agentlog
/agentlog
Load when the user wants to view, sync, or analyze multi-agent activity across multiple devices — Claude Code / Codex / Cursor / Maestri / browser-use sessions captured to a shared GitHub-synced pool, OR wants a distilled per-project context document so a fresh agent in a different tool can pick up where another left off. Triggers on "agentlog X" commands, "what did I do today across all my agents", "show me my pool", "sync the pool", "拉一下另一台机器上的 agent 记录", "看看 vps 上跑的", "跨设备 agent log", "跨工具上下文", "switch from Codex to Claude Code", "AGENTS.md / CLAUDE.md", "项目状态文档", "agent context". Do NOT lo
- Author
- yrzhe ↗
- Repository
- claude-skills ↗
- Licence
- MIT
- Last repository change
- 27.10.2026
Assessment and security
- Files in this package
- 49
- Scripts
- 35
- HTML comments
- 0
- URLs in SKILL.md
- 0
No signals detected. Repository changed on 27.10.2026, without references to retired models or APIs.
MIT, open: use and modify while retaining author attribution.
- 35 scripts in this package. Review them before installing, as Claude may execute them.
Scripts: hooks/capture-claude-code.sh, src/agentlog/__init__.py, src/agentlog/__main__.py, src/agentlog/adapters/__init__.py, src/agentlog/adapters/base.py, src/agentlog/adapters/browser_use.py, src/agentlog/adapters/claude_code.py, src/agentlog/adapters/codex.py, src/agentlog/adapters/cursor.py, src/agentlog/adapters/maestri.py, src/agentlog/brief.py, src/agentlog/cli.py, src/agentlog/config.py, src/agent
What it does and when to use it
Load when the user wants to view, sync, or analyze multi-agent activity across multiple devices — Claude Code / Codex / Cursor / Maestri / browser-use sessions captured to a shared GitHub-synced pool, OR wants a distilled per-project context document so a fresh agent in a different tool can pick up where another left off. Triggers on "agentlog X" commands, "what did I do today across all my agents", "show me my pool", "sync the pool", "拉一下另一台机器上的 agent 记录", "看看 vps 上跑的", "跨设备 agent log", "跨工具上下文", "switch from Codex to Claude Code", "AGENTS.md / CLAUDE.md", "项目状态文档", "agent context". Do NOT lo
Triggers from the description
Original author description
Load when the user wants to view, sync, or analyze multi-agent activity across multiple devices — Claude Code / Codex / Cursor / Maestri / browser-use sessions captured to a shared GitHub-synced pool, OR wants a distilled per-project context document so a fresh agent in a different tool can pick up where another left off. Triggers on "agentlog X" commands, "what did I do today across all my agents", "show me my pool", "sync the pool", "拉一下另一台机器上的 agent 记录", "看看 vps 上跑的", "跨设备 agent log", "跨工具上下文", "switch from Codex to Claude Code", "AGENTS.md / CLAUDE.md", "项目状态文档", "agent context". Do NOT lo
How it works
- Boundaries (when NOT to use)
- Architecture
- Setup
- Common flows
- Reference index
- When extending
- Status
SKILL.md preview
---
name: agentlog
description: Load when the user wants to view, sync, or analyze multi-agent activity across multiple devices — Claude Code / Codex / Cursor / Maestri / browser-use sessions captured to a shared GitHub-synced pool, OR wants a distilled per-project context document so a fresh agent in a different tool can pick up where another left off. Triggers on "agentlog X" commands, "what did I do today across all my agents", "show me my pool", "sync the pool", "拉一下另一台机器上的 agent 记录", "看看 vps 上跑的", "跨设备 agent log", "跨工具上下文", "switch from Codex to Claude Code", "AGENTS.md / CLAUDE.md", "项目状态文档", "agent context". Do NOT load for single-machine tweet material capture (use `seed`) or one-off project planning.
---
# agentlog · Multi-agent, multi-device activity pool + project context layer
agentlog has two layers:
- **Layer 1 — event pool**: captures notable activity from all your AI agents (Claude Code, Codex, Cursor, Maestri, browser-use) across all your machines (Macs + VPS) into one normalized event pool, synced via a private GitHub repo.
