agentsclimarketplace

Update module memory

Skill Karthick-Ramachandran/persist-os/.agents/skills/update-module-memory

Local-first CLI that gives your repo durable, AI-ready memory - features, ADRs, modules, architecture, standards & tests and a deterministic doctor that validates health, evidence & drift.

Install
npx -y skills add Karthick-Ramachandran/persist-os --skill update-module-memory

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

  • 8 stars8 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

SKILL.md

2.0 KB, as published. Nobody here has run it

Skill: Update Module Memory

Purpose

Keep module docs accurate so agents do not rediscover ownership, boundaries, tests, and decisions.

Inputs

  • Changed module or feature.
  • Implementation summary.
  • Test results.
  • Architecture or ADR changes.

Required Reading

  • docs/60-engineering/ENGINEERING_STANDARDS.md
  • docs/ai/MODULE_DELIVERY_WORKFLOW.md
  • Relevant docs/30-modules/<module>/MODULE.md
  • Relevant docs/30-modules/<module>/DECISIONS.md
  • Relevant feature docs and ADRs.

Output Files

  • docs/30-modules/<module>/MODULE.md
  • docs/30-modules/<module>/TASKS.md
  • docs/30-modules/<module>/TEST_PLAN.md
  • docs/30-modules/<module>/DECISIONS.md

Process

  1. Identify affected modules.
  2. Confirm module memory is linked to feature delivery docs when the module is new or materially changed.
  3. Update module purpose, responsibilities, non-responsibilities, public interfaces, and boundaries when behavior changes.
  4. Update task status only when supported by completion evidence.
  5. Update test expectations when risks or behavior change.
  6. Record decisions or link ADRs when architecture changes.
  7. Avoid copying full feature docs into module docs.

Stop Conditions

Stop and request human decision if:

  • Module ownership is unclear.
  • A change crosses module boundaries without architecture review.
  • Module memory updates would conflict with engineering standards.
  • A decision belongs in an ADR instead of a module note.
  • Feature delivery docs are missing for new module work.

Quality Bar

  • Module docs are concise and current.
  • Boundaries are clear.
  • Test expectations are actionable.
  • Decisions link to ADRs where appropriate.
  • Future agents can tell what the module owns and what it must not own.

Keep looking

Skills are one crate of 328,083. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.