`, `.git`, `.turbo`, `coverage`) |