- **Layer 2 — project context**: distills the pool into a per-project `AGENTS.md` + `CLAUDE.md` + `docs/agent-context/` snapshot, so any AI coding agent entering the project reads the same up-to-date state, decisions, and next steps.
## Boundaries (when NOT to use)
| Task | Use this instead |
|---|---|
| Capture a single Claude Code session for tweet drafting | `seed` skill |
| One-off project planning / brainstorming | `planner` / `brainstorming` |
| Team collaboration / sharing with others | (not supported in v0) |
## Architecture
```
┌─────────────────────────────────────────────────────────────┐
│ Device A (Mac) Device B (VPS) │
│ ───────────────── ───────────────── │
│ Claude Code Claude Code │
│ Codex Codex │
│ Maestri canvas (scripts) │
│ browser-use │
│ ↓ ↓ │
│ agentlog adapters agentlog adapters │
│ ↓ ↓ │
│ ~/.agent-seeds/ ~/.agent-seeds/ │
│ (local pool clone) (local pool clone) │
│ ↓ ↓ │
│ └──── GitHub (private repo) ────┘ │
└─────────────────────────────────────────────────────────────┘
```
Each agent → adapter → local pool shard → GitHub. Other devices pull. Everyone sees a unified feed.
## Setup
Detailed: `references/setup.md`. Quick version:
```bash
gh repo create agent-seeds --private --confirm
agentlog init --repo git@github.com:YOUR_USER/agent-seeds.git
agentlog poll --once --source claude_code # smoke test
```
On each additional device: same `agentlog init` command. Pool syncs via GitHub.
## Common flows
### See what I did across all agents today
```bash
agentlog recap
```
### Live feed of last 4 hours, all sources
```bash
agentlog pool --last 4h
```
### Group view by project / agent / source
```bash
agentlog pool --by project
agentlog recap --by agent
```
### Pull everything from other machines now
```bash
agentlog pull
```
### Push current local changes immediately
```bash
agentlog push --force
```
### Manually log an event from a script
```bash
agentlog event push '{"action":{"type":"checkpoint","status":"completed","label":"deploy success"},"summary":"shipped api v2"}'
```
### Distill a project's recent activity into a context document (Layer 2)
```bash
agentlog context init --project-root .
agentlog brief --project agentlog --last 7d
```
Writes `AGENTS.md` + `CLAUDE.md` + `docs/agent-context/{state,decisions,next-steps}.md` so the next agent (Cursor / Codex / Claude Code) entering the project reads a unified state. Requires `ANTHROPIC_API_KEY`.
### Re-sync entry-file blocks after manually editing state
```bash
agentlog context sync
```
### Migrate historical seed data (one-time)
```bash
agentlog migrate-from-seed --dry-run
agentlog migrate-from-seed
```
### Run the background daemon (auto poll + sync)
```bash
agentlog daemon install # macOS launchd or Linux systemd
agentlog daemon start
```
## Reference index
| File | Covers |
|---|---|
| `references/cheatsheet.md` | **Start here** — one-page mental model: commands, capture modes, push rhythm, file layout, schema |
| `references/setup.md` | Full multi-device install, GitHub remote, env vars, daemon install |
| `references/troubleshooting.md` | Common install / sync failures with root-cause + fix (UNKNOWN-0.0.0, command not found, SSH publickey, hostname collision, Cursor adapter blank) |
| `references/cli-reference.md` | Every CLI command with examples |
| `references/cursor-adapter.md` | Cursor IDE SQLite storage layout, action-type mapping, schema-drift handling |
| `references/brief.md` | Haiku distill prompt contract, event selection, idempotency rules |
| `references/context-contract.md` | AGENTS.md + CLAUDE.md double-write, decisions append-only, decision entry format |
For schema details read `src/agentlog/schema.py` directly — the type hints + validate() are the source of truth.
## When extending
- Adding a new source → implement `SourceAdapter` interface (`src/agentlog/adapters/base.py`), register in `_ADAPTER_REGISTRY` in `src/agentlog/cli.py`
- Changing event schema → bump `SCHEMA_VERSION` in `src/agentlog/schema.py` and write a converter
- Adding a CLI command → wire into `build_parser()` in `src/agentlog/cli.py`
## Status
v0 — schema + pool + 5 adapters (claude_code, codex, cursor, maestri, browser_use) + GitHub sync + daemon + shot + recap + Layer 2 (brief + context). Tests: 59 passing.
