// Summarizes session work for commit messages or branch reviews. Queries the OpenCode server API to find and read sessions, extract major changes, bug fixes, challenges requiring multiple iterations, and code review fixes. Load before committing or when preparing to document completed work.
| name | summarize-work |
| description | Summarizes session work for commit messages or branch reviews. Queries the OpenCode server API to find and read sessions, extract major changes, bug fixes, challenges requiring multiple iterations, and code review fixes. Load before committing or when preparing to document completed work. |
Generate meaningful summaries of work completed in one or more sessions. Use for commit messages, PR descriptions, or documenting what happened across a time period.
OpenCode exposes session data through its HTTP server. The server runs automatically when OpenCode is active.
Discover the server URL with:
OPENCODE_URL=$(curl -sf http://localhost:4096/global/health | jq -r '.version' > /dev/null && echo "http://localhost:4096")
Default is http://localhost:4096. All endpoints below are relative to this base URL.
See references/api.md for the full endpoint reference. The key endpoints for summarization:
Discover sessions across all projects:
curl -sf "$OPENCODE_URL/global/session?roots=true&limit=20" | jq '.[] | {id, title, project: .project.worktree}'
Query parameters: directory, roots, start, search, limit, archived.
Discover sessions for the current project:
curl -sf "$OPENCODE_URL/session?roots=true&limit=20" | jq '.[] | {id, title}'
Query parameters: directory, roots, start, search, limit.
Read a session's messages:
curl -sf "$OPENCODE_URL/session/<SESSION_ID>/message" | jq '[.[] | {role: .info.role, parts: [.parts[] | select(.type == "text") | .text[:1000]]}]'
Get a session's todos:
curl -sf "$OPENCODE_URL/session/<SESSION_ID>/todo" | jq '.[] | {content, status, priority}'
If the server is unreachable (e.g. OpenCode not running), query the database directly at ~/.local/share/opencode/opencode.db. Tables: session, message, todo. Columns mirror the API response shapes. Use json_extract() for JSON fields.
?start=<ms> to filter by time.?roots=true for session discovery.?archived=true to include them./global/session returns sessions across all projects with project metadata. /session returns sessions for the current project only.Read the user's request to decide which endpoint to use. Default to the current project unless the request asks for more.
| Request | Endpoint |
|---|---|
| "summarize this session" | Use conversation history already in context. Do not query the API. |
| "summarize my last session" | GET /session -- current project. |
| "summarize today's sessions" | GET /session?start=<today_ms> -- current project. |
| "summarize this morning" | GET /session?start=<today_ms> -- current project, filter by time. |
| "summarize all my work this morning" | GET /global/session?start=<today_ms> -- all projects. |
| "what did I do today across repos" | GET /global/session?start=<today_ms> -- all projects. |
| "summarize the bonk sessions" | GET /global/session?search=bonk -- all projects. |
| "summarize sessions in this repo" | GET /session -- current project. |
If the user says the summary is incomplete or asks "what about X?", widen scope and re-query.
- [ ] Gather context (session history + git state)
- [ ] Categorize changes
- [ ] Generate summary
Current session: Use the conversation history already in context.
Other sessions: Determine scope (above), then query the appropriate endpoint. For each substantive session (more than 2 messages), read messages via /session/:id/message. Supplement with todo data via /session/:id/todo if the text alone is unclear.
For repo-scoped requests, also check git state:
git diff --stat
git diff --cached --stat
git log --oneline origin/main..HEAD 2>/dev/null || git log --oneline origin/master..HEAD
Group into these categories (skip empty ones):
| Category | Examples |
|---|---|
| Features | New endpoints, UI components, CLI commands |
| Fixes | Edge case handling, validation, error corrections |
| Refactors | Extractions, simplifications, performance |
| Challenges | Issues requiring 3+ attempts, debugging sessions |
| Review fixes | Changes made from code review feedback |
Write like a colleague giving a verbal recap. Mix prose and bullets naturally.
Commit messages: One subject line, a sentence of context in the body, a few bullets if there were multiple meaningful changes. Most commits don't need bullets.
PR summaries: Open with the goal and outcome in prose. Bullet the major functional changes. Skip what the diff already makes obvious.
Cross-project summaries: Group by project or theme. A short prose paragraph per group reads better than a flat list of bullets across unrelated repos.
| Context | Shape |
|---|---|
| Single commit | 1-3 sentences, maybe a couple bullets. No headers. |
| Multi-commit session | Paragraph of context + grouped bullets. |
| Feature branch | Prose intro + bullets per component. Include challenges if significant. |
| Cross-session / cross-project | Paragraph per project or theme, bullets within each. |
Manages GitLab merge requests, CI/CD pipelines, and issues via glab CLI. Load before running glab commands, creating MRs, debugging pipeline failures, checking CI status, or any GitLab operation. Triggers on "merge request", "pipeline", "CI failure", "glab", or when git remote contains "gitlab".
Audits a codebase for unnecessary complexity -- premature abstractions, deep nesting, inconsistent patterns, and indirection that hurts readability. Use when asked to simplify code, audit complexity, reduce cognitive load, or review maintainability. Triggers: simplify, complexity audit, too complex, hard to read, maintainability review.
Reviews, improves, and iterates on system prompts and LLM instructions. Load when writing, rewriting, reviewing, or optimizing a system prompt, agent prompt, tool description, skill description, or any LLM instructions. Triggers on "prompt engineering", "improve this prompt", "make this more LLM-friendly", or any block of instructions to refine. Applies structured analysis to maximize instruction clarity and model compliance.
Manages PlanetScale databases via MCP server or pscale CLI. Load before running pscale commands, using PlanetScale MCP tools, debugging connection errors, or analyzing slow queries.