agentlog
/agentlog
Przegląda, synchronizuje i analizuje aktywność wielu agentów na wielu urządzeniach (Claude Code, Codex, Cursor, Maestri, browser-use) w puli synchronizowanej przez GitHub oraz tworzy skondensowany dokument kontekstu projektu.
- Autor
- yrzhe ↗
- Repozytorium
- claude-skills ↗
- Licencja
- MIT
- Ostatnia zmiana repozytorium
- 27.10.2026
Ocena i bezpieczeństwo
- Pliki w paczce
- 49
- Skrypty
- 35
- Komentarze HTML
- 0
- Adresy URL w SKILL.md
- 0
Brak sygnałów. Repozytorium zmienione 27.10.2026, bez odwołań do wycofanych modeli i API.
MIT, otwarta: można używać i zmieniać, z zachowaniem informacji o autorze.
- 35 skryptów w paczce. Przejrzyj je przed instalacją, bo Claude może je uruchomić.
Skrypty: 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
Co robi i kiedy
Przegląda, synchronizuje i analizuje aktywność wielu agentów na wielu urządzeniach (Claude Code, Codex, Cursor, Maestri, browser-use) w puli synchronizowanej przez GitHub oraz tworzy skondensowany dokument kontekstu projektu.
Wyzwalacze z opisu
Oryginalny opis (EN)
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
Jak działa
- Boundaries (when NOT to use)
- Architecture
- Setup
- Common flows
- Reference index
- When extending
- Status
Podgląd SKILL.md
---
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.
Pliki w paczce (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
Wersje
W bazie nie ma innych skilli o nazwie agentlog.
Migawka bazy z 13.11.2026 · wersja paczki a4047ec84b21 (skrót SHA-256 całej paczki)
Pobrania w ostatnich 30 dniach: 0 · ranking
Zgłoś problem z tym skillem: szkodliwa treść, błędny opis albo prośba autora o usunięcie.
Podobne skille
- 100agent-smith
Projektuje, tworzy, recenzuje, migruje i waliduje Agent Skills, agentów, hooki, pluginy i marketplace dla Claude Code, Codex i Cursor oraz synchronizuje wiele harnessów. - 100agent-sync
Synchronizuje pliki konfiguracji agentów kodujących tak, by AGENTS.md było źródłem prawdy, a CLAUDE.md i instructions.md dowiązaniami symbolicznymi, ze wspólnymi skillami i poleceniami dla Claude, Codex, Cursor i opencode. - 100agents-md-author
Tworzy lub aktualizuje pliki instrukcji dla agentów AI (AGENTS.md dla Codex, CLAUDE.md dla Claude Code lub oba) na podstawie struktury projektu, w tym polecenia dev, test i build. - 95but-agentlog
Przegląda wcześniejszą pracę agentów dla gałęzi GitButler z zapisów agentlog, żeby odtworzyć kontekst zmian. - 100party
Zakłada wspólny kanał dla wielu sesji agentów AI i ich użytkowników, takich jak Claude Code, Cursor czy Codex, działających na jednej lub wielu maszynach, i pozwala do niego dołączać. - 100agents-md-starter
Tworzy lub ulepsza AGENTS.md oraz CLAUDE.md, żeby Claude Code, Codex, Cursor i Gemini CLI korzystały z jednego zestawu zasad.