Files in this package (49)
- .gitignore 1 KB
- CHANGELOG.md 2 KB
- README.md 5 KB
- SKILL.md 6 KB
- pyproject.toml 1 KB
- .claude-plugin/plugin.json 1 KB
- hooks/capture-claude-code.sh 1 KB
- references/brief.md 3 KB
- references/cheatsheet.md 8 KB
- references/cli-reference.md 4 KB
- references/context-contract.md 3 KB
- references/cursor-adapter.md 3 KB
- references/setup.md 8 KB
- references/troubleshooting.md 7 KB
- scripts/agentlog 1 KB
- src/agentlog/__init__.py 1 KB
- src/agentlog/__main__.py 1 KB
- src/agentlog/brief.py 8 KB
- src/agentlog/cli.py 27 KB
- src/agentlog/config.py 3 KB
- src/agentlog/context.py 7 KB
- src/agentlog/daemon.py 6 KB
- src/agentlog/migrate_seed.py 5 KB
- src/agentlog/pool.py 7 KB
- src/agentlog/reader.py 6 KB
- src/agentlog/recap.py 4 KB
- src/agentlog/schema.py 8 KB
- src/agentlog/shot.py 7 KB
- src/agentlog/sync.py 16 KB
- src/agentlog/adapters/__init__.py 1 KB
- src/agentlog/adapters/base.py 3 KB
- src/agentlog/adapters/browser_use.py 12 KB
- src/agentlog/adapters/claude_code.py 19 KB
- src/agentlog/adapters/codex.py 26 KB
- src/agentlog/adapters/cursor.py 12 KB
- src/agentlog/adapters/maestri.py 12 KB
- tests/test_adapter_browser_use.py 4 KB
- tests/test_adapter_claude_code.py 6 KB
- tests/test_adapter_codex.py 5 KB
- tests/test_adapter_cursor.py 6 KB
- tests/test_adapter_maestri.py 5 KB
- tests/test_brief.py 6 KB
- tests/test_context.py 4 KB
- tests/test_migrate_seed.py 3 KB
- tests/test_pool.py 3 KB
- tests/test_reader.py 5 KB
- tests/test_schema.py 3 KB
- tests/test_shot.py 3 KB
- tests/test_sync.py 5 KB
Versions
The database has no other skills named agentlog.
Database snapshot: 13.11.2026 · package version a4047ec84b21 (SHA-256 digest of the entire package)
Downloads in the last 30 days: 0 · ranking
Report a problem with this skill: harmful content, incorrect descriptions or an author’s removal request.
Similar skills
- 100agent-smith
Architect, create, review, migrate, validate, and maintain Agent Skills, agents, hooks, plugins, and marketplaces for Claude Code, Codex, and Cursor. Use when building or auditing an agent capability layer or keeping multiple harnesses in sync. - 100agent-sync
Syncs coding agent config files so AGENTS.md is source of truth and CLAUDE.md/instructions.md are symlinks. Ensures skills and commands are shared across Claude, Codex, Cursor, and opencode. Use when adding skills, commands, or modifying agent config. - 100agents-md-author
Bootstrap or update project AI-agent instruction files (AGENTS.md for Codex, CLAUDE.md for Claude Code, or both) from the current project's structure. Triggers on: write AGENTS.md, write CLAUDE.md, generate AGENTS.md, agent instructions, project conventions for AI, bootstrap… - 95but-agentlog
Use for prompts like \"get context for branch\", \"catch up on this branch\", \"recover branch context\", or \"what prior agent work happened here\". Skim prior agent work from `but agentlog` captures for a GitButler branch, review / pull request / merge request, or change.… - 100party
Throw or join an agents-party: a shared channel where several AI agent sessions (and their humans) talk to each other — Claude Code, Cursor, Codex or any other agent, on one machine or across machines. Use when the user asks to throw or start a party, wants several agent… - 100agents-md-starter
Creates or upgrades a repository's AGENTS.md (read by Codex, Cursor, and other agents) and a CLAUDE.md that imports it, so Claude Code, Codex, Cursor and Gemini CLI share one set of project rules. Scans the repo to detect languages, package manager, real build/test/lint…