session-commit

Capture learnings from the current coding session and update AGENTS.md. Use when the user asks to close the loop, run session-commit, record best practices, or update agent instructions based on recent work.

Safety Notice

This listing is imported from skills.sh public index metadata. Review upstream SKILL.md and repository scripts before running.

Copy this and send it to your AI assistant to learn

Install skill "session-commit" with this command: npx skills add olshansk/agent-skills/olshansk-agent-skills-session-commit

Session Commit

Analyze the current coding session, propose improvements to AGENTS.md, and apply approved changes.

Available scripts

  • scripts/preflight.sh - Checks whether required instruction files exist and optionally repairs missing files.

Workflow

  1. Run preflight checks:
bash scripts/preflight.sh
  1. If preflight fails and user approves repairs, run:
bash scripts/preflight.sh --fix
  1. Read the current AGENTS.md and build a mental map of existing sections.
  2. Extract only durable learnings from the current session.
  3. Propose changes using the format in references/change-proposal-format.md.
  4. Wait for explicit user approval before applying any edits.
  5. Apply approved changes and merge with existing content.

What to capture

  • Coding patterns and conventions established in the session
  • Architecture decisions and reasoning that should persist
  • Debugging playbooks and recurring gotchas
  • Workflow preferences that improve future sessions

Guardrails

  • Do not capture transient implementation details that will age quickly.
  • Prefer updating existing sections before creating new headings.
  • Use concise bullet points rather than long paragraphs.
  • Keep guidance tool-agnostic unless behavior differs by tool.
  • If no meaningful learning occurred, report that and stop.

Pointer file behavior

If CLAUDE.md, CODEX.md, or GEMINI.md are missing or empty, create symlinks that point to AGENTS.md.

Output contract

  • Proposal stage: output only proposed changes with explicit add/modify/remove counts.
  • Apply stage: update AGENTS.md only after explicit approval.
  • Completion stage: summarize what changed and where.

Source Transparency

This detail page is rendered from real SKILL.md content. Trust labels are metadata-based hints, not a safety guarantee.

Related Skills

Related by shared tags or category signals.

Automation

skills-dashboard

No summary provided by upstream source.

Repository SourceNeeds Review
Automation

cmd-rss-feed-generator

No summary provided by upstream source.

Repository SourceNeeds Review
Automation

cmd-idiot-proof-docs

No summary provided by upstream source.

Repository SourceNeeds Review